Release version 0.2.0

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

.github/dependabot.yml

@@ -0,0 +1,6 @@
+version: 2
+updates:
+  - package-ecosystem: pip
+    directory: /
+    schedule:
+      interval: daily

.github/workflows/test.yml

@@ -24,7 +24,8 @@ jobs:
 
       - name: 📦 Install lint tools
         run: |
-          pip install ruff
+          python -m pip install --upgrade pip
+          pip install --group lint
           sudo apt-get update && sudo apt-get install -y shellcheck
           npm install -g markdownlint-cli2
 

.github/workflows/update.yml

@@ -29,7 +29,8 @@ jobs:
 
       - name: 📦 Install lint tools
         run: |
-          pip install ruff
+          python -m pip install --upgrade pip
+          pip install --group lint
           sudo apt-get update && sudo apt-get install -y shellcheck
           npm install -g markdownlint-cli2
 

.gitignore

@@ -15,6 +15,7 @@ npm-debug.log*
 # Rendered skill install targets
 .agents/
 .claude/
+.mcp.json
 
 # Editor / OS
 .DS_Store

CHANGELOG.md

@@ -0,0 +1,67 @@
+# Changelog
+
+## [0.2.0] - 2026-10-31
+
+Added:
+
+- Git: *branch-gc* clears merged branches and worktrees with *pkgmgr*
+- Agents: *subagent-model* uses a cheaper model only at 90 % same result
+- Agents: *subagent-model* hooks log every spawn and its rated quality
+
+Changed:
+
+- Coordination: never cut a running job or agent short, not even at its cap
+- Resources: *watch.py admit* grants test slots only below CPU and RAM limits
+- Coordination: a relayer writes an operator rule to shared memory first
+
+Fixed:
+
+- Resources: stop-stage cleanup now skips worktrees where *make* still runs
+- Resources: the block hook ignores heavy commands in quotes and heredocs
+- Update: *make update* now updates every locked source, not just the first
+- Update: *make update* installs for Claude Code only
+- CI: *ci-artifacts* signs lint failures by finding, ignores later steps
+- Release: *changelog* warns when a workflow on HEAD already failed
+- CI: ruff pinned in *pyproject.toml*; local and CI lint now agree
+
+Upgrade notes:
+
+- 0.1.0 was never published (its CI failed); its upgrade notes follow
+- Install: restart the agent after *make install* to load skills and hooks
+- Resources: *watch.py* needs *~/.config/agents-council/config.json*
+- Resources: add *busy_processes* and *load_limits* to that config
+
+## [0.1.0] - 2026-10-30
+
+Added:
+
+- Install: *make install* and *make project* install every locked skill
+- Install: enables caveman and ponytail; adds autotune and dream reminders
+- Commit: *commit-next* commits a bundle and stages the next one
+- Commit: *comments-clean* and *advocate* audit every commit before it lands
+- Commit: *confidence* and *break-risk* report measured fix and break numbers
+- Coordination: *democracy* elects the first agent to claim work as its owner
+- Coordination: *council.py* claims work; a hook blocks edits without a claim
+- Coordination: *funnel* keeps agent work in worktrees until it clears 90/5
+- Resources: *watch.py* blocks heavy jobs and cleans up before the disk fills
+- Cleanup: *cleanup* frees disk space after asking every peer agent
+- CI: *triage*, *observe* and *ci-artifacts* with *ci_failures.py* clustering
+- CI: *tune* finds speed-ups that never cut logic, coverage or correctness
+- Git: *merge-fix* with *find_fix.py* finds a fix on any branch and merges it
+- Reasoning: *active-listening* and *dialectic* pin requirements and causes
+- Review: *criticize* and *sceptic* give critique hardened by dialectic
+- Autonomy: *plan* hands an objective-oriented plan to *robot*
+- Quality: *test* runs Makefile targets; *--fix* loops until they are green
+- Quality: *refactor*, *no-defaults* and *scope-guard* keep changes lean
+- Skills: *autotune*, *autoskill*, *dream* and *essence* improve the skills
+- Release: *changelog* writes the pkgmgr release message since the last tag
+- Status: *status-matrix* lists everything in flight with its confidence
+- Help: *explain* and *help-skills* explain code and the skill set
+- Chat: *shortcuts* expands operator tokens such as *sobu* and *socon*
+- Security: *medusa* runs the MEDUSA scanner on repos and secret stores
+- Docs: the README skill map shows how the skills invoke each other
+
+Upgrade notes:
+
+- Install: restart the agent after *make install* to load skills and hooks
+- Resources: *watch.py* needs *~/.config/agents-council/config.json*

README.md

@@ -7,6 +7,143 @@ Every skill is pinned in `skills-lock.json` for reproducible installs.
 First-party skills live under `skills/` and are layered on top of the locked ones at install time.
 Compatible with Claude Code, Codex, Gemini CLI, Cursor, Copilot, Windsurf, Cline, and other agents.
 
+## Skill map 🗺️
+
+How the first-party skills work together. A solid arrow means the skill invokes or relies on the other one; a dotted arrow means it fires automatically. Every skill that reports a result closes with the `confidence` block; those arrows are left out. The locked third-party skills (caveman, ponytail, archify) are not drawn.
+
+```mermaid
+flowchart LR
+  subgraph triggers [Triggers]
+    commit_req([commit request])
+    stage_req([staging or fix ready])
+    edit_hook([edit in a git worktree])
+    reminders([reminder hooks])
+    code_task([code task])
+    spawn([subagent spawn])
+  end
+  subgraph commit [Commit]
+    commit_next[commit-next]
+    commit_no_verify[commit-no-verify]
+    comments_clean[comments-clean]
+    advocate[advocate]
+    confidence[confidence]
+    break_risk[break-risk]
+    explain[explain]
+  end
+  subgraph coordination [Coordination]
+    democracy[democracy]
+    coordinate[coordinate]
+    funnel[funnel]
+    cleanup[cleanup]
+    branch_gc[branch-gc]
+    subagent_model[subagent-model]
+  end
+  subgraph ci [CI]
+    observe[observe]
+    triage[triage]
+    ci_artifacts[ci-artifacts]
+    tune[tune]
+    merge_fix[merge-fix]
+  end
+  subgraph reasoning [Reasoning]
+    active_listening[active-listening]
+    dialectic[dialectic]
+    criticize[criticize]
+    sceptic[sceptic]
+    auto_feature[auto-feature]
+  end
+  subgraph autonomy [Autonomy]
+    plan[plan]
+    robot[robot]
+  end
+  subgraph self_improvement [Self-improvement]
+    dream[dream]
+    autotune[autotune]
+    autoskill[autoskill]
+    essence[essence]
+    shortcuts[shortcuts]
+  end
+  subgraph quality [Quality]
+    test[test]
+    refactor[refactor]
+    no_defaults[no-defaults]
+    scope_guard[scope-guard]
+  end
+  subgraph standalone [Standalone]
+    changelog[changelog]
+    help_skills[help-skills]
+    status_matrix[status-matrix]
+    medusa[medusa]
+  end
+
+  commit_req -.-> commit_next
+  commit_req -.-> commit_no_verify
+  stage_req -.-> confidence
+  edit_hook -. council gate .-> democracy
+  reminders -.-> dream
+  reminders -.-> autotune
+  code_task -.-> no_defaults
+  code_task -.-> scope_guard
+  spawn -.-> subagent_model
+
+  commit_next --> merge_fix
+  commit_next --> commit_no_verify
+  commit_next --> explain
+  commit_next --> dialectic
+  commit_no_verify --> comments_clean
+  commit_no_verify --> advocate
+  advocate --> dialectic
+  confidence --> break_risk
+  confidence -. objective .-> autotune
+
+  coordinate --> democracy
+  cleanup --> democracy
+  cleanup --> branch_gc
+  branch_gc --> democracy
+  funnel --> democracy
+  funnel --> dialectic
+  funnel --> subagent_model
+  dialectic --> subagent_model
+  democracy --> merge_fix
+
+  observe --> triage
+  observe --> ci_artifacts
+  triage --> ci_artifacts
+  triage --> democracy
+  triage --> dialectic
+  triage --> funnel
+  triage --> tune
+  tune --> democracy
+  tune --> funnel
+  tune --> merge_fix
+  tune --> dialectic
+
+  dialectic --> active_listening
+  criticize --> dialectic
+  criticize --> active_listening
+  sceptic --> dialectic
+  sceptic --> no_defaults
+  auto_feature --> sceptic
+  auto_feature --> active_listening
+
+  plan --> robot
+  plan --> active_listening
+  robot --> dialectic
+
+  dream --> dialectic
+  dream --> autotune
+  dream --> autoskill
+  autoskill --> autotune
+  autoskill --> shortcuts
+  autotune --> essence
+
+  test --> triage
+  test --> dialectic
+  test --> no_defaults
+  test --> comments_clean
+  refactor --> comments_clean
+```
+
 ## Requirements 📦
 
 - Node.js (provides `npx skills`).
@@ -26,7 +163,7 @@ Copy the skills into a specific project (`<repo>/.agents/skills` and `<repo>/.cl
 make project TARGET=/path/to/repo
 ```
 
-Both commands also enable the caveman and ponytail plugins in the target's `.claude/settings.json` so their modes auto-activate on session start; existing settings are preserved.
+Both commands also patch the target's `.claude/settings.local.json` — the machine-local, untracked file, so a project's reviewed `.claude/settings.json` is never rewritten by an install: the caveman and ponytail plugins are enabled so their modes auto-activate on session start, and two reminder hooks are registered — `autotune` points you at `/autotune` at most once an hour, `dream` points you at `/dream` at most once every twelve hours per repository (stamped in that repository's git dir). A PreToolUse gate from the `democracy` skill blocks edits to files in a git worktree until the session holds a claim (`skills/democracy/scripts/council.py`), and its resource watch (`skills/democracy/scripts/watch.py`) measures disk, Docker and caches, cleans up low-risk data and blocks new heavy jobs before the disk runs out; it stays inactive until `~/.config/agents-council/config.json` exists. Two hooks of the `subagent-model` skill (`skills/subagent-model/scripts/log.py`) log every Agent spawn with its task class, model and effort, and store the quality feedback a sandboxed session prints, in `~/.local/state/agents-council/subagent-model.jsonl`. Existing settings are preserved.
 
 Restart your agent afterwards so it loads the new skills.
 

pyproject.toml

@@ -0,0 +1,5 @@
+[dependency-groups]
+lint = ["ruff==0.17.3"]
+
+[tool.ruff]
+target-version = "py312"

scripts/enable-plugins.js

@@ -1,11 +1,12 @@
 #!/usr/bin/env node
 // Enable the caveman and ponytail plugins in a Claude Code settings.json so
-// their SessionStart hooks auto-activate both modes. Merges non-destructively:
-// existing marketplaces and enabled plugins are preserved, unparseable files
-// are left untouched.
+// their SessionStart hooks auto-activate both modes, register the autotune
+// and dream reminder hooks, the democracy claim gate, the resource watch and the subagent-model log. Merges non-destructively: existing marketplaces,
+// plugins and hooks are preserved, unparseable files are left untouched.
 "use strict";
 
 const fs = require("fs");
+const path = require("path");
 
 const settingsPath = process.argv[2];
 if (!settingsPath) {
@@ -18,6 +19,7 @@ const MARKETPLACES = {
   ponytail: { source: { source: "github", repo: "DietrichGebert/ponytail" } },
 };
 const PLUGINS = { "caveman@caveman": true, "ponytail@ponytail": true };
+const REMINDERS = ["autotune", "dream"];
 
 let data = {};
 if (fs.existsSync(settingsPath)) {
@@ -38,5 +40,43 @@ for (const [name, entry] of Object.entries(MARKETPLACES)) {
 }
 data.enabledPlugins = Object.assign(data.enabledPlugins || {}, PLUGINS);
 
+data.hooks = data.hooks || {};
+data.hooks.UserPromptSubmit = data.hooks.UserPromptSubmit || [];
+const alreadyRegistered = JSON.stringify(data.hooks.UserPromptSubmit);
+for (const skill of REMINDERS) {
+  if (alreadyRegistered.includes(`${skill}/hooks/reminder.sh`)) continue;
+  const reminder = path.join(path.dirname(settingsPath), "skills", skill, "hooks", "reminder.sh");
+  data.hooks.UserPromptSubmit.push({
+    hooks: [{ type: "command", command: `bash ${JSON.stringify(reminder)}` }],
+  });
+}
+
+data.hooks.PreToolUse = data.hooks.PreToolUse || [];
+if (!JSON.stringify(data.hooks.PreToolUse).includes("democracy/scripts/council.py")) {
+  const council = path.join(path.dirname(settingsPath), "skills", "democracy", "scripts", "council.py");
+  data.hooks.PreToolUse.push({
+    matcher: "Edit|Write|MultiEdit|NotebookEdit",
+    hooks: [{ type: "command", command: `python3 ${JSON.stringify(council)} gate` }],
+  });
+}
+
+const SCRIPT_HOOKS = [
+  ["democracy/scripts/watch.py", "UserPromptSubmit", null, "watch"],
+  ["democracy/scripts/watch.py", "PostToolUse", "Bash", "watch"],
+  ["democracy/scripts/watch.py", "PreToolUse", "Bash", "block"],
+  ["subagent-model/scripts/log.py", "PreToolUse", "Agent|Task", "spawn"],
+  ["subagent-model/scripts/log.py", "PostToolUse", "Bash", "persist"],
+];
+for (const [script, event, matcher, sub] of SCRIPT_HOOKS) {
+  data.hooks[event] = data.hooks[event] || [];
+  const registered = data.hooks[event].some((entry) =>
+    (entry.hooks || []).some((hook) =>
+      String(hook.command).includes(script) && String(hook.command).endsWith(` ${sub}`)));
+  if (registered) continue;
+  const file = path.join(path.dirname(settingsPath), "skills", ...script.split("/"));
+  const entry = { hooks: [{ type: "command", command: `python3 ${JSON.stringify(file)} ${sub}` }] };
+  data.hooks[event].push(matcher ? { matcher, ...entry } : entry);
+}
+
 fs.writeFileSync(settingsPath, JSON.stringify(data, null, 2) + "\n");
-console.log(`skills: enabled caveman + ponytail plugins in ${settingsPath}`);
+console.log(`skills: enabled caveman + ponytail plugins, the ${REMINDERS.join(" + ")} reminders, the democracy claim gate, the resource watch and the subagent-model log in ${settingsPath}`);

scripts/install.sh

@@ -23,10 +23,11 @@ if [[ ! -d "${TARGET}" ]]; then
 fi
 
 cd "${REPO_ROOT}"
+src="${REPO_ROOT}/.agents/skills"
+rm -rf "${src}"
 log "skills: restoring from skills-lock.json..."
 npx --yes skills experimental_install
 
-src="${REPO_ROOT}/.agents/skills"
 if [[ ! -d "${src}" ]]; then
 	warn "skills: ${src} not found after install."
 	exit 1
@@ -44,7 +45,7 @@ for dst in "${TARGET}/.agents/skills" "${TARGET}/.claude/skills"; do
 	cp -a "${src}/." "${dst}/"
 done
 
-settings="${TARGET}/.claude/settings.json"
+settings="${TARGET}/.claude/settings.local.json"
 if command -v node &>/dev/null; then
 	log "skills: auto-enabling caveman + ponytail plugins in ${settings}"
 	node "${REPO_ROOT}/scripts/enable-plugins.js" "${settings}"

scripts/update.sh

@@ -30,6 +30,6 @@ fi
 log "skills: updating from ${lockfile}..."
 jq -r '.skills[].source' "${lockfile}" | sort -u | while read -r source; do
 	log "skills: updating ${source}..."
-	npx --yes skills add --yes "${source}"
+	npx --yes skills add --yes --agent claude-code "${source}" </dev/null
 done
 log "skills: update complete."

skills-lock.json

@@ -1,83 +1,89 @@
 {
   "version": 1,
   "skills": {
+    "archify": {
+      "source": "tt-a1i/archify",
+      "sourceType": "github",
+      "skillPath": "archify/SKILL.md",
+      "computedHash": "e9ef0923cda908886e667eb48e36b29e81d0a7a7b9fe2bc05f3779be271e5119"
+    },
     "cavecrew": {
       "source": "JuliusBrussee/caveman",
       "sourceType": "github",
       "skillPath": "skills/cavecrew/SKILL.md",
-      "computedHash": "c5527c994fbd4c22b36714e3b124a0f167a533d114ab164fb1d35e2123533917"
+      "computedHash": "2e122d819a812bef0e4958706f306e4346e78ecb5a4893997b99cbc19866f514"
     },
     "caveman": {
       "source": "JuliusBrussee/caveman",
       "sourceType": "github",
       "skillPath": "skills/caveman/SKILL.md",
-      "computedHash": "d18cdf73a5f5c496d681a43a6846336b110223bdffa6817b8992529c57f1a815"
+      "computedHash": "71b600c88c8d1d36f18c4875db23b53c5d6cb9ba3195e19451d6b1bb67db07c4"
     },
     "caveman-commit": {
       "source": "JuliusBrussee/caveman",
       "sourceType": "github",
       "skillPath": "skills/caveman-commit/SKILL.md",
-      "computedHash": "790a4eeace0be35c6691faf923518ba5bd50f1f1305d1101d09dd4971be94e00"
+      "computedHash": "b416cf134b0f33ddadeca7977aebdbb2d3db79a166d0fce2e1aabeec98132766"
     },
     "caveman-compress": {
       "source": "JuliusBrussee/caveman",
       "sourceType": "github",
       "skillPath": "skills/caveman-compress/SKILL.md",
-      "computedHash": "84517cd4cf7a49d8d2bc1baf00f61bc359306c6ad9389756b6937eff958bd374"
+      "computedHash": "9c8d35882a93e387a584cc4efaacb74433d379a2bd02e3e6f6ad4f7c30ff55ed"
     },
     "caveman-help": {
       "source": "JuliusBrussee/caveman",
       "sourceType": "github",
       "skillPath": "skills/caveman-help/SKILL.md",
-      "computedHash": "dd85267e76baad76995157e7b9f762dfa557cd58951ee92af0c283f48aa26537"
+      "computedHash": "c7a73a8c6afb6f871690666449209106aba847b4a9b0698686648960ece80012"
     },
     "caveman-review": {
       "source": "JuliusBrussee/caveman",
       "sourceType": "github",
       "skillPath": "skills/caveman-review/SKILL.md",
-      "computedHash": "fb7214a1c5793bae6ba8b1be4329e2e6f40dbec6dd911dfb335ad29f09c316a1"
+      "computedHash": "36a4007c5c0c6b90b5accfee1cd769a86e4963b651dece2ce5f17a223a0abb4b"
     },
     "caveman-stats": {
       "source": "JuliusBrussee/caveman",
       "sourceType": "github",
       "skillPath": "skills/caveman-stats/SKILL.md",
-      "computedHash": "47ce2de3d6cb39a75047b5c962e4eb3da15594e7397c94103e9a104d42626553"
+      "computedHash": "cc9fcd21f2a30cff5596b3cbb197fe0f4b1b30b58084a864350853c217ad301a"
     },
     "ponytail": {
       "source": "DietrichGebert/ponytail",
       "sourceType": "github",
       "skillPath": "skills/ponytail/SKILL.md",
-      "computedHash": "210fa0831f649ce9f8a305f7b7c8cf2a0dd09ac4dd53067109941b96e7811d4e"
+      "computedHash": "061f887d9e3e735f85db3be3655a8936a00f24d5fb65ac4ab74a968a770fe342"
     },
     "ponytail-audit": {
       "source": "DietrichGebert/ponytail",
       "sourceType": "github",
       "skillPath": "skills/ponytail-audit/SKILL.md",
-      "computedHash": "8b8d72e6ff70b65b6c9518d470fcf29dc696eea93d28f3efa10fdcc60cbd696d"
+      "computedHash": "1d718f893dabc01caad0dacef86444b5b4b3e1e59409527d66e8b5dd0cd85ae0"
     },
     "ponytail-debt": {
       "source": "DietrichGebert/ponytail",
       "sourceType": "github",
       "skillPath": "skills/ponytail-debt/SKILL.md",
-      "computedHash": "0099b82174e3a4261828b4ec04d2c068b1b294fdab14f76701c2acd1f7c99539"
+      "computedHash": "f5d1d2ab891ff0a650a90b67235e487828e7d2a189de08a1ae073032de379407"
     },
     "ponytail-gain": {
       "source": "DietrichGebert/ponytail",
       "sourceType": "github",
       "skillPath": "skills/ponytail-gain/SKILL.md",
-      "computedHash": "c45ecba7906960eea904218b623abf097ebff84ecbacca6d68da1d0687435f75"
+      "computedHash": "fca2297cf7b5fd26692f6bd94d398b522e19fa81ad6e2aaebf1933575f7a6803"
     },
     "ponytail-help": {
       "source": "DietrichGebert/ponytail",
       "sourceType": "github",
       "skillPath": "skills/ponytail-help/SKILL.md",
-      "computedHash": "10e8382b1033c9a0fec0073de6d3de3846b4f5dca7d78b6df2d476a1f4cd43c6"
+      "computedHash": "4582025c3923072fb6c35b8cbd75adf4f7ce47df0eff43cc9a2a39808537fd61"
     },
     "ponytail-review": {
       "source": "DietrichGebert/ponytail",
       "sourceType": "github",
       "skillPath": "skills/ponytail-review/SKILL.md",
-      "computedHash": "4646594fcd75455533f7ff1425f4f1c5ba0fa65f88241bf262b1c4fc275f049a"
+      "computedHash": "800dc0c86402978e12359f701b9e0c81ba4607a0cd0027f4596d0f835a67eadc"
     }
   }
 }

skills/active-listening/SKILL.md

@@ -1,11 +1,10 @@
 ---
 name: active-listening
 description: >
-  Gather every requirement before acting. Trigger at the start of any task
-  whose scope, constraints, or success criteria are not fully pinned down, and
-  whenever another skill needs an operator-only fact — ask focused questions
-  until nothing needed is still open, then reflect the understanding back.
-  Portable across projects.
+  Ask focused questions until every requirement is pinned down, then reflect
+  the task back. Trigger at the start of any task with unclear scope,
+  constraints or success criteria, and when another skill needs an
+  operator-only fact.
 ---
 
 Do not act on a half-understood request. Listen actively until you could state

skills/advocate/SKILL.md

@@ -0,0 +1,88 @@
+---
+name: advocate
+description: >
+  Check a commit for legal soundness: licence compatibility of added code and
+  dependencies, attribution, copied snippets, GDPR, trademarks. Run
+  AUTOMATICALLY before every commit the operator requests; also on /advocate
+  [ref|range], "rechtlich prüfen", "lizenz prüfen".
+---
+
+The stance is the project's counsel: find what would make the change unlawful
+to distribute before it is distributed. This is not legal advice but a reading
+of the licence texts, with German and EU law where jurisdiction matters; every
+report says so in one line. Leaked secrets belong to `medusa`, engineering
+principles to `sceptic`.
+
+## Target
+
+- Before a commit: the staging index (`git diff --cached`, plus every added or
+  changed file in full where origin or licence is in question).
+- `/advocate <ref>` or `/advocate <a>..<b>`: that commit or range.
+- `/advocate` alone: the index if it is non-empty, else `HEAD`.
+
+## Fast exit
+
+The target is in scope only if it adds or changes at least one of: a
+dependency manifest or lockfile; a vendored, generated, or third-party file; a
+LICENSE, NOTICE, or COPYING file or a licence header; code with a foreign
+origin (a source URL, a foreign copyright line, a block that reads unlike its
+surroundings); an external request (CDN, web font, analytics, embed, API);
+handling of personal data; a logo, icon, or third-party brand name. Nothing in
+scope: report `advocate: nothing licence-relevant in <target>` in one line and
+let the commit proceed.
+
+## Project licence
+
+Read every declaration: LICENSE/COPYING, the manifest's licence field
+(`package.json`, `pyproject.toml`, `Cargo.toml`, `composer.json`, ...), SPDX
+headers, the README's licence section. Declarations that disagree are a
+finding. A project without any licence is a finding (all rights reserved),
+never a blocker of the commit at hand.
+
+## The checks
+
+Only for a target in scope: read `checks.md` next to this file and apply its
+seven checks (inbound code, dependency licences, project licence fit,
+attribution, copied snippets, data protection, trademarks).
+
+## Severity
+
+- **Blocker** - the commit would distribute what the project may not
+  distribute: an incompatible inbound or dependency licence, or non-trivial
+  code or assets without a licence.
+- **Finding** - fixable while keeping the change: missing attribution, NOTICE,
+  or header; a data-protection gap; trademark use; a block of unclear origin.
+- **Note** - worth knowing, no action required.
+
+## Blockers stop the commit
+
+Harden every blocker with the `dialectic` skill before reporting it. The
+antithesis tries: the code is trivial or the operator's own; the dependency is
+build- or test-only and never distributed; an exception applies (linking or
+Classpath exception, dual licensing, a licence grant in the issue or commit
+history). A blocker that survives stops the commit: present it with the
+options (remove, replace with a compatible alternative, relicense, obtain
+permission) and wait. The operator's explicit acceptance lets this one commit
+proceed and never carries over to the next. Findings and notes never stop a
+commit.
+
+## Output
+
+One line with the target, the project licence, and "Keine Rechtsberatung" (in
+the operator's language). Then one table, blockers first:
+
+| Severity | Check | Location | What is wrong | Licence or law | Fix | Evidence |
+
+`Evidence` is `proven` (licence text, metadata, or file read; cite path:line
+or the registry URL) or `derived` (inferred). Close with the verdict (commit
+stops or proceeds) and the `confidence` skill's numbers.
+
+## Rules
+
+- Never infer a licence from a package's name or reputation; read it. An
+  unreachable registry makes the row `derived`, never clean.
+- Never invent a licence clause, a statute, or a court ruling; cite only what
+  you read.
+- Read-only apart from stopping the commit: never edit licence files, add
+  headers, or remove dependencies on your own. Propose the fix; the operator
+  decides.

skills/advocate/checks.md

@@ -0,0 +1,37 @@
+# Advocate: the checks
+
+Apply each check to a target the `advocate` skill found in scope.
+
+1. **Inbound code** - every file or block of foreign origin carries a licence
+   that the project licence can absorb in the direction of distribution. GPL
+   code cannot enter a project distributed under MIT without relicensing the
+   whole; Apache-2.0 cannot enter GPL-2.0-only; code without a licence is all
+   rights reserved.
+2. **Dependency licences** - for each added or bumped dependency, read the
+   licence of the resolved version (lockfile, registry metadata, or the
+   package's own LICENSE), including the transitive dependencies the lockfile
+   newly pulls. Watch copyleft reach (GPL, AGPL's network clause, LGPL static
+   versus dynamic linking), source-available terms that are not open source
+   (SSPL, BUSL, Commons Clause, "non-commercial"), and an upstream relicensing
+   between the old and the new version.
+3. **Project licence fit** - the project's declarations still hold against
+   what checks 1 and 2 found: a dependency that forces copyleft forces either
+   the project licence or the dependency's removal.
+4. **Attribution** - retained copyright notices, the licence text shipped
+   where required, an Apache-2.0 NOTICE propagated, modified-file notices
+   (Apache-2.0 §4(b), GPL-3.0 §5(a)), SPDX headers where the project uses them,
+   credit for CC BY material.
+5. **Copied snippets** - Stack Overflow content is CC BY-SA (attribution plus
+   share-alike); gists, blog posts, other repositories, and verbatim
+   reproductions of well-known code need a traceable origin and licence.
+   Trivial code without originality (one-liners, usage dictated by an API) is
+   not a finding.
+6. **Data protection (GDPR, TDDDG)** - new collection, storage, logging, or
+   transfer of personal data; IP addresses sent to third parties through
+   external fonts, CDNs, analytics, or embeds; storage on the user's device
+   without consent (§ 25 TDDDG); transfers outside the EU. Name the data flow
+   and the missing legal basis or consent mechanism.
+7. **Trademarks and branding** - third-party logos, icons, and product names
+   used beyond plain reference: implied endorsement, use in the project's own
+   name, modified logos. Icon sets carry their own licence, and a free licence
+   on an icon does not license the trademark it depicts.

skills/auto-feature/SKILL.md

@@ -0,0 +1,98 @@
+---
+name: auto-feature
+description: >
+  Derive missing work (sceptic pass for structural flaws, usability pass for
+  missing features) and write requirement documents after single-select
+  confirmation. Trigger on /auto-feature, "was fehlt noch", "welche features
+  brauchen wir", or when the operator asks what to build next.
+---
+
+Two blind spots produce different work: the code has defects of structure,
+the product has gaps of use. This skill runs both lenses, ranks what comes
+out, and lets the operator choose — it writes requirement documents, never
+implementations.
+
+## Step 1: fix the scope
+
+Name the target in one line: repository, subsystem, role, or user-facing
+surface. Read the project's existing requirement documents first — their
+location, filename convention, and section structure are the template, and
+an already-written requirement is not a finding.
+
+## Step 2: the sceptic pass
+
+Invoke the `sceptic` skill on the target. Its findings become requirement
+candidates by severity: a violated SPOT, SRP, or trust boundary is work the
+product needs whether or not a user ever notices. Carry each finding's
+`file:line` evidence forward — a requirement without it is a guess.
+
+## Step 3: the usability pass
+
+Independently, look for what the product does not do yet. Anchor every gap
+in something observable in the repository, never in an invented persona:
+
+- **Entry** — can someone install, configure, and run it without reading the
+  source? Missing `--help`, missing example config, an undocumented required
+  variable.
+- **Recovery** — does a failure tell the user what to do next? Errors that
+  print a stack trace instead of the remediation, no dry-run, no way to undo
+  or uninstall, no idempotent re-run.
+- **Feedback** — does a long operation say anything while it works? Silent
+  minutes, no progress, no exit summary.
+- **Empty and edge states** — first run with no data, zero results, an
+  expired credential, a partially completed run.
+- **Discoverability** — a capability that exists but nothing surfaces:
+  undocumented flags, features reachable only by reading tests.
+- **Accessibility and locale** — output that assumes colour, a terminal
+  width, or one language.
+
+Each gap gets one line: `observed evidence -> who is blocked -> smallest
+change that unblocks them`. Drop anything you cannot anchor.
+
+## Step 4: rank and ask
+
+Merge both lists, drop duplicates where a structural finding and a usability
+gap describe the same defect, and rank by blocked users first, blast radius
+second.
+
+Then apply `active-listening`: answer everything you can from the code, the
+docs, and the git history yourself, and put only the genuinely open decisions
+to the operator with `AskUserQuestion`, `multiSelect: false`, so every
+question renders as radio buttons. At most four questions per call, each
+option a real alternative — never one option plus filler:
+
+1. **Which candidates** become requirements this run, ranked, each option
+   carrying its evidence in the description.
+2. **Which shape** the chosen one takes — for a feature typically
+   `Minimal version that unblocks the user`, `Full version`, `Fix the
+   underlying structure instead`, `Document the limitation and defer`.
+3. **Scope boundary** — what is explicitly out of scope, when the candidate
+   could grow in more than one direction.
+4. **Placement** — which requirement file or directory receives it, when the
+   project has more than one.
+
+Never assume an answer, never fold two decisions into one option, and never
+write a file before the answers are in.
+
+## Step 5: write the requirements
+
+One document per feature — a requirement that needs "and" in its title is
+two requirements. Follow the project's existing template; when there is
+none, keep it to: problem with its evidence, the decided scope and its
+boundary, definition of done as checkable criteria, and the alternatives the
+operator rejected with the reason.
+
+Show the drafted document and ask for a final `Write it` / `Revise it` /
+`Discard` before touching disk.
+
+## Rules
+
+- Requirements only: no implementation, no refactor, no staging as part of
+  this skill.
+- Every requirement traces to evidence — a `file:line`, a failing path, a
+  missing artifact. A requirement whose justification is "would be nice" is
+  not written.
+- Record the rejected alternatives inside the document; the next reader
+  needs to know what was already considered and dismissed.
+- Close with the `confidence` skill's numbers for the analysis: how sure the
+  gaps are real, and what the passes did not cover.

skills/autoskill/SKILL.md

@@ -1,12 +1,16 @@
 ---
 name: autoskill
 description: >
-  Detect operator repetition and turn it into a skill. Trigger when the
-  operator gives an instruction, correction, or prompt pattern for roughly
-  the third time in a conversation (or says they keep repeating themselves),
-  and the pattern is general enough to reuse. Portable across projects.
+  Turn operator repetition into a skill. Trigger when the operator gives the
+  same instruction, correction or prompt pattern about the third time in a
+  conversation, or says they keep repeating themselves, and the pattern is
+  reusable.
 ---
 
+Its objective is the `autotune` skill's **Objective** section: a skill is worth
+creating only when it cuts tokens or time and raises quality; judge every
+candidate against its three axes and rules.
+
 When you notice the operator repeating the same kind of instruction,
 correction, or prompt pattern (about three occurrences, exact wording may
 vary), do the following:
@@ -18,10 +22,12 @@ vary), do the following:
 3. On approval, write the skill:
    - a conversation shortcut or expansion: add it to the `shortcuts` skill
      table instead of creating a new skill.
-   - project-specific behavior: create it in the project's own skills
-     directory (e.g. `skills/<name>/SKILL.md` in the repository).
-   - portable behavior: create `skills/<name>/SKILL.md` in the operator's
-     skills repository.
+   - anything else: persist it exactly as the `autotune` skill's
+     **Persistence** section specifies — locate the operator's skills
+     repository, write `skills/<name>/SKILL.md` there (or in the current
+     project for project-specific behavior), then mirror the skill directory
+     into `~/.claude/skills/` and `~/.agents/skills/`, plus the project's
+     `.claude/skills/` and `.agents/skills/` when it is project-specific.
    Follow the local naming conventions and keep the skill a thin,
    single-purpose instruction; route to an authoritative doc when one
    exists instead of duplicating it.

skills/autotune/SKILL.md

@@ -0,0 +1,148 @@
+---
+name: autotune
+description: >
+  Generate new skills or optimize existing ones (fewer tokens, fewer errors,
+  persistent learnings), each proposal confirmed by single-select question.
+  Trigger ONLY on an explicit request: /autotune, "autotune", "tune the
+  skills"; never on your own initiative.
+---
+
+Autotune turns observed friction into durable skills. It runs on demand only,
+it changes nothing without an explicit answer from the operator, and every
+skill it writes or rewrites lands in the operator's skills repository.
+
+## Objective
+
+The shared objective of the self-improving skills (autotune, autoskill,
+confidence): every skill, rule, or report the agent produces about its own
+working is judged on three axes at once. A proposal that cannot name the axis
+it moves is not an optimization, it is a preference.
+
+- **Tokens** — fewer input and output tokens for the same result: read the range
+  instead of the whole file, grep the saved log instead of re-running the
+  command, route to an authoritative doc instead of duplicating it, report in
+  lines instead of paragraphs.
+- **Time** — fewer round trips and less waiting: independent calls in parallel,
+  one command that answers the question instead of three that circle it, no
+  polling for work the harness will report on its own.
+- **Quality** — fewer errors and less rework: verification instead of
+  assumption, and learnings that persist so the same mistake is not paid for
+  twice.
+
+- A change must improve at least one axis and damage none. Output that got
+  cheaper but lost correctness is a regression, not an optimization.
+- Quality is never the currency: validation, error handling, tests, and security
+  steps are not what gets cut to save tokens or time.
+- Measure, do not guess: name the observed friction — the re-read, the retry,
+  the correction the operator had to give twice — and what it cost. A guessed
+  percentage is not a measurement.
+- The cheapest step is the one that does not run: drop work before optimizing
+  it.
+- Persist it or pay again: an optimization that lives only in this session is
+  re-derived in the next one, so it belongs in a skill or a memory entry.
+
+## Trigger discipline
+
+- Run **only** when the operator asks: `/autotune`, "autotune", "tune the
+  skills", or an equivalent instruction.
+- The 60-minute reminder hook is a hint for the operator, not a trigger. When it
+  fires, print the hint and continue the operator's actual request.
+- Never propose, write, or edit a skill as a side effect of unrelated work.
+
+## Step 1: collect evidence
+
+Before asking anything, gather concrete friction from the current session and,
+where readable, from the project's memory and agent instruction files:
+
+- **Token waste**: repeated file re-reads, whole-file reads where a range was
+  enough, long tool output pasted back, re-running a command instead of
+  grepping a saved log, verbose report prose.
+- **Errors**: rejected tool calls, permission prompts, retried commands,
+  corrections the operator had to give twice.
+- **Focus loss**: work that drifted beyond the request, unrequested tests or
+  deploys, questions that stalled an autonomous run.
+- **Lost learnings**: facts re-derived this session that a memory file or a
+  skill should already have carried.
+
+List each finding as one line: `symptom -> cost -> candidate fix`. Skip
+anything that happened once and is not a pattern.
+
+## Step 2: ask, do not decide
+
+Use `AskUserQuestion` with `multiSelect: false` so every question renders as
+radio buttons. Never assume an answer, never batch several decisions into one
+option, and never write a file before the answers are in.
+
+Ask in this order, at most four questions per call:
+
+1. **Scope** - "What should autotune do this run?" Options: `Create a new
+   skill`, `Optimize an existing skill`, `Both`, plus the ranked findings if
+   more than one candidate exists.
+2. **Target** - which finding becomes a skill, or which existing skill gets
+   optimized. One option per candidate, each with its measured cost in the
+   description.
+3. **Shape** - for a new skill: `Standalone skill`, `Row in the shortcuts
+   skill`, `Extend an existing skill`, `Memory entry instead of a skill`.
+   For an optimization: `Tighten wording only`, `Change the trigger`, `Add
+   rules`, `Split into two skills`, `Merge into another skill`.
+4. **Placement** - `Operator skills repository (portable)` or
+   `This project's skills directory (project-specific)`.
+
+Present the drafted skill text (name, trigger phrasing, body outline) and ask
+for a final `Write it` / `Revise it` / `Discard` confirmation before touching
+disk. Rewrites of an existing skill additionally show a before/after diff of
+the changed lines in that confirmation.
+
+## Persistence
+
+A skill that exists only under `.claude/skills` is lost on the next install, and
+one that exists only in the repository is not live until the next restart — so
+every skill is written to **both**, in this order:
+
+1. **Locate the operator's skills repository.** Take the first hit: the
+   `SKILLS_REPO` environment variable; the current repository, when it holds
+   `skills-lock.json` and a `skills/` directory; `pkgmgr path skills`; a git
+   checkout named `skills` under the usual roots
+   (`~/Repositories/*/*/skills`, `~/git`, `~/src`, `~/Projects`) carrying
+   `skills-lock.json`. If none matches, ask the operator for the path with a
+   single-select question — never skip the repository and write only the live
+   copies.
+2. **Write the source of truth**: `skills/<name>/SKILL.md` in that repository
+   (portable skills), or `skills/<name>/SKILL.md` in the current project
+   (project-specific ones). This is the copy that gets committed.
+3. **Mirror it live**, so it works without a reinstall: copy the skill's whole
+   directory to `~/.claude/skills/<name>/` and `~/.agents/skills/<name>/`, and
+   for a project-specific skill additionally to that project's
+   `.claude/skills/<name>/` and `.agents/skills/<name>/`. Copy the directory,
+   not just `SKILL.md`, so hooks and references come along.
+
+Report all written paths. Deleting or renaming a skill follows the same list in
+reverse — remove the mirrors too, or the old name keeps firing.
+
+## Step 3: write
+
+- Write the skill to every location the **Persistence** section lists.
+- Frontmatter carries `name` and a `description` that states what the skill
+  does **and** when to trigger it - the description is the only part loaded into
+  every session, so it decides whether the skill ever fires.
+- Body is thin and single-purpose: the smallest instruction that changes
+  behaviour. Route to an authoritative doc instead of duplicating it.
+- Optimizing an existing skill means the file gets shorter or sharper, not
+  longer. Delete rules the agent already follows, merge duplicated ones, and
+  cut every sentence that does not change an action. Route that compaction
+  through the `essence` skill instead of trimming by hand: it runs a health
+  pass for dead pointers and rules duplicated across skills before cutting
+  anything, ranks by what loads in every session, and shows the diff before it
+  writes. It asks for its own scope — answer with the skill being optimized.
+- Report what changed in at most three lines, then refresh the reminder stamp
+  so the next hint is an hour out: `date +%s > ~/.claude/.autotune-stamp`.
+
+## Rules
+
+- One skill per run unless the operator picked `Both`; a broad rewrite of the
+  whole collection is not what autotune is for.
+- Never write a skill for one-off work, for secrets, or for behaviour an
+  existing skill already covers - propose extending that skill instead.
+- The **Objective** section decides what counts as an improvement: at least
+  one axis better, none damaged, and the claim named as observed friction rather
+  than a guessed percentage.

skills/autotune/hooks/reminder.sh

@@ -0,0 +1,32 @@
+#!/usr/bin/env bash
+# UserPromptSubmit hook: emit the autotune hint at most once per interval.
+# Stdout lands in the agent's context, which is why the payload tells the agent
+# to show the hint and keep going instead of running autotune by itself.
+set -euo pipefail
+
+interval="${AUTOTUNE_INTERVAL_SECONDS:-3600}"
+stamp="${AUTOTUNE_STAMP:-${HOME}/.claude/.autotune-stamp}"
+
+now="$(date +%s)"
+last=0
+if [[ -f "${stamp}" ]]; then
+	read -r last <"${stamp}" || true
+	[[ "${last}" =~ ^[0-9]+$ ]] || last=0
+fi
+
+if ((now - last < interval)); then
+	exit 0
+fi
+
+mkdir -p "$(dirname "${stamp}")"
+printf '%s\n' "${now}" >"${stamp}"
+
+cat <<'HINT'
+AUTOTUNE HINT: over an hour since the last hint. Show the operator this notice
+verbatim as a short block, then continue with their request. Do NOT run
+autotune, do not propose skills, do not ask questions about it.
+
+    💡 /autotune - generate a new skill or optimize an existing one
+       (fewer tokens, fewer errors, more focus, learnings that persist).
+       Runs only when you trigger it.
+HINT

skills/branch-gc/SKILL.md

@@ -0,0 +1,104 @@
+---
+name: branch-gc
+description: >
+  Remove merged branches and worktrees with `pkgmgr branch gc`: dry run,
+  operator picks from the plan, then apply; unmerged items only one by one.
+  Trigger on /branch-gc, "branches aufräumen", "worktrees aufräumen",
+  "garbage collect".
+---
+
+`pkgmgr branch gc` decides what is merged and does the removing; this skill
+decides what may go and who has to agree first. The dry run changes nothing,
+and nothing is removed before the operator's pick in this run.
+
+## Step 0: claim and chair
+
+1. Claim `work/branch-gc-<repo>`, or `work/branch-gc-all` for every
+   repository, through the `democracy` skill.
+2. The apply takes stacks down and ends with a host-wide
+   `docker image prune -f` and `docker builder prune -f`, which reach every
+   session's images and build cache. When another session holds the chair,
+   send it what, where and how long, and wait for the grant; the prune never
+   runs during a peer's build.
+
+## Step 1: dry run
+
+`pkgmgr branch gc --json`, with `--all` only when the operator asked for every
+repository, output to `/tmp/branch-gc-<N>.json`. No `git fetch` of your own
+before it: gc fetches without auto-maintenance, while a plain fetch on git
+2.50 or later may prune the sandbox's bind-mount stubs. Every repository's
+`warnings` (a failed fetch) go to the top of the plan. Sort the items:
+
+- **Candidates**: `state` `merged-clean`, non-empty `actions`, and `skip`
+  null or `lock: liveness unknown`.
+- **Step 5**: `state` `unmerged` or `dirty`.
+- **Reported only**: `protected`, every other `skip`, and `stale` as one count
+  per repository.
+
+Never override a state: a branch without own commits is `unmerged` even
+though git sees its tip on the default branch, because it is fresh work.
+
+`host_pid_namespace: false` means the dry run ran inside a sandbox: it saw no
+processes and could not tell whether a lock is live. Say so above the plan;
+the apply re-checks both on the host.
+
+## Step 2: claims
+
+Read `council.py list`. For every candidate whose branch or worktree a peer's
+claim names, send that peer one message (Peer protocol) and wait up to 5
+minutes. A kept or unanswered item leaves the plan as `keep (<peer>)`;
+silence is not consent.
+
+## Step 3: plan
+
+One table:
+
+| Repo | Branch or worktree | Merged by | Actions | Note |
+
+Then ask with `AskUserQuestion`:
+
+- **Call 1** (`multiSelect: true`): the candidates, grouped by repository,
+  nothing preselected. Each description names `merged_by` and every action
+  (stack with volumes, the `images`, worktree, local and remote branches), and
+  `lock checked at apply` where liveness was unknown.
+- **Call 2** (`multiSelect: false`): `Apply: <n> items (Recommended)`,
+  `Revise the selection`, `Abort`. Revise repeats call 1.
+
+## Step 4: apply
+
+1. Re-read `council.py list` and drop every item claimed since the dry run.
+2. `--apply` refuses outside the host PID namespace (exit 2) and deletes
+   remote branches, which is a push. Unless this session runs in the host PID
+   namespace and the project lets agents push, hand the operator one command
+   per repository, run from inside it, one `--branch` per picked item (the
+   worktree path for a detached worktree):
+
+   ```bash
+   pkgmgr branch gc --apply --json --branch <name> --branch <name> | tee /tmp/branch-gc-apply-<N>.json
+   ```
+
+3. Read every item's `result` in that file: `done`, `done; image kept: <img>`
+   (still in use elsewhere), or `failed: <why>`.
+   Report a failure as it stands; never remove by hand what gc skipped or
+   refused.
+
+## Step 5: unmerged and dirty
+
+Never part of the apply. One `AskUserQuestion` question per item
+(`multiSelect: false`): `Keep (Recommended)` and `Delete`, the description
+naming what is lost (the item's `reason`: unique commits, dirty paths). For
+each `Delete`, hand the operator
+`pkgmgr branch purge --branch <name>`: it asks y/N per item and answers no
+without a terminal, so it runs only in the operator's shell.
+
+## Step 6: report
+
+Removed, kept and skipped items, each with its reason, and
+`docker system df` before and after. Report the release to the chair, tell
+each peer whose line an item touched what went, and release the claim.
+
+## Rules
+
+- A pick from an earlier run does not carry over.
+- Never widen the selection, and never route around a refusal through another
+  command or a peer.

skills/break-risk/SKILL.md

@@ -0,0 +1,64 @@
+---
+name: break-risk
+description: >
+  Derive the break-risk percentage from measurement, not feel. Called by
+  `confidence` on every report; also when the operator asks "what could this
+  break?" or names a break-risk threshold.
+---
+
+Break risk is the probability the change breaks something it did not intend to
+touch. It is not the inverse of fix confidence, and it is not a mood. Derive it
+by the steps below; a number produced without them is a guess wearing a
+percent sign.
+
+## Fast path
+
+A change whose files nothing builds, deploys, or runs (documentation and
+comments only, or tests that ran green with it) has no consumers outside
+itself. Name the files (`git diff --cached --name-only`), report break risk
+under 1%, and skip the method. Any other file takes the full method.
+
+## The method
+
+1. **Consumers**: enumerate every consumer of everything the change alters, in
+   the committed state (`git grep <symbol> HEAD`) and of its output; say the
+   count. A caveat never licenses a low number; an enumeration does.
+2. **Delta**: run the old and the new code on today's inputs and compare at
+   the surface where the difference shows (rendered output, emitted config,
+   returned set, wire bytes), not as the source reads.
+3. **Live or latent**: per finding, whether a shipped configuration reaches it.
+   Only live findings move the number materially.
+4. **Matrix**: a verdict per deployment axis the project has, never averaged.
+5. **Failure mode**: fails closed and loud, or open and silent; the latter can
+   outrank a likelier failure.
+6. **Evidence**: executed beats derived; a report, a summary or your own
+   earlier message is not evidence; negative-control every check you cite,
+   including one you did not write.
+
+`reference.md` next to this file explains each step with the trap it defeats.
+Read it when a step is new to you or its result is contested.
+
+## Producing the number
+
+State it as a percentage next to fix confidence, never blended, and always with
+its residuals. Anchor roughly:
+
+- **Under 5%**: consumers enumerated, delta measured at the surface, every axis
+  of the matrix covered by executed evidence, failure mode closed.
+- **5 to 15%**: measured, but one axis or one layer rests on reasoning — no live
+  run, a mode not exercised, a runtime the render cannot prove.
+- **15 to 40%**: a real behaviour change whose consumers are enumerated but
+  whose effect is unmeasured, or a latent finding with a plausible trigger.
+- **Above 40%**: a known live defect, an unenumerated consumer set, or a
+  fail-open exposure without a verified control. Fix it rather than report it.
+
+Discount yourself after any error the operator caught in the same area during
+this session, and say that you are doing so. A region where you have already
+been wrong twice deserves a worse number than its paper evidence suggests.
+
+## When the operator names a threshold
+
+A named threshold is a gate on the work, not a field in the report. Missing it
+is a work item: name the cheapest evidence that would close the gap, go get it,
+re-measure. Report a miss only when the evidence is genuinely out of reach, and
+name which piece.

skills/break-risk/reference.md

@@ -0,0 +1,81 @@
+# Break risk: the method in detail
+
+Each step of the `break-risk` skill, with the trap it defeats.
+
+## The consumer question, first and always
+
+Enumerate every consumer of every thing the change alters, before naming a
+number. A written caveat never licenses a low number; an enumeration does.
+
+- Search the **committed** state, not just the working tree. A symbol that looks
+  unused in your branch may still be called from a file you have not opened
+  (`git grep <symbol> HEAD`). Removing a function with zero external callers is
+  a different risk class from removing one with nine.
+- Enumerate consumers of the **output**, not only of the code: who reads the
+  variable, renders the template, parses the emitted block, imports the
+  constant.
+- Say the count out loud. "Two consumers, both inside this change set" is
+  evidence. "I don't think anything else uses it" is not.
+
+## Measure the delta at the surface that matters
+
+Compare what the old code **actually produced** against what the new code
+produces, at the point where the difference becomes observable: rendered output,
+emitted config, returned set, wire bytes.
+
+The trap this defeats: reasoning about what the old code *looks like* it did. A
+sweep that appeared to forward sixteen ports forwarded **zero** in production,
+because the flag it gated on was unrendered template text. Had the delta been
+argued from the source rather than measured, the risk would have been sized
+against a behaviour that never existed.
+
+Extract the old implementation from version control and run it on today's
+inputs. If `DROPPED` is empty, nothing can regress; say so and move on.
+
+## Classify every finding as live or latent
+
+For each way the change could break something, decide which it is and say so:
+
+- **Live**: a shipped configuration, inventory, variant or default reaches it.
+- **Latent**: reachable only under a configuration nobody ships today.
+
+Both belong in the report. Only live findings drive the number up materially. A
+latent finding with a named trigger is worth more to the operator than a vague
+worry, and it is honest about why the number is not zero.
+
+## Walk the deployment matrix
+
+A change verified in one mode is unverified in the others. Enumerate the axes
+the project actually has, and state the verdict per cell rather than averaging
+them away. Typical axes: deployment mode, node role, topology, distro,
+filesystem, single versus multi host.
+
+Two numbers for two modes beats one blended number that is wrong in both.
+
+## Weigh the failure mode, not only the probability
+
+A low-probability failure that **fails open** can outrank a likely one that
+fails closed. Ask what the world looks like when the change misbehaves:
+
+- Fails closed and loud: the service refuses to start, a gate goes red, a
+  request errors. Cheap to detect, bounded blast radius.
+- Fails open and silent: a port stays reachable, a check passes vacuously, a
+  credential keeps working, traffic is forwarded to an unintended place.
+
+Say which one applies. When a design choice is between an unverifiable control
+over an exposure and not creating the exposure, prefer the second and say why.
+
+## Evidence rules
+
+- Executed beats derived. Run it, render it, read the output.
+- A subagent's report, a conversation summary, or your own earlier message is
+  **not** evidence. Re-verify the claim yourself before it changes a number.
+- Negative control before claiming a check works: make the thing it should
+  catch, watch it fail, restore. A check never observed failing is not known to
+  work.
+- The same applies to a check you did not write. Citing an existing lint, test
+  or gate as the reason a change is safe means reading its pattern, not its
+  docstring, and watching it fail on the case you are trusting it to catch. A
+  green gate whose rule never matched your case is silence, not a pass.
+- After a context compaction, rebuild attributions from the source; conclusions
+  survive compaction, the evidence under them does not.

skills/changelog/SKILL.md

@@ -0,0 +1,143 @@
+---
+name: changelog
+description: >
+  Write the release message since the last release for `pkgmgr release`;
+  prints it only, never edits CHANGELOG.md, tags or releases. Trigger on
+  /changelog, "release message", "changelog entry", before cutting a release,
+  or on pkgmgr's markdown-lint rejection.
+---
+
+The message is one text that pkgmgr writes to four places: the CHANGELOG.md
+entry, the annotated release tag, `debian/changelog` and the RPM `%changelog`.
+Every rule below exists because one of those four would otherwise break or
+mangle it.
+
+## 1. Find the range
+
+```bash
+git fetch --tags
+git describe --tags --abbrev=0 --match 'v[0-9]*.[0-9]*.[0-9]*'
+git log --no-merges --format='%h %s%n%b' <tag>..HEAD
+```
+
+- pkgmgr tags every release `vX.Y.Z`; the newest one reachable from HEAD is
+  the base. No such tag: the range is the whole history, say so.
+- Drop the `Release version X.Y.Z` commits and any revert together with the
+  commit it reverts inside the range.
+- A subject is a lead, not the change: read the diff (`git show --stat`, then
+  the hunks) when the subject does not say what changed for the user.
+- When `gh` is available, read the CI of the previous tag's commit and of HEAD,
+  every workflow (`gh run list --commit <sha> --json
+  workflowName,status,conclusion`), not one picked by `-L 1`.
+  - Previous tag: a workflow that finished as a failure means that version was
+    never published: say so under *Upgrade notes* and carry its upgrade notes
+    forward to this release.
+  - HEAD: a workflow that finished as a failure means pkgmgr would tag a
+    release that never goes stable, because its CI gate runs after the tag.
+    Queued, running or missing runs are normal; report only the failure, in
+    step 5.
+
+## 2. Sort into sections
+
+| Commit | Section |
+| --- | --- |
+| `feat` | Added, or Changed when it alters existing behaviour |
+| `fix`, `perf` | Fixed |
+| `!` or `BREAKING CHANGE:` | Breaking, plus one Upgrade notes line per required action |
+| `docs`, `style`, `refactor`, `test`, `ci`, `build`, `chore` | omitted unless a user sees the effect |
+| dependency bumps | one collapsed line, or omitted |
+
+When nothing user-visible remains (a test- or CI-only release), keep those
+commits under Fixed with an area prefix (`Tests:`, `CI:`) so the entry is not
+empty.
+
+Order: Breaking, Added, Changed, Fixed, Upgrade notes. Leave out empty
+sections.
+
+## 3. Format
+
+```text
+Fixed:
+
+- Backup: rsync -a stored no xattrs, ACLs or hardlinks; now -aHAX
+- Restore: *--empty* no longer aborts on a database with an extension
+
+Upgrade notes:
+
+- First backup re-copies every attribute-carrying volume once in full
+```
+
+1. **Section labels are plain lines ending in `:`**, never `#` headings and
+   never a bold-only line. pkgmgr creates the tag with `git tag -a -m`, whose
+   default `strip` cleanup deletes every line starting with `#`. A bold-only
+   line fails MD036.
+2. **No version heading, date or "Release X.Y.Z" line.** pkgmgr adds
+   `## [X.Y.Z] - YYYY-MM-DD` itself.
+3. **One bullet, one line. Too long means shorter, never wrapped.** RPM turns
+   every non-empty line into its own `-` entry and Debian indents each line,
+   so a continuation line becomes a separate, broken entry.
+4. **Line length: the repository's MD013 limit**, which is markdownlint's
+   default of 80 unless the repo's config changes it. Aim for 78 or less, so
+   lines stay within 80 after Debian's two-space indent and RPM's two-character
+   `-` prefix.
+5. **Lists use the marker CHANGELOG.md already uses**, no nesting, with a
+   blank line before and after every list (MD004, MD032). MD004's default
+   *consistent* style takes the marker of the first list in the file, and
+   pkgmgr puts the new entry on top, so a marker that differs from the older
+   entries turns every older list into a finding. Take the marker of the first
+   list item in the existing CHANGELOG.md; use `-` only when there is no
+   CHANGELOG.md yet, and the configured one when the repo's MD004 pins a style.
+6. **No backticks and no code blocks.** pkgmgr rewrites inline code to
+   *italic* in all four targets, and a fenced block fails its fallback lint.
+   Write *names*, *--flags* and *paths* in `*` italics yourself; use `*`, not
+   `_`, for emphasis (MD049).
+7. **Bullet text is `Area: effect`**: the component the user knows (Backup,
+   Restore, CLI, Tests), then what changed for them, not how the code
+   changed. No commit SHAs, no em dashes: use `:` or `;`.
+8. **Plain hygiene**: no trailing whitespace (MD009), no double blank lines
+   (MD012), no bare URLs: wrap them as `<https://...>` (MD034).
+
+## 4. Lint it the way pkgmgr does
+
+pkgmgr wraps the message as `# Changelog`, blank line, `## [X.Y.Z] - date`,
+blank line, message, then runs `markdownlint-cli2` with the target repo's own
+config. Reproduce that exactly:
+
+1. Write that wrapped document to a scratch file outside the repository.
+2. From the repository root, so its config is picked up, run:
+
+   ```bash
+   markdownlint-cli2 --no-globs - < <scratch-file>
+   ```
+
+   *--no-globs* keeps the config's own globs from linting the whole tree too.
+3. A finding on line N points at message line N - 4. Shorten that line and
+   lint again; print nothing until the result is 0 errors.
+4. The standalone check cannot see rules that compare the entry with the rest
+   of the file (MD004 *consistent*, MD024 duplicate headings), but the
+   repository's own markdown lint and pre-push gate do. Copy CHANGELOG.md to a
+   scratch file, insert the wrapped heading and message below its
+   `# Changelog` line, and lint that copy the same way. A finding in the older
+   entries that the unmodified CHANGELOG.md does not produce comes from the
+   new entry; fix the message, never the older entries.
+
+Without `markdownlint-cli2`, check by hand what pkgmgr's fallback checks plus
+the length limit: no line over the limit, no trailing whitespace, no
+backtick, no double blank line.
+
+When the operator pastes pkgmgr's rejection (`changelog entry:7:81 error
+MD013/line-length ...`), apply the same N - 4 mapping to the message they
+used, shorten only the lines it names, and lint again.
+
+## 5. Output
+
+1. The message in one fenced `text` block, nothing else inside it.
+2. One line: `Bump: patch | minor | major` and why (breaking → major,
+   `feat` → minor, otherwise patch).
+3. One line with the lint result (`markdownlint-cli2: 0 errors` or the manual
+   check that ran).
+4. Only when a workflow on HEAD finished as a failure: one line naming it and
+   its run, and the advice not to release before it is green.
+
+Then stop. Never edit CHANGELOG.md or a version file, never run
+`pkgmgr release`, never tag: the operator releases.

skills/ci-artifacts/SKILL.md

@@ -0,0 +1,78 @@
+---
+name: ci-artifacts
+description: >
+  Get the evidence out of a CI run: failed job logs (also mid-run) clustered
+  by error line, and the artifacts that hold the cause. Trigger whenever a CI
+  failure must be explained, and from triage.
+---
+
+A job log tells you what broke. An artifact tells you why. Investigating a CI
+failure without downloading its artifacts is guessing with extra steps.
+
+## Getting the log
+
+For a GitHub Actions run, one call does it:
+
+    ${CLAUDE_SKILL_DIR}/scripts/ci_failures.py <RUN_ID> [--repo <owner>/<repo>] [--artifacts]
+
+It prints how far HEAD moved since the run's commit, saves every finished
+failed job's log to `/tmp/ci-logs-<run>/` (colour stripped, even while the run
+is still in progress), and clusters the jobs by the normalised error line that
+ended them. Jobs still running are listed, not fetched: their API log can stop hours
+early. The clustering is a heuristic; check each boundary against the logs.
+
+Grep the saved files repeatedly. Re-fetching a log to find the line you just
+lost costs minutes; grepping the saved copy costs milliseconds.
+
+## Getting the artifacts
+
+    gh api /repos/<owner>/<repo>/actions/runs/<RUN_ID>/artifacts --paginate \
+      --jq '.artifacts[] | "\(.name)\t\(.size_in_bytes)"'
+    gh run download <RUN_ID> --repo <owner>/<repo> -n <NAME> -D <DIR>
+
+Choose by content, not by name length:
+
+- **Rescue / diagnostics bundles** carry the reverse-proxy access and error log,
+  the per-service and per-container logs, the journal, and the event stream.
+  This is where causes live. Prefer them.
+- **Test-report bundles** (Playwright and friends) are mostly video and traces
+  and can run to hundreds of megabytes for one assertion string. Pull one only
+  when you need the assertion text or the error-context file.
+- **Inventory / runtime dumps** settle "what was actually deployed" questions.
+
+Inside a rescue bundle, read in this order: the reverse-proxy log (it shows
+status code, upstream, and time-to-response for the exact failing request), the
+application container log, then the journal and event stream for restarts and
+OOM kills.
+
+An access-log line is a timing witness. A `499` means the *client* gave up; the
+server was still working. A `504` or an `upstream timed out ... while reading
+upstream` means your backend never answered. `ReqTime` versus `UpstreamTime`
+tells you whether the proxy or the upstream burned the seconds.
+
+## Grep hygiene
+
+Two failure modes turn a search into a false conclusion:
+
+- **Clustered flags silently change the pattern.** Write them separately —
+  `grep -r -a -i -l -F "needle" dir/`, not `-ariel`. A cluster where one letter
+  takes an argument consumes your pattern and searches for something else, and
+  the run still exits successfully.
+- **Substring matches lie.** A protocol token like `h2c` matches inside
+  `veth2cb3f8c`; a short id matches inside a hash. Before concluding anything
+  from a hit, print its context (`grep -o ".\{30\}needle.\{30\}"`) and look at
+  it. Before concluding anything from a *miss*, prove the command was
+  well-formed by searching for a string you know is present.
+
+Binary-ish logs need `-a`, or grep reports "binary file matches" and you see
+nothing.
+
+## Rules
+
+- Download before theorising. Do it even when the job log looks conclusive: a
+  log that explains the symptom rarely explains the cause.
+- Quote literally, with the file path and line number. Never paraphrase a log
+  line you did not read, and never reconstruct one from memory.
+- A negative result is a finding only when the search was verified sound.
+- "The artifact does not settle this" is a legitimate answer. Say it instead of
+  filling the gap with a plausible mechanism.

skills/ci-artifacts/scripts/ci_failures.py

@@ -0,0 +1,170 @@
+#!/usr/bin/env python3
+"""Fetch the failed jobs of a GitHub Actions run and cluster them by error line.
+
+Usage:
+    ci_failures.py RUN_ID [--repo OWNER/REPO] [--out DIR] [--artifacts]
+
+Prints how far HEAD moved since the run's commit, saves each finished failed
+job's log (colour stripped) under DIR (default /tmp/ci-logs-RUN_ID), and
+groups the jobs by the normalised error line that ended them (the last one). Jobs still running are
+listed but not fetched: their API log can stop hours early. The clustering is
+a heuristic; confirm a cluster's boundary against the logs.
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+import re
+import subprocess
+import sys
+from pathlib import Path
+
+FAILED = {"failure", "cancelled", "timed_out"}
+ANSI = re.compile(r"\x1b\[[0-9;]*[A-Za-z]")
+STAMP = re.compile(r"^\d{4}-\d\d-\d\dT[\d:.]+Z\s?")
+GENERIC = re.compile(r"failed=0\b|FAILED - RETRYING|^make(\[\d+\])?: \*\*\* \[.*\] Error \d+")
+PROCESS_END = re.compile(r"##\[error\]Process completed with exit code")
+ANNOTATION = re.compile(r"##\[error\]")
+FATAL = re.compile(r"fatal: \[|FAILED!|Traceback|AssertionError|panic:")
+LINT_AT = re.compile(r"\S+:\d+:\d+:? ((error|warning) )?[A-Z]{1,4}\d{3,4}\b")
+LINT_CODE = re.compile(r"^[A-Z]{1,4}\d{3,4}\b")
+LINT_ARROW = re.compile(r"^-->\s+\S+:\d+:\d+")
+SIGNAL = re.compile(r"\b(ERROR|Error|FAILED|FAIL|fatal|Exception|failed)\b")
+TASK = re.compile(r"^TASK \[")
+REFUSAL = "terminal escape sequences"
+
+
+def run(*cmd: str) -> subprocess.CompletedProcess:
+    return subprocess.run(list(cmd), capture_output=True, text=True, check=False)
+
+
+def clean(line: str) -> str:
+    return STAMP.sub("", ANSI.sub("", line)).strip()
+
+
+def normalise(line: str) -> str:
+    line = re.sub(r"\b[0-9a-f]{7,}\b", "<hex>", line)
+    line = re.sub(r"\d+", "<n>", line)
+    return line[:200]
+
+
+def output_lines(text: str) -> list[tuple[str, str]]:
+    kept, echo, task = [], False, ""
+    for raw in text.splitlines():
+        line = clean(raw)
+        if PROCESS_END.search(line):
+            break
+        if line.startswith("##[group]Run "):
+            echo = True
+        elif line.startswith("##[endgroup]"):
+            echo = False
+        elif TASK.match(line):
+            task = line
+        elif line and not echo and not GENERIC.search(line):
+            kept.append((task, line))
+    return kept
+
+
+def is_lint(lines: list[tuple[str, str]], index: int) -> bool:
+    line = lines[index][1]
+    if LINT_AT.search(line):
+        return True
+    following = lines[index + 1][1] if index + 1 < len(lines) else ""
+    return bool(LINT_CODE.match(line) and LINT_ARROW.match(following))
+
+
+def signature(text: str) -> str:
+    lines = output_lines(text)
+    tiers = (
+        (lambda i: ANNOTATION.search(lines[i][1]), False),
+        (lambda i: FATAL.search(lines[i][1]), True),
+        (lambda i: is_lint(lines, i), False),
+        (lambda i: SIGNAL.search(lines[i][1]), False),
+    )
+    for matches, with_task in tiers:
+        for index in reversed(range(len(lines))):
+            if matches(index):
+                task, line = lines[index]
+                found = ANNOTATION.sub("", line).strip()
+                return normalise(f"{task} {found}" if with_task and task else found)
+    return normalise(lines[-1][1]) if lines else "<empty log>"
+
+
+def cluster(jobs: list[tuple[str, str]]) -> dict[str, list[str]]:
+    groups: dict[str, list[str]] = {}
+    for job, text in jobs:
+        groups.setdefault(signature(text), []).append(job)
+    return dict(sorted(groups.items(), key=lambda item: -len(item[1])))
+
+
+def behind(sha: str) -> str:
+    if run("git", "cat-file", "-e", f"{sha}^{{commit}}").returncode:
+        return "behind=unknown (run commit not in this clone)"
+    count = run("git", "rev-list", "--count", f"{sha}..HEAD").stdout.strip()
+    moved = {p.split("/")[0] for p in run("git", "diff", "--name-only", f"{sha}..HEAD").stdout.split()}
+    return f"behind={count} moved={','.join(sorted(moved)) or '-'}"
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(prog="ci_failures")
+    parser.add_argument("run_id")
+    parser.add_argument("--repo")
+    parser.add_argument("--out")
+    parser.add_argument("--artifacts", action="store_true")
+    args = parser.parse_args()
+    repo = args.repo or run("gh", "repo", "view", "--json", "nameWithOwner", "-q", ".nameWithOwner").stdout.strip()
+    if not repo:
+        parser.error("no --repo and gh cannot resolve the current repository")
+    meta = run("gh", "api", f"/repos/{repo}/actions/runs/{args.run_id}")
+    # per_page=100 on a large matrix answers HTTP 502; 30 per page goes through.
+    listing = run("gh", "api", "--paginate", f"/repos/{repo}/actions/runs/{args.run_id}/jobs?per_page=30",
+                  "--jq", ".jobs[] | {id, name, status, conclusion}")
+    if meta.returncode or listing.returncode:
+        print((meta.stderr or listing.stderr).strip(), file=sys.stderr)
+        return 1
+    data = json.loads(meta.stdout)
+    jobs = [json.loads(line) for line in listing.stdout.splitlines() if line]
+    out = Path(args.out or f"/tmp/ci-logs-{args.run_id}")
+    out.mkdir(parents=True, exist_ok=True)
+    print(f"run={args.run_id} repo={repo} head={data['head_sha'][:10]} status={data['status']} "
+          f"jobs={len(jobs)} {behind(data['head_sha'])}")
+    running = [j["name"] for j in jobs if j["status"] != "completed"]
+    if running:
+        print(f"running ({len(running)}, not fetched): {', '.join(running)}")
+    fetched, missing = [], []
+    for job in jobs:
+        if job["status"] != "completed" or job["conclusion"] not in FAILED:
+            continue
+        log = run("gh", "api", "--allow-escape-sequences", f"/repos/{repo}/actions/jobs/{job['id']}/logs")
+        if log.returncode or REFUSAL in log.stdout[:200]:
+            missing.append(f"{job['conclusion']}\t{job['name']}\t{log.stderr.strip()[:80]}")
+            continue
+        slug = re.sub(r"[^A-Za-z0-9._-]+", "_", job["name"])[:80]
+        path = out / f"{job['id']}-{slug}.log"
+        path.write_text("\n".join(ANSI.sub("", line) for line in log.stdout.splitlines()), encoding="utf-8")
+        text = "##[error]cancelled" if job["conclusion"] == "cancelled" else log.stdout
+        fetched.append((f"{job['conclusion']}\t{job['name']}\t{path}", text))
+    if missing:
+        (out / "no-log.txt").write_text("\n".join(missing) + "\n", encoding="utf-8")
+        counts = {c: sum(m.startswith(c) for m in missing) for c in FAILED}
+        summary = ", ".join(f"{n} {c}" for c, n in sorted(counts.items()) if n)
+        print(f"no log for {len(missing)} jobs ({summary}; never started or expired): {out / 'no-log.txt'}")
+    for number, (sig, jobs) in enumerate(cluster(fetched).items(), 1):
+        print(f"cluster {number} ({len(jobs)} jobs): {sig}")
+        for job in jobs[:3]:
+            print(f"  {job}")
+        if len(jobs) > 3:
+            members = out / f"cluster-{number}.txt"
+            members.write_text("\n".join(jobs) + "\n", encoding="utf-8")
+            print(f"  ... +{len(jobs) - 3} more: {members}")
+    if args.artifacts:
+        listing = run("gh", "api", f"/repos/{repo}/actions/runs/{args.run_id}/artifacts", "--paginate",
+                      "--jq", '.artifacts[] | "\\(.name)\\t\\(.size_in_bytes)"')
+        print("artifacts:")
+        print(listing.stdout.rstrip() or "  none")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

skills/cleanup/SKILL.md

@@ -0,0 +1,177 @@
+---
+name: cleanup
+description: >
+  Free disk space agents filled: ask peer sessions what they still need,
+  inventory /tmp, Docker and agent dirs, and delete only what the operator
+  picks. Trigger on /cleanup, "aufräumen", "bereinigen", "platte voll", "no
+  space left on device".
+---
+
+Nothing is deleted before the operator has picked it. Every candidate carries
+its owner, its size, and its risk.
+
+## Step 0: the resource chair
+
+Shared resources belong to the resource chair of the `democracy` skill. If
+another session holds the chair, send it the cleanup request and stop, unless
+the operator ordered the cleanup in this session; then tell the chair before
+step 1, so its grants and queue stay consistent. The `democracy` resource
+watch already runs the configured low-risk cleanup at its stop threshold; this
+skill covers everything that needs the operator's pick.
+
+## Step 1: ask the peers
+
+List every agent the host can message (in Claude Code: `ListAgents`). Only
+peers sharing this machine's filesystem and Docker daemon count: local
+sessions and your own subagents. Cloud sessions and remote sessions on other
+machines hold nothing here; skip them.
+
+Send each local peer one message (`SendMessage`) and go on with step 2 while
+they answer:
+
+```text
+Cleanup planned by <own session name>. Reply to me with everything you still
+need, one item per line:
+- paths under /tmp, caches, worktrees
+- containers, compose or stack projects, volumes, images, networks
+- running jobs (deploys, tests, builds) and when they finish
+Reply "nothing" if you need none of it. Items you do not answer for stay.
+```
+
+## Step 2: inventory
+
+Read-only, in parallel, sizes included:
+
+- **Scope**: the directories agents may write to, taken from the host's
+  sandbox or permission config (in Claude Code:
+  `sandbox.filesystem.allowWrite` in `.claude/settings.json`) plus the session
+  scratch dirs. Anything outside is out of scope, even when readable.
+- **/tmp**: `du -sh` per top-level entry the current user owns. System entries
+  (`.X11-unix`, `.ICE-unix`, `systemd-private-*`, `ssh-*`, `tmux-*`, sockets)
+  are never candidates.
+- **Docker**: `docker system df -v`; containers with state and compose project
+  label, volumes with the containers using them
+  (`docker ps -a --filter volume=<name>`), dangling and unused images, build
+  cache, unused networks. For every stopped container (`exited`, `created`)
+  record its volumes (`{{.Mounts}}`); for every volume no running container
+  uses, record size, `CreatedAt` (`docker volume inspect`) and compose project
+  label, anonymous ones included.
+- **Other agent dirs**: package and tool caches (pip, npm, pre-commit, act,
+  gh, buildx), worktrees with `git status --short` and whether their branch is
+  merged or pushed, Ansible and build temp dirs. With `pkgmgr` installed,
+  merged branches and worktrees go to the `branch-gc` skill instead.
+- **Live use**: open handles (`fuser`, `lsof`) and running processes by name
+  only (`ps -o pid,etime,comm`). Never print full command lines or
+  environments: process arguments carry credentials. A sandboxed agent often
+  sees only its own processes, so an empty handle list proves nothing there;
+  then only entries untouched for more than 24 hours (`find -mtime +0`) are
+  candidates, and newer ones stay as `keep (recent, possibly in use)`.
+- **Archive duties**: memory and project instructions that require copying
+  something out before deletion (logs, reports, generated maps). Such an item
+  is `archive first`, never a plain delete.
+
+Prefer the project's own cleanup and teardown targets (Makefile, scripts) over
+raw commands where they exist, and obey project rules that forbid raw
+commands.
+
+## Step 3: attribute
+
+Give every candidate an owner: a peer's reply, a session id in the path, a
+worktree or compose project name, a container label, an open handle, or
+`unknown`. Then apply, first match wins:
+
+1. Claimed by a peer: `keep`.
+2. A job running on it (deploy, gate, test, swarm run, build): `keep
+   (running)`.
+3. Attributable to a peer that has not answered: `keep (no answer from
+   <peer>)`. Silence is not consent.
+4. Archive duty: `archive first`.
+5. Everything else is a candidate with a risk class:
+
+| Risk | Meaning | Typical items |
+| ---- | ------- | ------------- |
+| low | regenerated automatically, cheap | stopped containers without volumes, dangling images, unused networks, scratch dirs and logs of finished sessions |
+| medium | regenerated, but slow, rate-limited or network-bound | unused tagged images (re-pull, registry limits), build cache (cold rebuilds), package caches |
+| high | data loss or a broken run possible | volumes, stopped containers with volumes, running unclaimed containers or stacks, worktrees with uncommitted or unpushed work, unread reports, anything `unknown` |
+
+## Step 4: propose
+
+One table, biggest first:
+
+| Area | Item | Size | Owner | Risk | Proposal | What breaks if wrong |
+
+Below it: reclaimable size per risk class, and every `keep` row grouped by
+reason, so the operator sees what was protected and why.
+
+Then ask with `AskUserQuestion` in two calls.
+
+**Call 1, the selection** (`multiSelect: true`, checklists, at most four
+questions): `/tmp`, `Docker`, `Other dirs`, and a separate `High risk`
+question that holds every high-risk candidate. Size, risk and worst case go
+into each option's description. An area with more than four options is
+grouped by owner or risk, or split into a further call. Only ticked items are
+selected; nothing is preselected.
+
+**Stopped containers and volumes** always get their own checklist
+(`multiSelect: true`, header `⚠ Volumes`, in a further call when call 1 is
+full). Every stopped container and every volume without a running container
+appears there unless a peer claimed it; none is dropped as "not proposed",
+`unknown` and anonymous ones included. The question text carries the warning:
+`Deleting a volume is irreversible; its data does not come back unless the
+description says how.` One option per stopped container together with its
+volumes (removing the container alone frees nothing of them), one per
+unattached volume, anonymous ones grouped. Each description gives size,
+`CreatedAt`, owner or compose project, and what is lost.
+
+**Call 2, the confirmation** (`multiSelect: false`, radio buttons), computed
+from the ticks: `Execute: <n> items, <size> (Recommended)`, `Revise the
+selection`, `Abort`. The execute description names the worst case of the
+ticked items. Revise repeats call 1; nothing is deleted before `Execute`.
+
+## Step 5: execute
+
+- Re-check claims, open handles and running state right before each delete: a
+  peer may have started something since the inventory.
+- Delete exactly the selected items, by name or path. No blanket prune
+  (`docker system prune -a --volumes`, `rm -rf /tmp/*`) that sweeps beyond the
+  selection. For more than a handful of paths, write the list to a file under
+  `/tmp`, grep it against every claim once more, then delete with
+  `xargs -d '\n' rm -rf -- < <list>`.
+- Locally built images free little on their own: their layers stay behind as
+  build cache. After removing images, re-measure `docker system df`; the
+  layers show up as reclaimable build cache. Offer
+  `docker builder prune --filter until=24h` as a follow-up candidate, ask the
+  peers that claimed build cache first, and run it outside their running
+  builds.
+- A host permission layer (an auto-mode classifier, a deny rule) may refuse a
+  delete. Never route around it with another command or a peer. Finish the
+  rest, then put the refused item to the operator again as its own option: an
+  explicit renewed selection may pass; if it is refused again, hand over the
+  exact command with its list file for the operator to run.
+- Never stop, take down or kill a running job, and never ask its owner to, to
+  free space: not for a priority slot, not at a disk stop. Free idle items,
+  ask the operator for an exception, or wait; an owner's own disk guard only
+  alerts the chair, and only the operator can order a running job down.
+- Idle running stacks go down through the project's teardown target, never by
+  removing their containers or volumes underneath them.
+- Archive-first items: copy out, verify the copy, then delete.
+- A delete failing on permissions (files owned by a container UID): use the
+  project's container helper. Never sudo, never bypass the sandbox; without a
+  helper, report the path.
+- Stop on the first unexpected error and report it.
+
+## Step 6: report
+
+`df -h` and `docker system df` before and after, freed size per area, every
+skipped or failed item with its reason. Tell each peer that answered which of
+the removed items lay near its own.
+
+## Rules
+
+- Questions, inventory and proposal change nothing. Deletion needs the
+  operator's selection in this run; a selection from an earlier run does not
+  carry over.
+- Never delete outside the agent write scope, another user's files, or system
+  entries in `/tmp`.
+- Never invent a peer's answer or a size. Unmeasured is `unknown`, and
+  `unknown` is high risk.

skills/comments-clean/SKILL.md

@@ -2,12 +2,9 @@
 name: comments-clean
 description: >
   Purge explanatory comments from staged and unstaged changes. Run
-  AUTOMATICALLY, without being asked, every time the operator requests a
-  commit or stage in any wording (commit, commit no-verify, stage next,
-  socon, sobu, socobu, "commite ..."), BEFORE executing that request; also
-  on /comments-clean or when the operator complains about comments.
-  Explanatory comments are bad practice: they narrate code instead of
-  letting it speak. Portable across projects.
+  AUTOMATICALLY before every commit or stage request (commit, commit
+  no-verify, stage next, socon, sobu, socobu, "commite ..."); also on
+  /comments-clean or comment complaints.
 ---
 
 When the operator asks to commit or stage, run this audit first and only
@@ -23,9 +20,22 @@ added lines only) and delete every explanatory comment:
 2. Keep only: parameter/exit-code docs, nocheck/noqa/shellcheck directives,
    and project-sanctioned exception markers that name a concrete trip-wire.
    A relabeled narration is not an exception; delete it instead.
-3. Re-run the project's comment lint if one exists and re-stage the files
-   that were already staged.
-4. Penalty: if this audit finds anything you wrote yourself, admit it in
+3. Block-comment languages are not line-oriented. In Jinja (`{# … #}`), C-like
+   (`/* … */`), HTML (`<!-- … -->`) and their kin, a closing delimiter alone on
+   its own line looks exactly like a comment line and gets deleted with the
+   rest — after which the opening delimiter swallows every live statement down
+   to the next closer. Never strip these languages with a line filter. Delete
+   the whole block by hand, then count the delimiters (`grep -c '{#'` against
+   `grep -c '#}'`) and re-parse the file.
+4. Re-run the project's comment lint if one exists. A green lint does NOT prove
+   the deletion was safe: a swallowed block is still syntactically valid, so
+   both the lint and the language parser can pass over code that no longer
+   executes. Diff against the pre-edit revision (`git show HEAD:<path>`) and
+   confirm that only comment lines left.
+5. Do not stage in order to run a check (the `commit-next` skill's step 4
+   says why). Re-stage after the audit exactly the files that were staged
+   before it.
+6. Penalty: if this audit finds anything you wrote yourself, admit it in
    the report (file and count, no excuses), lower your confidence numbers
    for the affected bundle, and write the incident to persistent agent
    memory (extend the existing minimal-comments feedback entry with the

skills/commit-next/SKILL.md

@@ -1,20 +1,36 @@
 ---
 name: commit-next
 description: >
-  Commit the staged bundle with --no-verify, then stage the next logical
-  bundle and brief the operator on it. Trigger on /commit-next or when the
-  operator asks to commit and stage the next bundle in one step. Portable
-  across projects.
+  Check every branch for the staged fix, commit the staged bundle with
+  --no-verify, then stage and brief the next bundle. Trigger on /commit-next
+  or when the operator asks to commit and stage the next bundle in one step.
 ---
 
-1. Run the commit-no-verify skill on the currently staged changes
-   (comments-clean audit first, then `git commit --no-verify`, exact
+1. `git fetch --all --prune --tags`, then hunt the staged fix across every
+   ref with the merge-fix skill's `find_fix.py` (by `--grep`, by `-S`, by
+   `--path`). Describe the staged bundle in one line first so a
+   wrong search intent is visible. Only the search runs here — never
+   cherry-pick or merge, and never touch the staging index or the tree.
+2. A similar fix on another branch is a stop: run the dialectic skill on the
+   two candidates (staged version as thesis, foreign commit as antithesis)
+   until one survives, then present sha, branch, both diffs, the verdict and
+   the recommended move (keep staged / take theirs / combine). Wait for the
+   operator's decision; do not commit.
+3. Nothing similar found, or the operator picked the staged version: run the
+   commit-no-verify skill on the currently staged changes (comments-clean
+   audit and advocate check first, then `git commit --no-verify`, exact
    staging index only).
-2. Group the remaining uncommitted changes into logical bundles (one
+4. Group the remaining uncommitted changes into logical bundles (one
    concern per bundle: same failure class, same mechanism, or same role)
-   and stage the next one; never mix concerns to save a commit.
-3. For the newly staged bundle run the explain skill (what the changes do
+   and stage the next one; never mix concerns to save a commit. Staging
+   happens here and nowhere else: never stage merely to run a lint or a
+   test. Repository checks that enumerate through `git ls-files` already
+   see tracked, modified files and read the worktree; only an untracked
+   NEW file needs `git add` to become visible. Path-scope every `git add`
+   to the bundle — `git add -A` sweeps up the operator's own edits and
+   their local config.
+5. For the newly staged bundle run the explain skill (what the changes do
    and how the pieces interact, file:line-anchored) followed by the
    confidence skill (fix confidence, break risk, evidence, residuals).
-4. Close with what remains unstaged and wait for the operator's commit
+6. Close with what remains unstaged and wait for the operator's commit
    decision; never auto-commit the newly staged bundle.

skills/commit-no-verify/SKILL.md

@@ -1,14 +1,14 @@
 ---
 name: commit-no-verify
 description: >
-  Commit the currently staged changes with --no-verify (skip the pre-commit
-  hooks). Trigger on /commit-no-verify or when the operator asks for a
-  no-verify commit in any wording. Invoking this skill IS the explicit
-  per-commit authorization that --no-verify requires; it never carries over
-  to later commits. Portable across projects.
+  Commit the staged changes with --no-verify. Trigger on /commit-no-verify or
+  any request for a no-verify commit; invoking it IS the per-commit
+  authorization --no-verify requires, never carried over to later commits.
 ---
 
-1. Run the comments-clean audit over the staged and unstaged changes first.
+1. Run the comments-clean audit over the staged and unstaged changes first,
+   then the advocate check over the staging index. An advocate blocker stops
+   here.
 2. Commit exactly the staging index with `git commit --no-verify` and a
    Conventional-Commits message derived from the staged diff; never add
    unstaged files, never push.

skills/confidence/SKILL.md

@@ -1,18 +1,21 @@
 ---
 name: confidence
 description: >
-  Report calibrated confidence unprompted. Trigger whenever you stage
-  changes, declare a fix or bundle ready, or summarize completed work the
-  operator may commit or deploy — the operator must never have to ask "how
-  sure are you?". Portable across projects.
+  Report calibrated fix confidence and break risk unprompted whenever you
+  stage changes, declare a fix or bundle ready, or summarize work the operator
+  may commit or deploy.
 ---
 
 Every stage summary, fix report, or ready-to-commit bundle ends with a
-confidence block:
+confidence block.
+
+Invoke the `break-risk` skill every time, before writing the block; this skill
+reports the number it derives and never estimates one itself.
 
 1. **Fix confidence** (percent): probability the change does what it
-   claims. **Break risk** (percent): probability it breaks anything else.
-   Two separate numbers, never one blended figure.
+   claims. **Break risk** (percent): probability it breaks anything else,
+   derived via the `break-risk` skill. Two separate numbers, never one
+   blended figure.
 2. **Evidence**: the strongest proof lines only — what was executed,
    reproduced, enumerated, or read from authoritative source. Distinguish
    proven (ran it, saw it) from derived (reasoned statically).
@@ -21,9 +24,17 @@ confidence block:
    Never a bare percentage without its residuals.
 
 Calibration rules:
+
 - Number the claim you verified, not the effort you spent; discount after
   any error the operator caught in the same area.
 - Distinguish "fixes the observed failure" from "makes the job green" when
   hidden layers may follow, and give both numbers.
 - Static analysis alone caps at the low nineties; only executed evidence
   (test, reproduction, live probe) justifies more.
+
+A threshold the operator named ("95% confidence, break risk ≤5%") is a gate on
+the work, handled as the `break-risk` skill's last section says, for both
+numbers.
+
+Objective: the `autotune` skill's **Objective** section. Two figures with their residuals replace a
+hedging paragraph and save the operator a verification round trip.

skills/coordinate/SKILL.md

@@ -0,0 +1,11 @@
+---
+name: coordinate
+description: >
+  Coordinate a failure or fix with the agents on related branches through
+  merges: claim, ask, report. Trigger on /coordinate and when a fix touches
+  code other branches share.
+---
+
+Run the `democracy` skill's **Lineage** and **Peer protocol** sections for the
+failure or fix at hand. They hold the whole procedure; this skill only keeps
+`/coordinate` working.

skills/criticize/SKILL.md

@@ -0,0 +1,93 @@
+---
+name: criticize
+description: >
+  Give constructive criticism of a problem, plan, design, decision, text or
+  code from diverse aspects, each point hardened by dialectic. Trigger on
+  /criticize, "kritisiere", "kritisch betrachten", "konstruktive Kritik", "was
+  haeltst du davon", or requests for honest feedback.
+---
+
+The stance is critical but constructive: the goal is a better result, not a
+verdict on its author. This skill judges any artifact from many angles; it is
+not limited to code (`sceptic` hunts violated engineering principles in code,
+`code-review` hunts bugs). Read-only: report the critique, change nothing
+unless the operator asks afterwards.
+
+## Before you start: listen
+
+Invoke the `active-listening` skill. Pin down what is being criticized, what it
+is meant to achieve, for whom, and under which constraints. Derive what you can
+from the artifact and its surroundings first; ask only what only the operator
+knows. A critique against the wrong goal is noise.
+
+## Steelman first
+
+Restate the artifact and its intent in its strongest form, in two or three
+sentences. Criticize that version, never a weaker one you made up. If you cannot
+steelman it, you have not understood it yet; go back to listening.
+
+## The aspects
+
+Sweep every aspect that applies, and name the ones you skipped and why:
+
+1. **Goal fit** - does it solve the stated problem for the stated audience, or
+   a neighbouring one?
+2. **Correctness** - are the facts, the logic, and the claimed cause-effect
+   chains right? Which claim lacks evidence?
+3. **Completeness** - missing cases, missing stakeholders, missing failure
+   paths, missing definition of done.
+4. **Consistency** - contradictions inside the artifact or against its
+   neighbours; the same truth stated twice in two versions.
+5. **Simplicity** - mechanism, scope, or wording the problem never asked for;
+   the smaller design that does the same.
+6. **Feasibility and cost** - effort, dependencies, order of steps, what blocks
+   what, what it costs to run and to maintain.
+7. **Risk** - security at trust boundaries, data loss, reversibility, blast
+   radius, what happens when it fails halfway.
+8. **People** - usability, accessibility, the reader's or user's actual path,
+   who gains, who carries the burden.
+9. **Alternatives** - at least one materially different approach, compared
+   honestly on the aspects above.
+10. **Ethics and compliance** - only where it touches personal data, licences,
+    law, or fairness.
+
+## Harden every point with dialectic
+
+Run each candidate critique through the `dialectic` skill before reporting it:
+
+- **Thesis**: the critique point with its evidence.
+- **Antithesis**: independent defenders argue that the artifact is right as it
+  is, or that the constraint behind it is real; independent skeptics attack the
+  suggested improvement for new problems it would cause.
+- **Synthesis**: keep the point, refine it, or drop it.
+
+Batch minor points into one dialectic round; run consequential points (high
+severity, expensive to act on, or challenging a premise) one by one.
+
+## Output
+
+One line of scope, then the steelman. Then:
+
+- **Keep**: up to three strengths that must survive any change.
+- **Critique**: one ranked table, highest impact first:
+
+| Severity | Aspect | Observation | Why it matters | Suggestion | Evidence |
+
+`Evidence` is `proven` (read, run, reproduced, cited) or `derived` (reasoned).
+
+Close with at most three lines: how many candidate points dialectic dropped and
+why, the single change that helps most, and the `confidence` skill's numbers for
+the critique as a whole.
+
+## Rules
+
+- Every critique carries a concrete suggestion. A complaint without one becomes
+  an open question or is dropped.
+- Criticize the work, never the person. Direct wording, no sarcasm, no
+  softening of a real problem, no inflation of a minor one.
+- A point that attacks a stated constraint or goal is labelled "challenges a
+  premise" and kept apart from points that work within it.
+- No taste or formatting nitpicks unless the operator asks for them.
+- Answer in the operator's language.
+- The critique ends at the report. Do not fix, stage, or rewrite as part of
+  this skill.

skills/democracy/SKILL.md

@@ -0,0 +1,195 @@
+---
+name: democracy
+description: >
+  Keep parallel agents from duplicating work: the first to claim it owns it;
+  line representatives and a resource chair coordinate. Run AUTOMATICALLY
+  before work another agent might also do (failure, cluster, feature, gate,
+  deploy, cleanup), and on /democracy.
+---
+
+Two agents doing the same work waste the second run and then collide in the
+merge. The remedy is an election nobody has to hold: whoever starts first owns
+the work. The structure is anarcho-syndicalist: councils (soviets) of
+delegates with a bound mandate, organised as a matrix, recallable by the
+operator at any time.
+
+## Offices
+
+- **President of a piece of work**: the first agent that starts it. It does
+  the whole piece. Every later agent hands its findings to the president and
+  moves on to other work; it never builds a second version.
+- **Representative of an organisational line**: the first agent that works in
+  the line. Lines come in as many dimensions as are useful: functional domain
+  (security, GUI, identity, i18n), repository, branch line, host, cloud
+  account. An agent belongs to one line per dimension.
+- **Organiser of a work cluster**: the first agent that starts a cluster
+  cutting across lines (a failure cluster from `triage`, a cost cluster from
+  `tune`, a feature touching several domains). It works the strand end to end
+  and informs the representative of every line the strand touches before it
+  changes that line's files.
+- **Chair**: the earliest-elected president still running. It chairs the
+  council of all representatives and organisers and allocates the resources of
+  the whole system everyone runs on. There is exactly one allocator at any
+  time.
+
+Every office is a mandate, not a rank: it coordinates and allocates, it never
+takes over or directs the content of another agent's work. The operator
+outranks every office and appoints or recalls at will; an operator
+appointment outranks the election.
+
+## Election
+
+The first to claim wins, and the claim is atomic, so two agents can never both
+be first. `${CLAUDE_SKILL_DIR}/scripts/council.py` keeps the claims in
+`/tmp/agents-council`; other runtimes call the same script from their skills
+directory with `--session <id>`.
+
+1. **Name the office**: `work/<slug>`, `cluster/<slug>`,
+   `<dimension>/<line>` for a representative, or `chair`. The slug names the
+   work concretely: the issue number, the failing line, the cost's log line.
+2. **Look first**: `council.py list`. A claim for the same work under another
+   slug counts as first.
+3. **Claim**: `council.py claim <office> --work "<what, evidence, branch or
+   worktree>"`. Exit 0: elected, or already yours. Exit 3: a live agent holds
+   it, and its claim is printed. Exit 4: the holder's session is dead (see
+   Succession).
+4. **Elected**: continue with the Peer protocol; its message is the
+   announcement.
+5. **Not elected**: send the holder your findings and stop on that work.
+
+A Claude Code session cannot edit a file in a git worktree before it holds a
+claim: a PreToolUse hook (`council.py gate`) blocks the edit.
+
+Peers on other machines cannot see this host's claims. Between machines the
+earliest announcement by message time wins, and each host's claim directory
+records the result.
+
+## Chair and resource allocation
+
+- The first agent elected on the system while `chair` is vacant also claims
+  `chair`, in the same way.
+- An operator-appointed allocator holds the chair: its claim says
+  `appointed: operator`, and no election replaces it while its session runs and
+  the operator has not ended the appointment.
+- Before starting anything that consumes shared capacity (gates, deploys,
+  iteration loops, swarm or cloud resources, cleanup of shared data), an agent
+  sends the chair what, where, for how long and its expected disk need, waits
+  for the grant, and reports the release. The chair keeps one queue, answers
+  every request with its position, enforces the limits the operator set,
+  checks every grant with `watch.py admit --need-gb <N>` (or `--kind <slot>`;
+  test kinds also need CPU and RAM below the configured limits).
+- A running job (deploy, gate, test, swarm run, build) is never cut short to
+  free capacity. The chair neither asks nor orders its owner to stop, take
+  down or kill it, not for an operator-prioritised slot and not for a
+  projected disk stop. It grants nothing new, frees idle items through the
+  `cleanup` flow, asks the operator for an exception, or waits. An owner's
+  own disk guard only alerts the chair and takes nothing down; only the
+  operator can order a running job down.
+- Handover is explicit: the outgoing chair sends every peer the new holder,
+  the queue and the running grants, and keeps allocating until the incoming
+  chair confirms. Two allocators never run at once.
+
+## Resource watch
+
+The chair keeps the system from running out instead of reacting once it has.
+`${CLAUDE_SKILL_DIR}/scripts/watch.py` does the measuring as hooks in every
+session, so no agent probes the disk by hand; it reads its thresholds, job
+patterns, cleanup commands and cache directories from
+`~/.config/agents-council/config.json` (keys in the script's docstring) and
+stays silent below the thresholds.
+
+- **Warn**: the chair and every session get the biggest consumers; the chair
+  plans a cleanup and grants no large slot.
+- **Stop**: new heavy jobs are blocked in every session (teardown commands
+  never), and the hook runs the configured low-risk cleanup by itself; it
+  skips every worktree where a gate or deploy process still runs.
+- **Critical**: additionally a desktop alarm to the operator. Running jobs
+  and their stacks still keep running; only the operator can make an
+  exception.
+- A measured fall that would reach the critical threshold within the
+  projection window raises the stage by one at once.
+- Caches together stay under their budget; the least recently used go first.
+
+`watch.py status` shows the last measurement. A `RESOURCE` line in a hook's
+context is addressed to the chair; any other session only adjusts its own
+plans to it.
+
+## Succession
+
+- A piece of work or a cluster ends with its result, a proposal, or an
+  abandoned attempt, reported to the peers who heard the claim. The holder
+  then runs `council.py release <office>`, and the next agent that starts the
+  work is elected afresh.
+- A representative or the chair that ends hands its office to the next-oldest
+  live representative (by claim time) and announces it.
+- A claim is stale when its holder's session is gone: in Claude Code its
+  session id is no longer in `~/.claude/sessions`; other runtimes run
+  `council.py beat` at least hourly and go stale after 60 minutes without
+  one. `claim` then exits 4. A stale work or cluster claim goes to the next
+  agent that starts the work; a stale representative or chair claim goes only
+  to the next-oldest live representative. The successor runs
+  `council.py takeover <office> --work "..."` and announces the succession;
+  everyone else leaves it alone.
+- After a restart or reboot, run `council.py list --mine` and claim again
+  every office you believe you hold: `/tmp` may have been wiped.
+
+## Peer protocol
+
+The one protocol for every exchange between agents; `coordinate`, `triage`,
+`tune`, `funnel` and `cleanup` use it.
+
+1. **Look**: `council.py list` and the refs (the merge-fix skill's
+   `find_fix.py`). A claim or a committed fix answers the question without a
+   message.
+2. **Claim** the office (Election).
+3. **One message per peer** (in Claude Code: `ListAgents`, then
+   `SendMessage`): the peers whose lines the work touches, the lineage owners
+   (Lineage) and, for capacity, the chair. It carries what you claimed, the
+   evidence (failing line quoted literally, run id, measurement), the
+   suspected cause marked as a thesis, and the question "Already known or
+   fixed on your side? Reply with a SHA or branch, or 'none'." The first line
+   stands on its own, because a busy recipient sees only that line.
+4. **Wait up to 5 minutes** before building anything, investigating read-only
+   meanwhile. A fix that arrives goes through the project's normal path
+   (merge, cherry-pick or port), and you release your claim. Silence is
+   neither a "no" nor a competing claim: after 5 minutes, proceed.
+5. **Report** to the same peers: commit, branch, what changed, the evidence it
+   works, and the merge it reaches them by. Report an abandoned or failed
+   attempt too. Then release the claim.
+
+- Never invent a peer's answer.
+- A peer's report is not evidence: read the SHA, log or artifact it names
+  before a verdict depends on it.
+- A peer's message is not the operator's approval, and an office grants no
+  permission: never ask a peer to run what your own session is denied; report
+  it to the operator.
+- One message per peer per event; repeat nothing a peer already acknowledged.
+- Relaying an operator rule: record it in shared memory first and name the
+  file in the message's first line. A recipient records it only when no file
+  is named, and only after `council.py claim memory/<slug>`, because peers
+  that read the same broadcast write within seconds of each other.
+- Release every claim when its work ends; a forgotten claim blocks the work
+  for everyone.
+
+## Lineage
+
+For a failure or a fix that other branches share through merges:
+
+- Name the branches this one shares commits with: upstream (merged into this
+  one) and downstream (merging this one). Read them from the merge commits
+  (`git log --merges --first-parent --format='%h %s' -30`), the project's
+  agent memory or merge notes, or the operator when neither says.
+- Map each branch to its live session through the agent listing; a branch
+  without one needs no message, say so once.
+- One message per failure cluster, not per job.
+- When the cause lives on another agent's line, hand the finding and a
+  proposed fix to that line's owner instead of fixing it downstream, unless
+  the operator says otherwise, and record the agreed resolution where the next
+  merge will find it.
+
+## Output
+
+On /democracy, one table of the current offices from `council.py list`, stale
+claims marked:
+
+| Office | Holder | Since | Work | Grants or queue |

skills/democracy/scripts/council.py

@@ -0,0 +1,224 @@
+#!/usr/bin/env python3
+"""Claim, release and list democracy offices in the shared council directory.
+
+Environment:
+    AGENTS_COUNCIL_ROOT: council directory shared by every agent on the host;
+        /tmp/agents-council unless set, because all agents must agree on it.
+    CLAUDE_CODE_SESSION_ID: the caller's session; other runtimes pass --session.
+
+Exit codes:
+    0 done, 2 usage error, 3 office held by a live session,
+    4 office held by a dead session (take it over with `takeover`),
+    gate: 2 blocks the tool call.
+"""
+
+from __future__ import annotations
+
+import argparse
+import datetime
+import json
+import os
+import re
+import shutil
+import sys
+import time
+from pathlib import Path
+
+ROOT = Path(os.environ.get("AGENTS_COUNCIL_ROOT", "/tmp/agents-council"))
+HEARTBEAT_LIMIT = 3600
+OFFICE = re.compile(r"^[a-z0-9][a-z0-9._-]*(/[a-z0-9][a-z0-9._-]*)*$")
+CLAIM = "claim.json"
+
+
+def live_sessions() -> dict[str, str | None]:
+    found: dict[str, str | None] = {}
+    for path in (Path.home() / ".claude" / "sessions").glob("*.json"):
+        try:
+            data = json.loads(path.read_text(encoding="utf-8"))
+        except (OSError, ValueError):
+            continue
+        if data.get("sessionId"):
+            found[data["sessionId"]] = data.get("name")
+    return found
+
+
+def caller(session: str | None) -> tuple[str, str]:
+    if session:
+        return session, "other"
+    env = os.environ.get("CLAUDE_CODE_SESSION_ID")
+    if env:
+        return env, "claude-code"
+    print("council: no session id; pass --session", file=sys.stderr)
+    sys.exit(2)
+
+
+def office_dir(office: str) -> Path:
+    if not OFFICE.match(office):
+        print(f"council: invalid office {office!r}", file=sys.stderr)
+        sys.exit(2)
+    return ROOT / office
+
+
+def read_claim(path: Path) -> dict | None:
+    try:
+        return json.loads((path / CLAIM).read_text(encoding="utf-8"))
+    except (FileNotFoundError, ValueError):
+        return None
+
+
+def is_stale(claim: dict | None, live: dict[str, str | None]) -> bool:
+    if claim is None:
+        return False
+    if claim["runtime"] == "claude-code":
+        return claim["session"] not in live
+    return time.time() - claim["beat"] > HEARTBEAT_LIMIT
+
+
+def claims() -> list[tuple[str, dict]]:
+    found = []
+    for path in sorted(ROOT.glob(f"**/{CLAIM}")):
+        claim = read_claim(path.parent)
+        if claim is not None:
+            found.append((path.parent.relative_to(ROOT).as_posix(), claim))
+    return found
+
+
+def write_claim(path: Path, office: str, sid: str, runtime: str, work: str) -> None:
+    claim = {
+        "office": office,
+        "session": sid,
+        "runtime": runtime,
+        "name": live_sessions().get(sid),
+        "since": datetime.datetime.now(datetime.UTC).isoformat(timespec="seconds"),
+        "beat": time.time(),
+        "work": work,
+    }
+    (path / CLAIM).write_text(json.dumps(claim), encoding="utf-8")
+
+
+def cmd_claim(args: argparse.Namespace) -> int:
+    sid, runtime = caller(args.session)
+    path = office_dir(args.office)
+    path.parent.mkdir(parents=True, exist_ok=True)
+    try:
+        path.mkdir()
+    except FileExistsError:
+        claim = read_claim(path)
+        if claim is not None and claim["session"] == sid:
+            write_claim(path, args.office, sid, runtime, args.work)
+            print(f"held {args.office}")
+            return 0
+        print(json.dumps(claim) if claim else f"{args.office}: claim in progress")
+        return 4 if is_stale(claim, live_sessions()) else 3
+    write_claim(path, args.office, sid, runtime, args.work)
+    print(f"elected {args.office}")
+    return 0
+
+
+def cmd_takeover(args: argparse.Namespace) -> int:
+    path = office_dir(args.office)
+    claim = read_claim(path)
+    if path.exists() and not is_stale(claim, live_sessions()):
+        print(json.dumps(claim) if claim else f"{args.office}: claim in progress")
+        return 3
+    # Two successors racing between this check and the rename can both win;
+    # democracy names exactly one successor per office to keep that window closed.
+    if path.exists():
+        tomb = path.with_name(f"{path.name}.stale-{os.getpid()}-{time.time_ns()}")
+        try:
+            path.rename(tomb)
+        except FileNotFoundError:
+            pass
+        else:
+            shutil.rmtree(tomb)
+    return cmd_claim(args)
+
+
+def cmd_release(args: argparse.Namespace) -> int:
+    sid, _ = caller(args.session)
+    path = office_dir(args.office)
+    claim = read_claim(path)
+    if claim is None:
+        print(f"{args.office}: not claimed")
+        return 0
+    if claim["session"] != sid and not is_stale(claim, live_sessions()):
+        print(json.dumps(claim))
+        return 3
+    shutil.rmtree(path)
+    print(f"released {args.office}")
+    return 0
+
+
+def cmd_beat(args: argparse.Namespace) -> int:
+    sid, _ = caller(args.session)
+    for office, claim in claims():
+        if claim["session"] == sid:
+            claim["beat"] = time.time()
+            (ROOT / office / CLAIM).write_text(json.dumps(claim), encoding="utf-8")
+    return 0
+
+
+def cmd_list(args: argparse.Namespace) -> int:
+    live = live_sessions()
+    sid = None
+    if args.mine:
+        sid, _ = caller(args.session)
+    for office, claim in claims():
+        if sid is not None and claim["session"] != sid:
+            continue
+        state = "stale" if is_stale(claim, live) else "live"
+        holder = claim["name"] or claim["session"]
+        print(f"{office}\t{holder}\t{claim['since']}\t{state}\t{claim['work']}")
+    return 0
+
+
+def in_git_worktree(target: Path) -> bool:
+    return any((path / ".git").exists() for path in (target, *target.parents))
+
+
+def cmd_gate(_: argparse.Namespace) -> int:
+    payload = json.load(sys.stdin)
+    tool_input = payload.get("tool_input") or {}
+    target = tool_input.get("file_path") or tool_input.get("notebook_path")
+    if not target or not in_git_worktree(Path(target).resolve()):
+        return 0
+    if any(claim["session"] == payload.get("session_id") for _, claim in claims()):
+        return 0
+    script = Path(__file__).resolve()
+    print(
+        "democracy: this session holds no claim, so it may not edit files in a git "
+        f"worktree. Claim the work first: python3 {script} claim work/<slug> "
+        "--work '<one line>'. Exit 3 or 4 means another agent holds it; read the "
+        "democracy skill.",
+        file=sys.stderr,
+    )
+    return 2
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(prog="council")
+    sub = parser.add_subparsers(dest="cmd", required=True)
+    for name, func in (("claim", cmd_claim), ("takeover", cmd_takeover)):
+        cmd = sub.add_parser(name)
+        cmd.add_argument("office")
+        cmd.add_argument("--work", required=True)
+        cmd.add_argument("--session")
+        cmd.set_defaults(func=func)
+    release = sub.add_parser("release")
+    release.add_argument("office")
+    release.add_argument("--session")
+    release.set_defaults(func=cmd_release)
+    beat = sub.add_parser("beat")
+    beat.add_argument("--session")
+    beat.set_defaults(func=cmd_beat)
+    listing = sub.add_parser("list")
+    listing.add_argument("--mine", action="store_true")
+    listing.add_argument("--session")
+    listing.set_defaults(func=cmd_list)
+    sub.add_parser("gate").set_defaults(func=cmd_gate)
+    args = parser.parse_args()
+    return args.func(args)
+
+
+if __name__ == "__main__":
+    sys.exit(main())

skills/democracy/scripts/watch.py

@@ -0,0 +1,422 @@
+#!/usr/bin/env python3
+"""Watch disk, Docker and caches for the democracy resource chair.
+
+Usage:
+    watch.py watch     hook (UserPromptSubmit, PostToolUse): measure at most once
+                       per interval machine-wide, act on the stage, show alerts
+    watch.py block     hook (PreToolUse on Bash): exit 2 for a heavy job while the
+                       stage is stop or critical
+    watch.py admit (--need-gb N | --kind KIND)
+                       exit 0 when the grant leaves at least the stop threshold
+                       free, 3 otherwise
+    watch.py cleanup (--caches | --full)
+                       trim caches to their budget; --full also runs the
+                       configured low-risk cleanup commands
+    watch.py status    print the last measurement
+
+Environment:
+    AGENTS_COUNCIL_ROOT: shared state directory; /tmp/agents-council unless set,
+        because every agent on the host must agree on it.
+    AGENTS_COUNCIL_CONFIG: config file; ~/.config/agents-council/config.json
+        unless set. Without a config file every command exits 0 and does nothing.
+
+Config keys, all required: disk, thresholds_gb {warn, stop, critical},
+projection_minutes, interval_seconds, cache_interval_seconds, heavy_commands,
+never_block (regexes), cleanup (shell commands), worktree_cleanup (shell
+commands with {worktree}), worktrees_command (shell command printing the
+running stacks' worktree paths, one per line), worktree_marker (path relative
+to a worktree that must exist), busy_processes (process names; a worktree
+where one of them runs is skipped), cache_dirs, cache_budget_percent,
+slot_need_gb {kind: GB}, notify (argv the alert text is appended to),
+load_limits {cpu_percent, mem_percent, sample_seconds, kinds}: admit for a
+kind listed in kinds also needs CPU busy and RAM used below the limits.
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+import os
+import re
+import shlex
+import subprocess
+import sys
+import time
+from pathlib import Path
+
+ROOT = Path(os.environ.get("AGENTS_COUNCIL_ROOT", "/tmp/agents-council"))
+CONFIG = Path(
+    os.environ.get(
+        "AGENTS_COUNCIL_CONFIG",
+        str(Path.home() / ".config" / "agents-council" / "config.json"),
+    )
+)
+STAGES = ("ok", "warn", "stop", "critical")
+STATE = ROOT / "watch.json"
+ALERTS = ROOT / "alerts.jsonl"
+ALERT_TTL = 3600
+LOCK_TTL = 1800
+GB = 1e9
+
+
+def load_config() -> dict | None:
+    if not CONFIG.is_file():
+        return None
+    return json.loads(CONFIG.read_text(encoding="utf-8"))
+
+
+def disk(cfg: dict) -> tuple[float, float]:
+    st = os.statvfs(cfg["disk"])
+    return st.f_bavail * st.f_frsize / GB, st.f_blocks * st.f_frsize / GB
+
+
+def read_json(path: Path) -> dict:
+    try:
+        return json.loads(path.read_text(encoding="utf-8"))
+    except (OSError, ValueError):
+        return {}
+
+
+def write_json(path: Path, data: dict) -> None:
+    # A full disk refuses the write; the stage must still act, so it is dropped.
+    try:
+        path.parent.mkdir(parents=True, exist_ok=True)
+        tmp = path.with_name(f"{path.name}.{os.getpid()}")
+        tmp.write_text(json.dumps(data), encoding="utf-8")
+        tmp.replace(path)
+    except OSError:
+        pass
+
+
+def stage_for(free: float, samples: list[list[float]], cfg: dict, now: float) -> str:
+    limits = cfg["thresholds_gb"]
+    level = 0
+    for index, name in ((1, "warn"), (2, "stop"), (3, "critical")):
+        if free < limits[name]:
+            level = index
+    window = cfg["projection_minutes"] * 60
+    recent = [s for s in samples if now - s[0] <= window and now > s[0]]
+    if recent and level < 3:
+        then, before = recent[0]
+        rate = (before - free) / (now - then)
+        if rate > 0 and (free - limits["critical"]) / rate < window:
+            level += 1
+    return STAGES[level]
+
+
+def alert(stage: str, text: str) -> None:
+    try:
+        ROOT.mkdir(parents=True, exist_ok=True)
+        with ALERTS.open("a", encoding="utf-8") as handle:
+            handle.write(json.dumps({"id": time.time_ns(), "stage": stage, "text": text}) + "\n")
+    except OSError:
+        pass
+
+
+def unseen_alerts(session: str) -> list[str]:
+    seen_path = ROOT / "seen" / session
+    try:
+        seen = int(seen_path.read_text(encoding="utf-8"))
+    except (OSError, ValueError):
+        seen = 0
+    try:
+        lines = ALERTS.read_text(encoding="utf-8").splitlines()
+    except OSError:
+        return []
+    cutoff = time.time_ns() - ALERT_TTL * 10**9
+    fresh = [json.loads(line) for line in lines if line]
+    fresh = [a for a in fresh if a["id"] > max(seen, cutoff)]
+    if fresh:
+        write_text(seen_path, str(fresh[-1]["id"]))
+    return [a["text"] for a in fresh]
+
+
+def write_text(path: Path, text: str) -> None:
+    try:
+        path.parent.mkdir(parents=True, exist_ok=True)
+        path.write_text(text, encoding="utf-8")
+    except OSError:
+        pass
+
+
+def consumers() -> str:
+    try:
+        out = subprocess.run(
+            ["docker", "system", "df", "--format", "{{.Type}}: {{.Size}} ({{.Reclaimable}} reclaimable)"],
+            capture_output=True, text=True, timeout=30, check=False,
+        ).stdout.strip()
+    except (OSError, subprocess.TimeoutExpired):
+        return "docker system df unavailable"
+    return "; ".join(out.splitlines()) or "docker system df printed nothing"
+
+
+def notify(cfg: dict, text: str) -> None:
+    try:
+        subprocess.run([*cfg["notify"], text], capture_output=True, timeout=10, check=False)
+    except (OSError, subprocess.TimeoutExpired):
+        alert("critical", f"RESOURCE: desktop notification failed: {cfg['notify'][0]}")
+
+
+def spawn_cleanup(mode: str) -> None:
+    subprocess.Popen(
+        [sys.executable, str(Path(__file__).resolve()), "cleanup", mode],
+        stdin=subprocess.DEVNULL, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL,
+        start_new_session=True,
+    )
+
+
+def act(cfg: dict, stage: str, previous: str, free: float) -> None:
+    limits = cfg["thresholds_gb"]
+    head = f"/ has {free:.1f} GB free (warn < {limits['warn']}, stop < {limits['stop']}, critical < {limits['critical']} GB)"
+    if STAGES.index(stage) < STAGES.index(previous):
+        alert(stage, f"RESOURCE {stage.upper()}: recovered, {head}.")
+        return
+    if stage == "warn":
+        alert(stage, f"RESOURCE WARN: {head}. Biggest consumers: {consumers()}. Chair: plan a cleanup; peers: request no large slot.")
+    elif stage in ("stop", "critical"):
+        alert(stage, f"RESOURCE {stage.upper()}: {head}. New heavy jobs are blocked; low-risk cleanup is running. {consumers()}")
+        spawn_cleanup("--full")
+        if stage == "critical":
+            notify(cfg, f"Agents council: {head}. Heavy jobs blocked; a running stack needs the operator's OK to go.")
+
+
+def cmd_watch(cfg: dict) -> int:
+    payload = json.load(sys.stdin)
+    now = time.time()
+    state = read_json(STATE)
+    if now - state.get("checked", 0) >= cfg["interval_seconds"]:
+        free, _ = disk(cfg)
+        samples = [s for s in state.get("samples", []) if now - s[0] <= cfg["projection_minutes"] * 60]
+        stage = stage_for(free, samples, cfg, now)
+        previous = state.get("stage", "ok")
+        samples.append([now, free])
+        state.update(checked=now, free=free, stage=stage, samples=samples)
+        due = now - state.get("caches_checked", 0) >= cfg["cache_interval_seconds"]
+        if due:
+            state["caches_checked"] = now
+        write_json(STATE, state)
+        if stage != previous:
+            act(cfg, stage, previous, free)
+        elif due:
+            spawn_cleanup("--caches")
+    texts = unseen_alerts(payload["session_id"])
+    if texts:
+        print(json.dumps({"hookSpecificOutput": {
+            "hookEventName": payload["hook_event_name"],
+            "additionalContext": "\n".join(texts),
+        }}))
+    return 0
+
+
+HEREDOC = re.compile(r"<<-?\s*(['\"]?)(\w+)\1[^\n]*\n.*?\n\s*\2(?=\s|\)|$)", re.DOTALL)
+QUOTED = re.compile(r"'[^']*'|\"(?:\\.|[^\"\\])*\"")
+
+
+def executable_text(command: str) -> str:
+    return QUOTED.sub("''", HEREDOC.sub("", command))
+
+
+def cmd_block(cfg: dict) -> int:
+    payload = json.load(sys.stdin)
+    command = executable_text((payload.get("tool_input") or {}).get("command", ""))
+    stage = read_json(STATE).get("stage", "ok")
+    if stage not in ("stop", "critical"):
+        return 0
+    if any(re.search(p, command) for p in cfg["never_block"]):
+        return 0
+    if any(re.search(p, command) for p in cfg["heavy_commands"]):
+        print(
+            f"democracy: resource stage is {stage}; new heavy jobs are blocked until "
+            "the disk recovers. Teardown commands still run. Ask the resource chair.",
+            file=sys.stderr,
+        )
+        return 2
+    return 0
+
+
+def cpu_times() -> tuple[int, int]:
+    fields = [int(v) for v in Path("/proc/stat").read_text(encoding="utf-8").split("\n", 1)[0].split()[1:]]
+    return sum(fields), fields[3] + fields[4]
+
+
+def cpu_busy_percent(before: tuple[int, int], after: tuple[int, int]) -> float:
+    total = after[0] - before[0]
+    idle = after[1] - before[1]
+    return 100.0 * (total - idle) / total
+
+
+def mem_used_percent(meminfo: str) -> float:
+    values = {}
+    for line in meminfo.splitlines():
+        key, _, rest = line.partition(":")
+        if rest:
+            values[key] = int(rest.split()[0])
+    return 100.0 * (1 - values["MemAvailable"] / values["MemTotal"])
+
+
+def load(cfg: dict) -> tuple[float, float]:
+    before = cpu_times()
+    time.sleep(cfg["load_limits"]["sample_seconds"])
+    cpu = cpu_busy_percent(before, cpu_times())
+    return cpu, mem_used_percent(Path("/proc/meminfo").read_text(encoding="utf-8"))
+
+
+def cmd_admit(cfg: dict, args: argparse.Namespace) -> int:
+    need = args.need_gb if args.need_gb is not None else cfg["slot_need_gb"][args.kind]
+    free, _ = disk(cfg)
+    left = free - need
+    floor = cfg["thresholds_gb"]["stop"]
+    passed = [left >= floor]
+    report = [f"free {free:.1f} GB, need {need} GB, leaves {left:.1f} GB (floor {floor} GB)"]
+    limits = cfg["load_limits"]
+    if args.kind in limits["kinds"]:
+        cpu, mem = load(cfg)
+        passed += [cpu < limits["cpu_percent"], mem < limits["mem_percent"]]
+        report.append(
+            f"cpu {cpu:.0f} % (limit {limits['cpu_percent']}), ram {mem:.0f} % (limit {limits['mem_percent']})"
+        )
+    verdict = "grant" if all(passed) else "deny"
+    print(f"{verdict}: {'; '.join(report)}")
+    return 0 if verdict == "grant" else 3
+
+
+def cache_files(dirs: list[str]) -> list[tuple[float, int, str]]:
+    files = []
+    for root in dirs:
+        for base, _, names in os.walk(os.path.expanduser(root)):
+            for name in names:
+                path = os.path.join(base, name)
+                try:
+                    st = os.lstat(path)
+                except OSError:
+                    continue
+                files.append((st.st_atime, st.st_size, path))
+    return files
+
+
+def trim_caches(cfg: dict) -> float:
+    _, total = disk(cfg)
+    budget = total * GB * cfg["cache_budget_percent"] / 100
+    files = sorted(cache_files(cfg["cache_dirs"]))
+    used = sum(size for _, size, _ in files)
+    freed = 0
+    for _, size, path in files:
+        if used - freed <= budget:
+            break
+        try:
+            os.remove(path)
+            freed += size
+        except OSError:
+            continue
+    return freed / GB
+
+
+def running_worktrees(cfg: dict) -> list[str]:
+    try:
+        out = subprocess.run(
+            cfg["worktrees_command"], shell=True, capture_output=True, text=True, timeout=60, check=False
+        ).stdout
+    except subprocess.TimeoutExpired:
+        return []
+    trees = sorted({line.strip() for line in out.splitlines() if line.strip()})
+    return [t for t in trees if os.path.exists(os.path.join(t, cfg["worktree_marker"]))]
+
+
+def busy(tree: str, names: list[str]) -> bool:
+    root = os.path.realpath(tree)
+    for pid in filter(str.isdigit, os.listdir("/proc")):
+        try:
+            if Path(f"/proc/{pid}/comm").read_text(encoding="utf-8").strip() not in names:
+                continue
+            cwd = os.readlink(f"/proc/{pid}/cwd")
+        except OSError:
+            continue
+        if cwd == root or cwd.startswith(root + os.sep):
+            return True
+    return False
+
+
+def run_cleanup(cfg: dict) -> list[str]:
+    commands = list(cfg["cleanup"])
+    for tree in running_worktrees(cfg):
+        if busy(tree, cfg["busy_processes"]):
+            continue
+        commands += [t.format(worktree=shlex.quote(tree)) for t in cfg["worktree_cleanup"]]
+    results = []
+    for command in commands:
+        try:
+            code = subprocess.run(command, shell=True, capture_output=True, timeout=900, check=False).returncode
+        except subprocess.TimeoutExpired:
+            code = "timeout"
+        results.append(f"{'ok' if code == 0 else f'failed ({code})'}: {command}")
+    return results
+
+
+def cmd_cleanup(cfg: dict, args: argparse.Namespace) -> int:
+    lock = ROOT / "cleanup.lock"
+    ROOT.mkdir(parents=True, exist_ok=True)
+    try:
+        if time.time() - lock.stat().st_mtime > LOCK_TTL:
+            lock.rmdir()
+    except FileNotFoundError:
+        pass
+    try:
+        lock.mkdir()
+    except FileExistsError:
+        return 0
+    try:
+        before, _ = disk(cfg)
+        results = run_cleanup(cfg) if args.full else []
+        cache_gb = trim_caches(cfg)
+        after, _ = disk(cfg)
+        failed = [r for r in results if not r.startswith("ok")]
+        if args.full or cache_gb:
+            alert(
+                "cleanup",
+                f"RESOURCE CLEANUP: freed {after - before:.1f} GB ({cache_gb:.1f} GB caches), "
+                f"/ now {after:.1f} GB free; {len(results) - len(failed)} commands ok"
+                + (f", failed: {' | '.join(failed)}" if failed else "."),
+            )
+    finally:
+        lock.rmdir()
+    return 0
+
+
+def cmd_status(cfg: dict) -> int:
+    state = read_json(STATE)
+    free, total = disk(cfg)
+    print(f"stage={state.get('stage', 'unmeasured')} free={free:.1f}GB total={total:.1f}GB samples={len(state.get('samples', []))}")
+    return 0
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(prog="watch")
+    sub = parser.add_subparsers(dest="cmd", required=True)
+    sub.add_parser("watch")
+    sub.add_parser("block")
+    admit = sub.add_parser("admit")
+    need = admit.add_mutually_exclusive_group(required=True)
+    need.add_argument("--need-gb", type=float)
+    need.add_argument("--kind")
+    cleanup = sub.add_parser("cleanup")
+    mode = cleanup.add_mutually_exclusive_group(required=True)
+    mode.add_argument("--caches", action="store_true")
+    mode.add_argument("--full", action="store_true")
+    sub.add_parser("status")
+    args = parser.parse_args()
+    cfg = load_config()
+    if cfg is None:
+        return 0
+    if args.cmd == "watch":
+        return cmd_watch(cfg)
+    if args.cmd == "block":
+        return cmd_block(cfg)
+    if args.cmd == "admit":
+        return cmd_admit(cfg, args)
+    if args.cmd == "cleanup":
+        return cmd_cleanup(cfg, args)
+    return cmd_status(cfg)
+
+
+if __name__ == "__main__":
+    sys.exit(main())

skills/dialectic/SKILL.md

@@ -1,11 +1,10 @@
 ---
 name: dialectic
 description: >
-  Reach a defensible conclusion through a dialectical process — thesis,
-  adversarial antithesis, synthesis — iterated until one thesis survives every
-  attack at ~99% confidence. Trigger for any consequential root-cause, design,
-  or decision where being wrong is expensive and the answer is not yet certain.
-  Deep-inspects every accessible source. Portable across projects.
+  Reach a defensible conclusion by thesis, independent skeptic antithesis and
+  synthesis, iterated to ~99% confidence. Trigger for any consequential root
+  cause, design or decision where being wrong is expensive and the answer is
+  uncertain.
 ---
 
 Reach the truth by dialectic, not by first guess. Do not stop at a plausible
@@ -19,6 +18,10 @@ needs. A dialectic run on the wrong question wastes the whole loop. Return to
 `active-listening` mid-loop whenever an objection turns on a fact only the
 operator holds.
 
+When another skill or an autonomous run (robot, observe, a loop) invoked this
+skill, derive the requirements from the task and the evidence instead of
+asking; ask only when an operator-only fact blocks the conclusion.
+
 ## The loop
 
 1. **Thesis.** Form the strongest initial claim you can, grounded in evidence,
@@ -27,7 +30,8 @@ operator holds.
    make or CLI helpers the project exposes); CI logs and artifacts; tests; docs.
    Cite `file:line` and command output — never a bare assertion.
 2. **Antithesis.** Spawn MULTIPLE independent skeptics (parallel subagents or a
-   workflow) whose only job is to REFUTE the thesis. Each re-inspects the
+   workflow, on the default model as the `subagent-model` skill requires)
+   whose only job is to REFUTE the thesis. Each re-inspects the
    sources itself and defaults to "refuted" on any concrete hole. Give diverse
    skeptics diverse lenses: correctness, an alternate mechanism, does-it-
    reproduce, does-the-fix-break-something-else.

skills/dream/SKILL.md

@@ -0,0 +1,135 @@
+---
+name: dream
+description: >
+  Consolidate the last 24 hours of work in this repository: what held, what
+  broke, which hypotheses follow, into memory and improvement proposals.
+  Trigger on /dream or when the operator asks to reflect on or learn from
+  recent work.
+---
+
+Sleep on the work: replay what happened in this repository, separate what held
+from what broke, and keep only the conclusions that survive an attack. A dream
+that flatters the dreamer is worthless — an unverified success counts as
+unknown, not as a win.
+
+## Objective
+
+The dream exists to raise the confidence of every future run in this repository
+until the mistakes it found cannot happen again. Judge every finding, memory
+entry, and proposal by one question: does it make the next run measurably less
+likely to repeat this failure? What changes nothing about future behaviour is
+not worth recording.
+
+A class of error counts as closed only when something structural prevents it —
+a test, a lint rule, a CI check, a hook, a written rule in the agent
+instructions, or a skill. "Be more careful next time" closes nothing. Report the
+confidence the next run can now hold on each closed class, calibrated as the
+`confidence` skill requires, and name what is still open.
+
+## Scope
+
+Everything is read from the repository the skill runs in (`git rev-parse
+--show-toplevel`); never mix in another project's history or memory. The default
+window is the last 24 hours — the operator may widen it (`/dream 7d`). State the
+repository and the window in one line before you start.
+
+Run only when the operator asks. The 12-hour reminder hook
+(`hooks/reminder.sh`, stamped per repository in its git dir) is a hint for the
+operator, not a trigger: print it and continue with their actual request.
+
+## Step 1: recall
+
+Gather the window's actual record, not your recollection of it:
+
+- **History**: `git log --since` across all branches plus `--reflog`, with
+  `--stat`; the reflog carries the resets, rebases, and amends the log hides.
+- **Working state**: `git status`, the staged and unstaged diff, stashes.
+- **CI**: the runs created in the window, their conclusions, and the failing
+  logs of the red ones — the failing log line, not the job title.
+- **Reviews**: pull requests and issues touched in the window, and the review
+  comments on them.
+- **Memory**: this project's memory directory and its `MEMORY.md` index — the
+  findings already recorded, so the dream extends them instead of repeating them.
+- **Instructions**: `CLAUDE.md`, `AGENTS.md`, and the project's own skills, to
+  see which rule a mistake actually violated.
+- **Sessions**: the readable session transcripts touched in the window, for the
+  operator corrections that never reached a commit.
+
+## Step 2: score
+
+Classify every action in the window, each with its evidence (`sha`, `file:line`,
+run id):
+
+- **Held** — shipped and still proven: green CI, a passing test that covers it,
+  no revert, no follow-up fix.
+- **Broke** — reverted, amended, hot-fixed by a later commit, red CI, or
+  corrected by the operator. A failure that ended green is still a failure; count
+  the detour, not only the destination.
+- **Unknown** — no verification exists either way. Unknown is a finding in its
+  own right, never a quiet pass.
+
+## Step 3: hypothesize
+
+Turn the scored record into falsifiable hypotheses, each written as *cause →
+predicted consequence → what would disprove it*. Take a pattern (two or more
+occurrences) or a single expensive failure; drop the one-off noise. A hypothesis
+that nothing could disprove is not a hypothesis — cut it.
+
+## Step 4: dialectic
+
+Put every surviving hypothesis through the `dialectic` skill: thesis,
+independent skeptics, synthesis, iterated to ~99%. What survives becomes a
+finding. What gets refuted is recorded as discarded **with the refutation**, so
+the next dream does not re-derive it.
+
+## Step 5: write memory
+
+Persist the findings in this project's memory directory: one file per fact, one
+pointer line in `MEMORY.md`. Update the file that already covers a fact instead
+of adding a duplicate, and delete the memories this run disproved. Absolute
+dates, never "yesterday". Nothing that the repository already records — code
+structure, git history, `CLAUDE.md` — belongs in memory.
+
+## Step 6: offer the improvements
+
+Two kinds come out of the findings:
+
+- **Code** — the change to this repository's source, tests, config, or CI that
+  the finding calls for.
+- **Agent instructions** — the missing or wrong rule in `CLAUDE.md`,
+  `AGENTS.md`, the project's own skills, or the contributor docs. Every mistake
+  the agent repeated in the window is a candidate: quote the line that failed to
+  prevent it, or name the rule that is absent, and propose the exact wording.
+
+Ask for each one with `AskUserQuestion` and `multiSelect: false` so it renders
+as radio buttons: the improvement, the evidence behind it, and the options
+`Apply now`, `Record as a task`, `Skip`. Ranked by evidence, one question per
+improvement. No repository file changes before an answer comes back.
+
+## Step 7: autotune, then autoskill
+
+With the dialectic done and memory written, run `autotune` — hand it this run's
+findings as its evidence so it does not re-collect them — and then `autoskill`
+for the operator corrections the window revealed. Both keep their own
+confirmation steps; the dream never writes a skill on their behalf.
+
+Close the run by refreshing this repository's reminder stamp, so the next hint
+is twelve hours out: `date +%s > "$(git rev-parse --path-format=absolute --git-common-dir)/.dream-stamp"`.
+
+## Rules
+
+- Evidence or unknown: a claim about what held needs a green signal, and its
+  absence is reported as unknown rather than assumed.
+- Honest scoring: reverts, amends, and follow-up fixes are failures of the first
+  attempt even when the final state is green.
+- Read-only until step 6: the dream inspects, and writes memory; repository code
+  changes only on an explicit radio answer.
+- An empty window is a valid result — report "nothing in the last 24 hours in
+  this repository" and stop. Never invent activity to have something to dream
+  about.
+- Prefer the structural fix over the remembered one: a test, check, hook, or
+  written rule that makes the error impossible beats a memory entry that only
+  reminds you of it.
+- Report the whole ledger: held, broke, unknown, the surviving findings, the
+  refuted hypotheses with why they fell, and the confidence each closed error
+  class now carries into the next run.

skills/dream/hooks/reminder.sh

@@ -0,0 +1,40 @@
+#!/usr/bin/env bash
+# UserPromptSubmit hook: emit the dream hint at most once per interval and per
+# repository. The stamp lives in the repository's git dir, so every repository
+# keeps its own cadence; outside a git repository the hook stays silent.
+# Stdout lands in the agent's context, which is why the payload tells the agent
+# to show the hint and keep going instead of running dream by itself.
+set -euo pipefail
+
+interval="${DREAM_INTERVAL_SECONDS:-43200}"
+if [[ -n "${DREAM_STAMP:-}" ]]; then
+	stamp="${DREAM_STAMP}"
+else
+	git_dir="$(git rev-parse --path-format=absolute --git-common-dir 2>/dev/null)" || exit 0
+	stamp="${git_dir}/.dream-stamp"
+fi
+
+now="$(date +%s)"
+last=0
+if [[ -f "${stamp}" ]]; then
+	read -r last <"${stamp}" || true
+	[[ "${last}" =~ ^[0-9]+$ ]] || last=0
+fi
+
+if ((now - last < interval)); then
+	exit 0
+fi
+
+mkdir -p "$(dirname "${stamp}")"
+printf '%s\n' "${now}" >"${stamp}"
+
+cat <<'HINT'
+DREAM HINT: over twelve hours since the last hint for this repository. Show the
+operator this notice verbatim as a short block, then continue with their
+request. Do NOT run dream, do not start replaying the history, do not ask
+questions about it.
+
+    💤 /dream - consolidate the last 24h in this repository: what held, what
+       broke, which hypotheses follow, into memory and improvement proposals.
+       Runs only when you trigger it.
+HINT

skills/essence/SKILL.md

@@ -0,0 +1,116 @@
+---
+name: essence
+description: >
+  Compact skills and memory to their essence after a health pass that finds
+  dead weight. Trigger on /essence or when skills or MEMORY.md grow too long,
+  duplicate, or eat too much context.
+---
+
+Shorter, not thinner. Every fact that still earns its place survives; what goes
+is repetition, narration, and entries nothing loads any more.
+
+## What actually costs context
+
+Compact by how often a thing is loaded, not by how large it is:
+
+1. **`MEMORY.md`** and every skill's **`description`** frontmatter load into
+   *every* session. A wasted line here is paid on every single turn. Highest
+   leverage by a wide margin.
+2. **Skill bodies** load when the skill fires. Worth tightening, paid only on use.
+3. **Memory files** load on recall. Lowest leverage — and the place where
+   cutting evidence does the most damage.
+
+A 200-line skill body that fires twice a month costs less than four bloated
+`MEMORY.md` pointers. Rank the work accordingly and say so in the report.
+
+## Step 1: ask for the scope
+
+Never assume the target. Ask once with `AskUserQuestion` and
+`multiSelect: true`, so the operator can tick several:
+
+- **Skills repository** — the portable `skills/*/SKILL.md` set.
+- **This project** — its `.claude/skills` and `.agents/skills`, plus the
+  project's memory directory and `MEMORY.md`.
+- **Home** — `~/.claude` and `~/.agents` (skills, rules, commands, agents).
+
+Take nothing outside what was ticked.
+
+## Step 2: doctor
+
+Before compacting anything, find what is already broken or dead. Report each
+finding with its path:
+
+- A `MEMORY.md` pointer whose file is gone, and a memory file no pointer names.
+- A dead `[[wikilink]]` — no memory of that name exists.
+- A memory asserting a `file:line`, function, or flag that no longer exists.
+  Verify against the current tree; a stale citation is worse than no memory,
+  because it reads as checked.
+- The same rule stated in two or more skills. One is authoritative, the rest
+  are drift.
+- A first-party skill shadowing a locked/vendored one.
+- Frontmatter missing `name` or `description`, or a `description` that says
+  what the skill does but never when it fires — such a skill costs context in
+  every session and never triggers.
+
+Dead entries are deleted, not compacted. Fix the broken ones or report them;
+never compact around a stale citation, or the error survives in denser form.
+
+## Step 3: compact
+
+Cut:
+
+- Anything the repository already records — code structure, git history, what
+  `CLAUDE.md`/`AGENTS.md` already say.
+- A rule the agent follows anyway without being told.
+- The second and third statement of one rule; keep the authoritative one and
+  point at it.
+- Narration, hedging, and worked examples beyond the one that carries the point.
+
+Keep, always:
+
+- The **why** and the evidence behind a memory — the date, the incident, the
+  quoted correction. A rule stripped of its evidence degrades into an
+  exhortation and stops changing behaviour.
+- Any fact with no other home. If it exists nowhere else, it is not redundancy.
+- Trigger wording in a `description`. Tighten it, never drop the "when".
+
+Dates stay absolute. Never introduce "recently" while shortening.
+
+## Step 4: show the diff, then write
+
+Writing happens in place — an essence that lives beside the original saves
+nothing, because the original is still what loads.
+
+Preconditions, per target:
+
+- A git repository must have a clean status for the paths being rewritten, so
+  every edit is revertable with git alone. Not clean: report and stop.
+- `~/.claude` and `~/.agents` are usually not under git. Copy each file to
+  `<file>.pre-essence` first.
+
+Then present, per file: the diff, and the lines and characters saved. Ask for
+one confirmation covering the batch. Write only after it.
+
+## Step 5: verify
+
+- Re-run the target's own validation if it has one (in a skills repository,
+  its test suite: frontmatter, lock, shadowing).
+- Re-read each rewritten file and confirm every kept fact is still stated, not
+  merely implied by something shorter.
+- Report the before/after loaded-context figure for the always-loaded surface
+  (`MEMORY.md` plus all descriptions) separately from the rest. That number is
+  the point of the run.
+
+## Rules
+
+- Deleting is the goal; rewriting shorter is the fallback. Prefer removing an
+  entry over polishing it.
+- Never merge two memories whose evidence differs. Two incidents supporting one
+  rule are stronger than one; two rules sharing one incident is a fabrication.
+- A skill that has never fired is a candidate for deletion, not compaction —
+  say so and let the operator decide.
+- Nothing is written without the Step 4 confirmation, and nothing outside the
+  scope ticked in Step 1.
+- `caveman-compress` is not a rival: it rewrites the wording of one named file,
+  this removes what should not be there at all. Run this one first — compressing
+  a dead entry is pure waste.

skills/explain/SKILL.md

@@ -1,10 +1,9 @@
 ---
 name: explain
 description: >
-  Explain code and its interactions. Trigger when the operator asks what a
-  piece of code does, how a mechanism works, why components interact the way
-  they do, or invokes /explain on a file, function, role, or module.
-  Portable across projects.
+  Explain code and its interactions. Trigger when the operator asks what code
+  does, how a mechanism works, why components interact, or invokes /explain on
+  a file, function, role or module.
 ---
 
 Explain the named code so an engineer who has never seen it can follow it:

skills/funnel/SKILL.md

@@ -0,0 +1,116 @@
+---
+name: funnel
+description: >
+  Keep agent work in its own git worktree until it reaches 90% fix confidence
+  and under 5% break risk; below that bar it becomes a proposal. Trigger when
+  delegating work to agents, when agents work in parallel, or on /funnel.
+---
+
+# Funnel
+
+The main line only receives changes that have earned it. Everything else stays
+in a sidetree until it does, or leaves as a proposal.
+
+## The bar
+
+- **Fix confidence of at least 90 %** and **break risk under 5 %**, both
+  reported by the `confidence` skill, the break risk derived through the
+  `break-risk` skill.
+- The operator may set a different bar. Never lower it to make a change fit.
+
+## The stages
+
+1. **Brief.** One concern per agent, on the model the `subagent-model` skill
+   picks. Name the goal, the exact base commit, the
+   scope that may change, the evidence expected back, a time cap (default
+   60 minutes) at which it reports its interim state, and what the agent must
+   not do: no pushes, no gates or deploys
+   unless the resource chair of the `democracy` skill granted them, read-only
+   probes on shared live systems.
+2. **Sidetree.** The agent works in its own worktree on its own branch,
+   created from the exact base commit, so its edits never land under a running
+   gate or deploy in the main line. Use the host's worktree isolation when it
+   has one.
+3. **Evidence.** The agent runs targeted tests, adds a test for the new
+   behaviour, and makes a negative control: the test fails without the change.
+   Numbers come from the same source before and after.
+4. **Self-assessment.** The agent reports fix confidence and break risk with
+   their residuals and commits on its branch.
+5. **Independent review.** Before anything is merged, run the `dialectic` skill
+   with skeptics who did not write the change. A hole they find returns the
+   change to stage 3.
+6. **Merge.** At or above the bar, merge the sidetree branch into the main line
+   following the repository's commit rules, then re-verify on the main line
+   with the project's gate.
+7. **Tear everything down.** Once the branch is merged, remove everything the
+   sidetree brought into being, so the next round starts from a clean
+   machine. See "After the merge" below.
+
+## After the merge
+
+A merged sidetree leaves nothing behind. Work through the list in this order,
+and verify each step instead of assuming it:
+
+1. **Stop its jobs**: background runs, watchers, scheduled loops and agents
+   that belong to the sidetree.
+2. **Tear down its stacks**: compose projects and swarm or test clusters
+   together with their volumes and networks, and the containers and images
+   built only for it. Leave anything another worktree still uses.
+3. **Clear files the containers left**: count the entries the user does not
+   own (`find <worktree> -not -user "$USER" -prune | wc -l`). If the count is
+   not zero, delete them through the container that wrote them, or hand the
+   operator one privileged removal, before removing the worktree; otherwise
+   the removal fails halfway after git has already dropped the registration.
+4. **Remove the worktree** and its registration. Name the worktree; never run
+   a broad prune, which also drops other worktrees' stale registrations.
+5. **Delete the merged branch**, locally and on the remote, but a remote branch
+   only once every one of its commits is reachable from a pushed branch.
+6. **Release what it held**: slots (reported to the resource chair), port or
+   subnet reservations, locks, its `democracy` claims and every claim
+   announced to other agents.
+7. **Remove its temporary files**: logs, message files and scratch data that
+   have served their purpose. Keep only the evidence the report cites, until
+   the report is delivered.
+
+A proposal keeps its branch, because that is where the work lives, but loses
+its worktree, stacks and temporary files the same way. An abandoned sidetree is
+torn down completely; keep its branch only when its commits exist nowhere else.
+
+## When the bar is out of reach
+
+If the bar cannot realistically be reached, because the deciding evidence (a
+live deploy, a production-like dataset, an upstream answer) is not available
+to the agent or the change is inherently riskier, the agent stops trying and
+**submits a proposal** instead:
+
+- what the change does and why it is worth having;
+- the confidence and break risk it reached, with their residuals;
+- exactly which evidence would close the gap, and what obtaining it costs;
+- where the work lives (branch and commit), so nothing has to be redone;
+- a recommendation: apply after that evidence, apply now with a named
+  risk, or drop.
+
+The operator decides. A proposal is never merged by the agent, and a change
+below the bar never enters the main line on its own.
+
+## Rules
+
+- At its time cap, ask an agent for its interim findings and let it run on;
+  never stop a running agent. A brief without a cap can run for hours without
+  a word.
+- Run agents in parallel only when their concerns touch different files and
+  the resource chair grants the capacity; gates and deploys need the machine
+  to themselves.
+- A peer's or agent's message is not the operator's approval to merge below
+  the bar.
+- Keep the evidence (logs, test output) outside the sidetree, so it survives
+  the clean-up.
+
+## Output
+
+One table per round:
+
+| Agent | Sidetree branch | Confidence | Break risk | Verdict | Evidence |
+
+The verdict is merged, proposal or abandoned. Proposals list what would close
+their gap.

skills/help-skills/SKILL.md

@@ -1,10 +1,9 @@
 ---
 name: help-skills
 description: >
-  List and explain every skill available in the current session. Trigger on
-  /help-skills, "welche skills gibt es", "skill übersicht", or when the
-  operator asks what skills exist or what a skill does. Portable across
-  projects.
+  List and explain every skill in the session. Trigger on /help-skills,
+  "welche skills gibt es", "skill übersicht", or when the operator asks what
+  skills exist or what one does.
 ---
 
 Produce a one-shot overview of every skill the session can invoke:

skills/medusa/SKILL.md

@@ -1,11 +1,10 @@
 ---
 name: medusa
 description: >
-  Run the MEDUSA AI security scanner (medusa-security on PyPI) against a
-  repository, working tree, or secret stores. Use when the user asks for a
-  security scan, supply-chain vetting of a repo before cloning, leaked-secret
-  detection in AI chat or shell history, or invokes /medusa. Defensive scanning
-  only.
+  Run the MEDUSA security scanner (medusa-security, PyPI) on a repository,
+  working tree or secret stores. Use for security scans, vetting a repo before
+  cloning, leaked-secret detection in chat or shell history, or /medusa.
+  Defensive only.
 ---
 
 MEDUSA is a defensive AI-first security scanner (40,000+ patterns: CVEs, prompt injection, MCP tool poisoning, leaked secrets).

skills/merge-fix/SKILL.md

@@ -0,0 +1,80 @@
+---
+name: merge-fix
+description: >
+  Hunt down the commits on any branch that carry a described fix and merge it
+  into the current branch. Trigger on /merge-fix <description> or when the
+  operator asks to bring over a fix from another branch.
+---
+
+The free text after `/merge-fix` is the fix description, exactly like `/loop`
+takes its prompt. Everything after the skill name is the search intent; there is
+no other input. If it is missing, ask for it and stop.
+
+## 1. Refuse to work on a dirty tree
+
+`git status --porcelain` must be empty. If it is not, stop and let the operator
+commit or open a worktree. Never stash, never `git checkout -- <file>`, never
+`git restore --staged`: those discard uncommitted work that other agents in the
+same tree may own.
+
+## 2. Fetch everything
+
+```bash
+git fetch --all --prune --tags
+```
+
+That is the "pull all branches" step. Do not check branches out one by one; all
+searching below runs against the fetched refs.
+
+## 3. Turn the description into search terms
+
+Derive from the operator's text: 2-4 keywords for commit messages, plus any
+symbol, string, or path the fix must have touched. State the derived terms in
+one line so a wrong reading is visible before the search.
+
+## 4. Search every ref
+
+Search by keyword, by literal and by path in one call; they find different
+things, and a commit matching any one of them is a hit, so `--path` widens
+the search instead of narrowing `--grep`:
+
+```bash
+${CLAUDE_SKILL_DIR}/scripts/find_fix.py --grep '<keyword>' -S '<symbol or literal>' --path '<path or glob>'
+```
+
+It drops every hit already in HEAD (`in_head` counts them; all in HEAD means
+the fix is already in, say so and stop) and prints the rest with their
+branches and files. Then read the actual change: `git show --stat <sha>` and
+the diff. A matching commit subject is a lead, not evidence, and `-S` also
+matches the commit that removed the literal; the diff decides.
+
+## 5. Present the candidates
+
+One table: sha, branch(es), subject, files touched, one line on what the diff
+really does. Let the operator pick unless exactly one candidate survives step 4
+and its diff plainly is the described fix.
+
+## 6. Bring it over
+
+- One or a few commits, rest of the branch unwanted: `git cherry-pick -x <sha>…`
+  (`-x` records the origin).
+- The whole branch is wanted: `git merge --no-ff <branch>`.
+- Conflicts: resolve them by reading both sides. Never `-X ours`/`-X theirs`,
+  never `git checkout --ours/--theirs` wholesale — that silently drops one
+  side's fix. Unresolvable → `git cherry-pick --abort` / `git merge --abort`,
+  report what conflicted, change nothing else.
+
+## 7. Report
+
+Show `git log --oneline <base>..HEAD` and the resulting diffstat, then apply the
+confidence skill: what came over, what did not, what still has to be verified.
+Run the project's test or quality gate only when the operator asks for it.
+
+## Rules
+
+- Never push and never force anything; the merge stays local until the operator
+  ships it.
+- Never rewrite history to make a cherry-pick fit (no rebase of the target
+  branch, no amend of foreign commits).
+- If the search finds nothing, say so plainly and list the terms tried. Do not
+  reimplement the fix under this skill — that is a different task.

skills/merge-fix/scripts/find_fix.py

@@ -0,0 +1,67 @@
+#!/usr/bin/env python3
+"""Find commits on any ref that match a fix, skipping those already in HEAD.
+
+Usage:
+    find_fix.py [--grep KEYWORD]... [-S LITERAL]... [--path PATH]... [--fetch]
+
+Prints one line per candidate: sha, up to three branches, subject, files
+touched. -S also matches commits that removed the literal; read the diff.
+Run it inside the repository; it never checks anything out.
+"""
+
+from __future__ import annotations
+
+import argparse
+import subprocess
+import sys
+
+LIMIT = 30
+
+
+def git(*args: str) -> subprocess.CompletedProcess:
+    return subprocess.run(["git", *args], capture_output=True, text=True, check=False)
+
+
+def search(args: argparse.Namespace) -> list[str]:
+    queries = [["--regexp-ignore-case", f"--grep={k}"] for k in args.grep]
+    queries += [[f"-S{s}"] for s in args.S]
+    queries += [["--", p] for p in args.path]
+    found: list[str] = []
+    for query in queries:
+        for sha in git("log", "--all", "--format=%H", *query).stdout.split():
+            if sha not in found:
+                found.append(sha)
+    return found
+
+
+def describe(sha: str) -> str:
+    subject = git("log", "-1", "--format=%h %s", sha).stdout.strip()
+    branches = git("branch", "-a", "--contains", sha, "--format=%(refname:short)").stdout.split()
+    files = [f for f in git("show", "--name-only", "--format=", sha).stdout.split("\n") if f]
+    shown = ",".join(branches[:3]) + (f",+{len(branches) - 3}" if len(branches) > 3 else "")
+    return f"{subject}\t{shown or '-'}\t{len(files)} files: {','.join(files[:5])}"
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(prog="find_fix")
+    parser.add_argument("--grep", action="append", default=[])
+    parser.add_argument("-S", action="append", default=[])
+    parser.add_argument("--path", action="append", default=[])
+    parser.add_argument("--fetch", action="store_true")
+    args = parser.parse_args()
+    if not (args.grep or args.S or args.path):
+        parser.error("give at least one --grep, -S or --path")
+    if args.fetch:
+        git("fetch", "--all", "--prune", "--tags")
+    hits = search(args)
+    outside = [sha for sha in hits if git("merge-base", "--is-ancestor", sha, "HEAD").returncode]
+    print(f"hits={len(hits)} in_head={len(hits) - len(outside)} candidates={len(outside)}")
+    for sha in outside[:LIMIT]:
+        print(describe(sha))
+    if len(outside) > LIMIT:
+        print(f"... {len(outside) - LIMIT} more, narrow the search")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

skills/no-defaults/SKILL.md

@@ -1,15 +1,10 @@
 ---
 name: no-defaults
 description: >
-  Forbid default values for parameters, settings, and environment lookups in
-  every language. Load and apply AUTOMATICALLY on every task that writes,
-  edits, generates, refactors, or reviews code, config, templates, schemas,
-  or infrastructure — never wait to be asked. A default silently substitutes
-  a guess for a value the caller failed to supply, so a misconfiguration
-  becomes wrong behaviour instead of a loud failure. Demand strict, explicit
-  values and fail loudly when one is missing. `false`, `null` and `""` are the
-  only free defaults; every other default needs a written justification.
-  Portable across projects.
+  Forbid default values for parameters, settings and environment lookups;
+  demand explicit values and fail loudly. Apply AUTOMATICALLY on every task
+  that writes, edits, generates, refactors or reviews code, config, templates,
+  schemas or infrastructure.
 ---
 
 A default value is a guess, written at the point where the caller's intent is
@@ -59,7 +54,7 @@ with `false`, `null`, or `""` is permitted, and with any other value is permitte
 only when justified in a comment.
 
 | Language | Never | Instead |
-|---|---|---|
+| --- | --- | --- |
 | Bash | `${VAR:-x}`, `${VAR:=x}`, `: "${VAR:=x}"` | `: "${VAR:?set VAR in <file>}"` |
 | Python | `def f(a=1)`, `d.get(k, x)`, `getattr(o, n, x)`, `os.environ.get(k, x)`, `argparse(default=)` | required args, `d[k]`, `os.environ[k]`, `add_argument(required=True)` |
 | Jinja / Ansible | `\| default(x)`, `lookup('env', k) \| default('')` | `\| mandatory`, `assert` on the var |

skills/observe/SKILL.md

@@ -1,10 +1,9 @@
 ---
 name: observe
 description: >
-  Watch a named target (a CI run, a pipeline, a build, a log) on a fixed
-  cadence and apply the triage skill whenever new failures appear. Trigger on
-  /observe <target> or when the operator asks to keep monitoring something and
-  fix regressions as they surface. Portable across projects.
+  Watch a named target (CI run, pipeline, build, log) on a cadence and triage
+  new failures as they appear. Trigger on /observe <target> or when the
+  operator asks to keep monitoring and fix regressions.
 ---
 
 Keep a target under continuous watch and act only when it degrades. The loop is
@@ -27,7 +26,8 @@ gave one): after each observation, schedule the next wake-up yourself and pass
 the same `/observe` prompt back so the next firing repeats the watch.
 
 1. **Poll the target.** Pull its current state (job list, check conclusions, the
-   log's tail). Enumerate the failures exactly as the `triage` skill's step 1
+   log's tail); for a GitHub Actions run, the ci-artifacts skill's
+   `ci_failures.py <run>`. Enumerate the failures exactly as the `triage` skill's step 1
    does: failure, cancelled, timed-out; a downstream aggregate that fails only
    because an upstream did is not its own failure.
 2. **Diff against the baseline.** A failure is *new* only if it is not in the

skills/plan/SKILL.md

@@ -0,0 +1,65 @@
+---
+name: plan
+description: >
+  Turn a request into an objective-oriented plan and hand it to the robot
+  skill. Trigger on /plan or when the operator asks for a plan, breakdown or
+  strategy before work starts.
+---
+
+Produce a plan whose every item is an outcome with a check, then execute it
+autonomously. A plan that lists activities instead of objectives cannot be
+verified, and an unverifiable plan cannot be handed to a robot.
+
+## Procedure
+
+1. **Interview first.** Open every plan with the `active-listening` skill: ask
+   until scope, constraints, success criteria, and the operator-only facts are
+   all pinned, then reflect the understanding back. This is the only point in
+   the run where questions are allowed, so leave nothing open here.
+2. **Pin the objective.** State the end state in one sentence, as a condition
+   that is either true or false, never as an activity. Name the command or
+   observation that proves it.
+3. **Inspect before decomposing.** Read the code, config, tests, and history the
+   objective touches. Every plan item must rest on something you have seen, not
+   on an assumption about how the project works.
+4. **Decompose into sub-objectives.** Each item gets: the outcome it reaches,
+   the verification that proves it, and the items it depends on. Split an item
+   whenever it needs more than one verification. Order by dependency and mark
+   the items that are independent, so they can run in parallel.
+5. **Resolve the open decisions now.** Any root cause, design choice, or
+   trade-off the plan rests on gets settled before execution, escalating to the
+   `dialectic` skill where being wrong is expensive. The robot does not ask, so
+   an unresolved decision becomes a guess at runtime.
+6. **Record the plan as a todo list.** Write the sub-objectives into the
+   harness's own todo tracking, one entry per item, phrased as the outcome. Keep
+   a plan file only when the operator asks for one.
+7. **Present it and wait.** Show the objective, the ordered sub-objectives with
+   their verifications, what is deliberately out of scope, and the assumptions
+   the plan rests on. Stop here: the plan is the deliverable of this step.
+8. **Implement it statically, in full.** On the operator's go, write every code,
+   config, test, and doc change the plan calls for, across all sub-objectives,
+   before running anything that needs live infrastructure. Verify statically:
+   read the diff, run the linters, the unit tests, and whatever dry-run or
+   syntax check the project offers. This step ends only when the whole plan
+   exists on disk, with no sub-objective left unwritten.
+9. **Then iterate under `robot`.** With the static implementation complete,
+   invoke the `robot` skill with the objective as its goal for the dynamic part:
+   run, deploy, observe, fix, repeat until every verification passes. It drives
+   the loop without check-ins, verifies each outcome instead of assuming it, and
+   reports the items that fall outside its clearance for the operator to run.
+
+## Rules
+
+- One objective per item, in outcome form: "endpoint returns 200 for an expired
+  token", not "fix the auth middleware".
+- No item without a verification. If you cannot name what proves it, the item is
+  still a wish, not a plan.
+- Plan only what the request covers. Speculative future-proofing, refactors
+  nobody asked for, and abstractions with one caller belong in the out-of-scope
+  list, not in the plan.
+- Static before dynamic: never start the robot loop on a half-written plan. A
+  deploy that fails on code you had not written yet costs a full cycle and
+  proves nothing.
+- Re-plan on contradicted evidence: when execution disproves an assumption the
+  plan rests on, revise the plan instead of forcing the original steps through.
+- Cite `file:line` for every claim about the current state of the code.

skills/refactor/SKILL.md

@@ -0,0 +1,106 @@
+---
+name: refactor
+description: >
+  Refactor every uncommitted file (staged, unstaged, untracked) up to the
+  project's standards without changing behaviour. Trigger on /refactor or when
+  the operator asks to clean up, tidy or polish the current changes.
+---
+
+The unit of work is the uncommitted change set, not the repository. Behaviour
+stays identical: a refactor that changes what the code does is a bug, not a
+cleanup.
+
+## Step 1: fix the file set
+
+Read the set from git, never from memory of what was edited:
+
+```bash
+git status --porcelain
+```
+
+Take modified, added, renamed and untracked files. Drop deleted files, binaries,
+lockfiles, vendored trees and generated output. Restate the resulting list in
+one line before touching anything; if it is empty, say so and stop.
+
+Never `git stash` and never revert a working-tree file to compare - other agents
+and the operator share this tree. Read the committed version with
+`git show HEAD:<path>` into a temporary file instead.
+
+## Step 2: get a safety net first
+
+A refactor is only provably behaviour-preserving if something failed before it
+and passes after it. Before editing, check what covers the change set:
+
+- **Coverage exists**: run it now and record the green baseline. A suite that
+  was already red gets reported, not refactored around.
+- **No coverage and the code is testable logic**: write the characterization
+  tests first, against the current behaviour - including the behaviour you
+  consider wrong, so the refactor cannot silently change it. Keep them small
+  and framework-free unless the project already has a framework. Fix the
+  captured wrongness in a separate change, never in this one.
+- **Not sensibly testable**: pure glue, declarative config, a thin wrapper over
+  a service the test would have to mock into meaninglessness, or a project with
+  no test setup at all. Say so in one line and refactor without a net; do not
+  invent a test harness the project never asked for.
+
+The new tests are part of the deliverable and must still pass unchanged after
+the refactor. A test that had to be edited to stay green means the behaviour
+moved: revert the refactor, not the test.
+
+## Step 3: refactor each file
+
+Read the whole file first, then apply the standards that the surrounding code
+and the project's own config already establish (formatter config, linter rules,
+existing idioms) over any generic preference of your own.
+
+Four principles govern the result:
+
+- **SRP**: one file, one responsibility; one function, one reason to change. A
+  unit that needs an "and" to describe it is two units.
+- **SPOT**: every fact - a constant, a path, a schema, a rule - lives in exactly
+  one place and everything else references it.
+- **KISS**: the simplest construct that works. No abstraction without a second
+  caller today, no configuration for a value that never varies.
+- **DRY**: the same logic is written once. A literal repeated three times is a
+  missing constant.
+
+Concretely:
+
+- **File size**: no file containing program code exceeds 250 lines. Split the
+  overflow along the SRP seam - it is the symptom, not the cause. Description
+  and markup languages are exempt (Markdown, YAML, JSON, HTML, translation and
+  data files), as is the rare file the language or framework genuinely forbids
+  splitting: name that reason in the report, "it was easier" does not qualify.
+- **Duplication**: fold repeated logic into the helper that already exists;
+  create a new one only when two or more call sites need it now.
+- **Dead weight**: unused imports, variables, parameters, branches that cannot
+  be reached, flags with a single value, abstractions with one implementation.
+- **Naming**: names that state what a thing is, matching the file's convention.
+- **Shape**: split a function that needs a scroll to read; collapse nesting by
+  returning early; replace magic values with a named constant at its use site.
+- **Errors**: never widen a caught exception, never swallow one, never remove a
+  validation or a security check to make the code shorter.
+- **Comments**: invoke the `comments-clean` skill rather than reimplementing its
+  rules here.
+
+Do not reformat regions you have no substantive fix for - cosmetic churn buries
+the real change in the diff. If a file's problem is architectural and cannot be
+fixed inside the change set, report it instead of half-doing it.
+
+## Step 4: keep behaviour provable
+
+- Re-run the step 2 net and require the same green result as the baseline.
+- Never fold a bug fix, a feature, or a dependency change into a refactor.
+  Found a real bug? Name it in the report and leave it for a separate change.
+- Run the cheap checks the project already has for the touched files (formatter,
+  linter, the module's own unit tests). Do not start a full suite, a build, or a
+  deploy on your own initiative - propose it and let the operator trigger it.
+- State plainly what was verified and what was not. An unverified refactor is
+  reported as unverified.
+
+## Step 5: report
+
+One line per file: what changed and why it is safe. Then one line naming what
+was deliberately left alone (architectural findings, bugs, files skipped) and
+the exact command the operator can run to validate. Do not commit unless the
+operator asked for a commit.

skills/robot/SKILL.md

@@ -1,10 +1,9 @@
 ---
 name: robot
 description: >
-  Work fully autonomously to a goal. Trigger when the operator wants hands-off,
-  uninterrupted execution — the agent drives the task to completion without
-  check-ins, never stops before the goal is reached, and uses only commands it
-  is already cleared to run. Portable across projects.
+  Work fully autonomously to a goal: no check-ins, no stopping before the goal,
+  only commands already cleared. Trigger when the operator wants hands-off,
+  uninterrupted execution.
 ---
 
 Operate as an autonomous robot: given a goal, reach it without hand-holding.

skills/sceptic/SKILL.md

@@ -0,0 +1,86 @@
+---
+name: sceptic
+description: >
+  Analyse a repository, path or diff with a hostile eye for violated
+  principles: SPOT, DRY, KISS, SRP, security at trust boundaries. Trigger on
+  /sceptic, "sei skeptisch", "kritische analyse", "review the architecture",
+  or "what is wrong with the code".
+---
+
+The stance is adversarial: the code is guilty until its structure proves
+otherwise. This skill hunts violated principles, not bugs (`code-review`),
+not bloat (`ponytail-audit`), not leaked secrets (`medusa`). Read-only —
+report the findings, change nothing unless the operator asks afterwards.
+
+## Scope
+
+The operator names the target: a repository, a directory, a role, or a diff.
+Without a target, take the whole repository and rank by blast radius. State
+the scope in one line before reporting, and name explicitly what you did not
+read — an audit that silently covered half the tree reads as clean.
+
+## The lenses
+
+Apply each independently; a finding belongs to exactly one:
+
+1. **SPOT** — one truth, one place. A value, a version, a hostname, a
+   schema, a list of names that exists twice is a divergence waiting to
+   happen. Name both locations and the drift they will cause.
+2. **DRY** — repeated *knowledge*, not repeated text. Two blocks that look
+   alike but change for different reasons are correctly separate; merging
+   them is the violation. Prove the shared reason to change, or drop the
+   finding.
+3. **SRP** — one reason to change per unit. Look for the module that both
+   parses and persists, the function whose name contains "and", the role
+   that configures and deploys and monitors. The test: name the two
+   stakeholders who would each demand a change here.
+4. **KISS** — mechanism the problem never asked for: an abstraction with one
+   implementation, a config value that never varies, a cache with no
+   measured pressure, a retry loop around a deterministic call.
+5. **Security** — only at trust boundaries: unvalidated input crossing into
+   a query, a shell, a template, or a path; authorization checked in the
+   caller instead of the resource; a secret in a default, a log, or an
+   image layer; a permission wider than the operation needs. Defensive
+   findings only.
+6. **Silent defaults** — a fallback that substitutes a guess for a value the
+   caller failed to supply, turning a misconfiguration into wrong behaviour
+   instead of a loud failure. See the `no-defaults` skill.
+
+## Method
+
+- **Evidence before verdict.** Every finding carries `file:line` you actually
+  read. Grep for the sibling occurrences before calling something a
+  duplicate — one hit is not a pattern.
+- **Name the failure.** A finding must state what concretely goes wrong:
+  which value drifts, which caller breaks, which input reaches which sink.
+  A finding whose worst case is "feels wrong" gets deleted, not softened.
+- **Attack your own finding.** For anything consequential or expensive to
+  fix, run it through the `dialectic` skill before reporting it — the
+  strongest counter-argument is usually "these two are not the same
+  knowledge" or "this boundary is already checked upstream".
+- **Respect intent.** A deliberate marker (`ponytail:`, a documented
+  exception, a nocheck directive with a reason) is a known ceiling, not a
+  finding. Report it only when the ceiling has since been exceeded.
+
+## Output
+
+One ranked table, worst blast radius first:
+
+| Severity | Principle | Location | What is wrong | Smallest fix |
+
+Then three closing lines at most: what the scope excluded, which findings
+survived `dialectic` versus which are still derived-only, and the single
+finding to fix first. No per-finding paragraphs — the operator asks when a
+row needs unpacking.
+
+## Rules
+
+- Never report formatting, naming taste, or missing comments; a linter owns
+  those and the operator did not ask.
+- Distinguish proven (grepped, read, reproduced) from derived (reasoned
+  statically) per finding, and close with the `confidence` skill's numbers
+  for the audit as a whole.
+- No silent caps: if you ranked and cut, say how many findings were dropped
+  and by what rule.
+- Skepticism ends at the report. Do not fix, stage, or refactor as part of
+  this skill.

skills/scope-guard/SKILL.md

@@ -0,0 +1,34 @@
+---
+name: scope-guard
+description: >
+  Deliver exactly what was asked and nothing more. Trigger on every task that
+  creates files, commands or commits, on unreviewed autonomous runs, on
+  hand-over requests, and when the operator asks why something unrequested
+  exists.
+---
+
+The requested scope is the deliverable. A problem you noticed behind the
+request is not an invitation to solve it.
+
+Before creating anything the request did not name, answer one question: which
+sentence of the request asks for this? No sentence, no artifact.
+
+1. No permanent scaffolding for a one-off need. A migration you run once needs
+   a throwaway script, not a CLI subcommand that ships forever. Do the thing,
+   then delete the scaffolding.
+2. Path-scope every `git add`. Never `-A`, never `.`. The operator's tree
+   carries their own edits and their local config, and sweeping those into
+   your bundle makes them undo your work by hand.
+3. An adjacent defect gets reported in one line, not fixed — unless it blocks
+   the request. Fixing it quietly puts an unreviewed change in someone else's
+   commit.
+4. An instruction to hand something over is complete on its own. Print the
+   artifact in the shape asked for: do not optimize, reorder or deduplicate it,
+   do not wrap it in a command that consumes it, and do not append commentary,
+   next steps, confidence blocks or offers. A narrowing qualifier ("just the
+   line") re-shapes the earlier request; re-emit narrower without re-deriving
+   the content. A problem with the artifact is worth one sentence before it,
+   never a rewrite of it.
+
+When something genuinely seems missing, say so in one sentence and finish the
+requested scope anyway. Widening the scope is the operator's call.

skills/shortcuts/SKILL.md

@@ -1,10 +1,9 @@
 ---
 name: shortcuts
 description: >
-  Portable operator conversation shortcuts, reusable across every project.
-  Trigger when the user's message is exactly one of these tokens (optionally
-  followed by arguments): sobu, soco, socobu, socon, sona, sote. Expand the
-  shortcut to the listed meaning and act on the expanded instruction.
+  Operator conversation shortcuts. Trigger when the message is exactly one of
+  these tokens, optionally with arguments: sobu, soco, socobu, socon, sona,
+  sote. Expand it and act on the expanded instruction.
 ---
 
 When an operator message is one of the shortcuts below, expand it to the meaning and act on it.

skills/status-matrix/SKILL.md

@@ -0,0 +1,61 @@
+---
+name: status-matrix
+description: >
+  Print one matrix of everything in flight: tasks, workflows, background jobs,
+  with confidence and break risk per item. Trigger on /status-matrix,
+  "status", "übersicht", "wo stehen wir", or what is done, left or running.
+---
+
+One-shot overview, no side effects: this skill reads state and reports it. It
+never edits files, stages, commits, deploys, or starts work — the operator
+decides what to act on after reading the matrix.
+
+## Collect the state
+
+Gather in parallel, skip any source the session does not have, and never invent
+a row for a source you could not read:
+
+1. **Tasks** — the session's todo list, the operator's stated goals this
+   session, and any requirement or plan documents the work follows.
+2. **Working tree** — `git status --short` and `git log --oneline -10`:
+   uncommitted files are open work, commits since the branch point are closed
+   work. Untracked files count as open.
+3. **Running** — background bash jobs, spawned agents not yet reported,
+   scheduled `/loop` wake-ups, and remote runs (CI, deploys). Poll their live
+   state; a job you started is not "running" because you started it.
+4. **Remote** — open PRs and issues for the branch, and their check
+   conclusions, when a forge CLI is available.
+
+## The matrix
+
+One table, most-blocking first, one row per item:
+
+| Item | State | Conf. | Break risk | Evidence / next step |
+
+- **State**: `open`, `running`, `blocked`, `done`. `done` means verified —
+  a passing run, a green check, a reproduction that now succeeds. Work that
+  merely looks finished is `open`.
+- **Conf.** and **Break risk**: two separate percentages per the `confidence`
+  skill — probability the item does what it claims, and probability it breaks
+  something else. Only for rows that changed something; `—` for pure
+  observation rows.
+- **Evidence / next step**: for `done`, the strongest proof line (what ran,
+  what it returned). For everything else, the single next action.
+
+Then at most three lines below the table:
+
+- **Blocked on**: what needs the operator (a decision, a credential, an
+  approval) — omit when nothing does.
+- **Residuals**: what keeps the lowest confidence number below 100.
+- **Running**: what will report back on its own, so the operator does not wait
+  on it manually.
+
+## Rules
+
+- Cover everything in scope, including work the operator did not ask about —
+  a forgotten background job or an unpushed commit is exactly what the matrix
+  exists to surface.
+- Report what the poll returned, never a predicted result for work still in
+  flight; a running item has no confidence number yet.
+- Compress: one row per item, no per-item paragraphs. If a row needs
+  explaining, the operator will ask.

skills/subagent-model/SKILL.md

@@ -0,0 +1,72 @@
+---
+name: subagent-model
+description: >
+  Pick `model` and `effort` per subagent from a fixed table: cheaper only on a
+  clear match at 90 % that the result equals the default's; log spawns and
+  quality. Apply AUTOMATICALLY before every Agent tool call.
+---
+
+A subagent runs on the main model and effort unless the spawn names others.
+Set `model` and `effort` on an Agent call only when the task clearly matches a
+row below and you are at least 90 % sure the cheaper setting delivers the same
+result as the default: no lost findings, no rework. Cost counts per finished
+task, retries included. Otherwise set neither, and the default stays.
+
+## Table
+
+| Task class | Subagent's task | `model` | `effort` | Evidence |
+| --- | --- | --- | --- | --- |
+| `lookup` | Read-only: find files, symbols or call sites, grep, list, read and quote, pull a log line or field, summarise a given text without judging it | `haiku` | `low` | Haiku 5.5 costs 1/40 of Opus 5.5 per token and is the speed tier; Anthropic names Haiku at low effort for simple, speed-critical and reading-heavy worker tasks; Explore and the cavecrew investigator already run on it |
+| `mechanical-edit` | An edit the brief fully specifies (exact old and new text, a rename, deleting listed lines) in one or two files | `haiku` | `low` | nothing is left to decide, and the parent checks the diff |
+| `judgement` | Everything else: root cause, skeptic or dialectic antithesis, review, security or legal checks, design, new or multi-file code, writing tests, performance work | omit | omit | no evidence at 90 % that a cheaper setting gives the same result |
+
+Prices per million tokens in and out (claude-api reference, cached
+2026-10-06): Haiku 5.5 $0.10 / $0.50, Sonnet 5.5 $2 / $10, Opus 5.5 $4 / $20,
+Fable 5.1 $10 / $50.
+
+## Spawn
+
+1. Pick the class. A task that mixes classes, or whose class you hesitate
+   over, is `judgement`.
+2. Start the brief with the line `task-class: <class>`; the spawn hook logs
+   it together with `model`, `effort` and the Agent `description`.
+3. Set `model` and `effort` from the row; for `judgement` set neither.
+
+- An agent type whose definition sets its own model (Explore, Plan, the
+  cavecrew agents) keeps it; never pass `model` or `effort` for it.
+- Never pass `fable` or `opus`: neither is cheaper than the default.
+- A Haiku agent that reports the task needs judgement, or returns an
+  incomplete result, is not retried on Haiku: the default continues it.
+- Never change the default itself (settings, `CLAUDE_CODE_SUBAGENT_MODEL`,
+  agent definitions); this skill only chooses per call.
+
+## Feedback
+
+Once you have judged the subagent's result, rate it under the same Agent
+`description`:
+
+```bash
+${CLAUDE_SKILL_DIR}/scripts/log.py feedback --description "<description>" --completed yes|no --tests pass|fail|none --redo yes|no
+```
+
+`--redo yes` when the default had to redo or finish the work. When the
+operator later asks a follow-up question about that result or corrects it:
+
+```bash
+${CLAUDE_SKILL_DIR}/scripts/log.py followup --description "<description>" --text "<question or correction>"
+```
+
+All sessions share `~/.local/state/agents-council/subagent-model.jsonl`.
+Inside a sandbox that cannot write it, the script prints the line as
+`pending:` and the PostToolUse hook stores it.
+
+## Evaluation
+
+`log.py report` shows per task class, model and effort the runs, the rated
+runs and the share with the same result: completed, not redone, no failing
+test, no follow-up. A row is added, or a cheaper setting extended to a class,
+only when the report shows at least 90 % over at least 20 rated runs, and only
+after the operator confirms it (for example through `/autotune`). A row whose
+rate falls below 90 % over 20 rated runs goes back to the default. `sonnet`
+enters the table only this way, and a trial run on a setting the table does
+not hold needs the operator's order.

skills/subagent-model/scripts/log.py

@@ -0,0 +1,205 @@
+#!/usr/bin/env python3
+"""Log subagent spawns with their quality feedback, and evaluate the table.
+
+Usage:
+    log.py spawn      hook (PreToolUse on Agent): append the spawn line
+    log.py feedback --description D --completed yes|no --tests pass|fail|none --redo yes|no
+                      rate the latest spawn with this Agent description
+    log.py followup --description D --text T
+                      record an operator follow-up question or correction on it
+    log.py persist    hook (PostToolUse on Bash): append the one line a sandboxed
+                      feedback or followup printed as `pending: <json>`, only
+                      when the command was that bare call and the line is
+                      well-formed and from the hook's own session
+    log.py report     runs, rated runs and same-result rate per task class,
+                      model and effort; a row qualifies at >= 90 % over >= 20
+
+Environment:
+    SUBAGENT_MODEL_LOG: the log shared by every session;
+        ~/.local/state/agents-council/subagent-model.jsonl unless set.
+    CLAUDE_CODE_SESSION_ID: the session that rates its spawns.
+"""
+
+from __future__ import annotations
+
+import argparse
+import datetime
+import json
+import os
+import re
+import shlex
+import sys
+from pathlib import Path
+
+LOG = Path(
+    os.environ.get(
+        "SUBAGENT_MODEL_LOG",
+        str(Path.home() / ".local" / "state" / "agents-council" / "subagent-model.jsonl"),
+    )
+)
+TASK_CLASS = re.compile(r"^task-class:\s*(\S+)", re.MULTILINE)
+PENDING = "pending: "
+SCRIPT = "subagent-model/scripts/log.py"
+CONTROL = re.compile(r"^[();<>|&]+$")
+KEYS = {
+    "feedback": {"kind", "time", "session", "description", "completed", "tests", "redo"},
+    "followup": {"kind", "time", "session", "description", "text"},
+}
+QUALIFY_RUNS = 20
+QUALIFY_RATE = 0.9
+
+
+def now() -> str:
+    return datetime.datetime.now(datetime.UTC).isoformat(timespec="seconds")
+
+
+def append(line: dict) -> None:
+    LOG.parent.mkdir(parents=True, exist_ok=True)
+    with LOG.open("a", encoding="utf-8") as handle:
+        handle.write(json.dumps(line, sort_keys=True) + "\n")
+
+
+def record(line: dict) -> int:
+    try:
+        append(line)
+    except OSError:
+        print(PENDING + json.dumps(line, sort_keys=True))
+    return 0
+
+
+def cmd_spawn() -> int:
+    payload = json.load(sys.stdin)
+    tool = payload.get("tool_input") or {}
+    match = TASK_CLASS.search(tool.get("prompt", ""))
+    append({
+        "kind": "spawn",
+        "time": now(),
+        "session": payload.get("session_id", ""),
+        "description": tool.get("description", ""),
+        "subagent_type": tool.get("subagent_type") or "general-purpose",
+        "task_class": match.group(1) if match else "unclassified",
+        "model": tool.get("model") or "default",
+        "effort": tool.get("effort") or "default",
+    })
+    return 0
+
+
+def rated(kind: str, args: argparse.Namespace, **fields: object) -> dict:
+    session = os.environ.get("CLAUDE_CODE_SESSION_ID")
+    if not session:
+        sys.exit("log.py: CLAUDE_CODE_SESSION_ID is not set")
+    return {"kind": kind, "time": now(), "session": session, "description": args.description, **fields}
+
+
+def invoked_kind(command: str) -> str | None:
+    if "$(" in command or "`" in command:
+        return None
+    lexer = shlex.shlex(command, posix=True, punctuation_chars=True)
+    lexer.whitespace_split = True
+    try:
+        tokens = list(lexer)
+    except ValueError:
+        return None
+    if any(CONTROL.match(token) for token in tokens):
+        return None
+    if tokens[:1] in (["python3"], ["python"]):
+        tokens = tokens[1:]
+    if len(tokens) < 2 or not tokens[0].endswith(SCRIPT) or tokens[1] not in KEYS:
+        return None
+    return tokens[1]
+
+
+def well_formed(line: object, kind: str, session: str) -> bool:
+    if not isinstance(line, dict) or set(line) != KEYS[kind] or line["kind"] != kind or line["session"] != session:
+        return False
+    if not all(isinstance(line[key], str) for key in ("time", "description")):
+        return False
+    if kind == "feedback":
+        return isinstance(line["completed"], bool) and isinstance(line["redo"], bool) and line["tests"] in ("pass", "fail", "none")
+    return isinstance(line["text"], str)
+
+
+def cmd_persist() -> int:
+    payload = json.load(sys.stdin)
+    kind = invoked_kind((payload.get("tool_input") or {}).get("command", ""))
+    if not kind:
+        return 0
+    response = payload.get("tool_response")
+    stdout = response.get("stdout", "") if isinstance(response, dict) else str(response or "")
+    pending = [text[len(PENDING):] for text in stdout.splitlines() if text.startswith(PENDING)]
+    if len(pending) != 1:
+        return 0
+    try:
+        line = json.loads(pending[0])
+    except json.JSONDecodeError:
+        return 0
+    if well_formed(line, kind, payload.get("session_id", "")):
+        append(line)
+    return 0
+
+
+def runs() -> list[dict]:
+    current: dict[tuple[str, str], dict] = {}
+    found: list[dict] = []
+    for text in LOG.read_text(encoding="utf-8").splitlines() if LOG.exists() else []:
+        line = json.loads(text)
+        key = (line["session"], line["description"])
+        if line["kind"] == "spawn":
+            current[key] = {**line, "feedback": None, "followups": 0}
+            found.append(current[key])
+        elif key in current and line["kind"] == "feedback":
+            current[key]["feedback"] = line
+        elif key in current and line["kind"] == "followup":
+            current[key]["followups"] += 1
+    return found
+
+
+def same_result(run: dict) -> bool:
+    feedback = run["feedback"]
+    return feedback["completed"] and not feedback["redo"] and feedback["tests"] != "fail" and not run["followups"]
+
+
+def cmd_report() -> int:
+    rows: dict[tuple[str, str, str], list[dict]] = {}
+    for run in runs():
+        rows.setdefault((run["task_class"], run["model"], run["effort"]), []).append(run)
+    print("task_class\tmodel\teffort\truns\trated\tsame\trate\tqualifies")
+    for (task_class, model, effort), group in sorted(rows.items()):
+        rated_runs = [r for r in group if r["feedback"]]
+        same = sum(map(same_result, rated_runs))
+        rate = same / len(rated_runs) if rated_runs else 0.0
+        qualifies = len(rated_runs) >= QUALIFY_RUNS and rate >= QUALIFY_RATE
+        print(f"{task_class}\t{model}\t{effort}\t{len(group)}\t{len(rated_runs)}\t{same}\t{rate:.0%}\t{'yes' if qualifies else 'no'}")
+    return 0
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
+    sub = parser.add_subparsers(dest="command", required=True)
+    sub.add_parser("spawn")
+    feedback = sub.add_parser("feedback")
+    feedback.add_argument("--description", required=True)
+    feedback.add_argument("--completed", required=True, choices=("yes", "no"))
+    feedback.add_argument("--tests", required=True, choices=("pass", "fail", "none"))
+    feedback.add_argument("--redo", required=True, choices=("yes", "no"))
+    followup = sub.add_parser("followup")
+    followup.add_argument("--description", required=True)
+    followup.add_argument("--text", required=True)
+    sub.add_parser("persist")
+    sub.add_parser("report")
+    args = parser.parse_args()
+    if args.command == "spawn":
+        return cmd_spawn()
+    if args.command == "feedback":
+        return record(rated(
+            "feedback", args, completed=args.completed == "yes", tests=args.tests, redo=args.redo == "yes"
+        ))
+    if args.command == "followup":
+        return record(rated("followup", args, text=args.text))
+    if args.command == "persist":
+        return cmd_persist()
+    return cmd_report()
+
+
+if __name__ == "__main__":
+    sys.exit(main())

skills/test/SKILL.md

@@ -0,0 +1,130 @@
+---
+name: test
+description: >
+  Discover the Makefile's test targets, let the operator pick, run and report;
+  fix mode loops until green. Trigger on /test, /test --fix, or when the
+  operator asks to run the tests, make them pass, or get the suite green.
+---
+
+The Makefile is the source of truth for how this project runs tests. Never
+invent a command (`pytest`, `npm test`, `go test`) while a Makefile target
+exists - the target carries the project's env vars, build dependencies and
+container setup.
+
+## Step 1: find the targets
+
+From the repository root:
+
+```bash
+grep -nE '^test[A-Za-z0-9_.-]*:' Makefile
+```
+
+Read the matched rules plus their prerequisites, so the selection list can say
+what each one actually does (delegated script, container build, sub-targets).
+
+Edge cases, handled explicitly rather than guessed around:
+
+- **No Makefile**: say so in one line, name the test runner the project does
+  use (from `pyproject.toml`, `package.json`, `tox.ini`, CI workflow), and ask
+  before running anything.
+- **No `test*` target**: report the targets that do exist and stop.
+- **Included makefiles** (`include foo.mk`): grep those too.
+- **Aggregate targets**: a target whose recipe is only other test targets (e.g.
+  `test: test-unit test-integration`) is the "run everything" entry - mark it as
+  such in the list, do not expand it into its parts silently.
+
+## Step 2: offer the selection
+
+Ask with `AskUserQuestion`, `multiSelect: true`, one question. Options are the
+discovered targets, each with a one-line description of what it runs. Order the
+aggregate/full target first and label it as the complete suite.
+
+The tool takes at most 4 options. With more targets than that:
+
+- print the **complete** discovered list as text first, one line per target, so
+  nothing is hidden, then
+- offer the 4 most useful entries (aggregate first, then the ones matching the
+  operator's stated intent or the files currently uncommitted), and note that
+  "Other" accepts any target name from the printed list.
+
+Never silently truncate. If the operator already named a target in their
+request, skip the question and run it.
+
+## Step 3: run
+
+Run the selected targets in the order the operator listed them, one `make`
+invocation per target, each as its own command so a failure is attributable:
+
+```bash
+make <target>
+```
+
+Do not add `-k`, do not reorder, do not substitute a faster equivalent. If a
+target needs a long timeout (container builds, e2e), set it on the Bash call
+rather than backgrounding blindly.
+
+Stop after the first failing target unless the operator asked for all of them -
+a later suite running against a broken build produces noise, not information.
+
+## Step 4: report
+
+Per target: pass/fail plus the failing test names and the exact error output,
+quoted verbatim. Never paraphrase a failure. Then one line with the exact
+command to reproduce the failure alone.
+
+Do not fix what failed unless the operator asks - report first. A request to
+make the tests pass, fix them, or get the suite green (`/test --fix`) switches
+to fix mode.
+
+## Fix mode
+
+The contract is narrow: the code becomes correct, the tests stay honest.
+
+One iteration is: run -> read the failure -> one root cause -> one fix ->
+re-run. Never batch several speculative fixes into one iteration; a green run
+after three simultaneous changes proves nothing about which one mattered.
+
+- **Run** the failing target alone, the fastest command that reproduces the
+  failure. Widen back to the full selection only when that target is green.
+- **Diagnose** from the actual error output before touching a file. Apply the
+  `triage` skill to reach a verified root cause; for a cause still unclear
+  after one look, apply `dialectic` rather than guessing twice. Say in one line
+  which side is wrong:
+  - **Code**: the test states the intended behaviour. Fix the code.
+  - **Test**: it encodes an outdated or incorrect expectation. Fix it only with
+    a stated reason why the old expectation was wrong, never because the code
+    disagrees with it.
+  - **Environment**: missing dependency, stale container, absent env var,
+    unbuilt artefact. Fix the environment or report it; do not patch code
+    around it.
+- **Fix** with the smallest change that addresses the root cause, in the
+  project's idioms and under the `no-defaults` and `comments-clean` rules.
+  Forbidden without explicit operator approval: deleting, skipping, `xfail`-ing
+  or commenting out a failing test; loosening an assertion to what the code
+  produces; swallowing the exception the test surfaces; retries, sleeps or
+  reruns over a flaky failure; disabling a linter rule, a type check or a
+  target. Any of these is a report item, not a fix: a suite that is green
+  because the failing test no longer runs is a regression disguised as success.
+- **Re-run** the same target, then every target that was already green; only
+  a full green selection ends the loop.
+
+Stop and report, without asking for permission to stop:
+
+- **Green**: the full selection passes.
+- **No progress**: the same failure survives 3 iterations, or the failure count
+  stops falling across 3 iterations. Report the root cause reached, what was
+  tried, and why each attempt failed.
+- **Beyond the mandate**: the real fix is an API change, a dependency bump, a
+  schema migration, or a redesign. Name it with its minimal diff and let the
+  operator decide.
+- **Oscillation**: fixing A re-breaks B and vice versa. Report both; that is a
+  design problem, not a test problem.
+- **Flaky**: a target passes and fails without any change. Report both
+  outputs; never rerun until green.
+
+Emit one line per iteration: target, failure, hypothesis, change. The final
+report gives per iteration what failed, the root cause, the fix and the
+result; the final state of every selected target with the verbatim output of
+anything still failing; everything deliberately not done; and the command
+reproducing the final state. State confidence per the `confidence` skill. Do
+not commit unless the operator asked for a commit.

skills/triage/SKILL.md

@@ -1,10 +1,9 @@
 ---
 name: triage
 description: >
-  Triage a failing CI run, pipeline, or job set to a verified root cause and a
-  real fix. Trigger when a build, test, or deploy pipeline has one or more failed
-  jobs. Applies the dialectic skill to every failing job independently. Portable
-  across projects.
+  Triage a failing CI run, pipeline or job set to a verified root cause and a
+  real fix, one cluster per worktree. Trigger when a build, test or deploy
+  pipeline has failed jobs.
 ---
 
 Drive a red pipeline to green by root cause, not by guesswork. Treat every
@@ -13,24 +12,80 @@ root cause is proven.
 
 ## Procedure
 
+For a GitHub Actions run, the ci-artifacts skill's `ci_failures.py <run>`
+does the mechanics of steps 0 to 2 in one call: distance to HEAD, the failed
+jobs' logs, and a first clustering. The judgement in those steps stays yours.
+
+0. **Check the run against HEAD before anything else.** A CI run is a snapshot
+   of one commit, and the branch has moved since. Run
+   `git log --oneline <run-sha>..HEAD | wc -l` as the first command of the
+   triage. Zero means the run speaks for the current tree and you proceed.
+   Non-zero means it does not, and you scope the job set down **before**
+   enumerating, clustering, or spawning anything — every job you investigate
+   against stale code is work thrown away, and a fix proposed there risks
+   reverting someone else's. Two cheap discriminators do it without opening an
+   artifact: `git diff --name-only <run-sha>..HEAD -- <source dir> | cut -d/ -f2 | sort -u`
+   for which components already moved, and a grep of the saved job logs for the
+   literal error signature of each cause already fixed in that range. What
+   survives both is the job set the rest of this procedure applies to; say how
+   many jobs you dropped and why.
 1. **Enumerate every failing job.** Pull the run's job list and isolate each job
    whose conclusion is failure, cancelled, or timed-out. A downstream aggregate
    job that fails only because an upstream job did is not a separate root cause —
    note it and move on.
-2. **Dialectic per failing job.** For EACH failing job, invoke the `dialectic`
-   skill: form a thesis about the root cause from evidence (the job log, its
-   artifacts, the code at the run's commit, git history), attack it with
-   independent skeptics, and iterate to a ~99% thesis. The jobs are independent,
-   so run their investigations in parallel where the tooling allows.
-3. **Distinguish shared vs hidden causes.** When several jobs share one root
-   cause, fix it once. When a job hides a second failure behind the first, keep
-   going until the job is actually green, not just past the first error.
-4. **Fix at the root.** Apply the real fix in the repository for each proven root
-   cause. Never mask a failure — no retry-until-pass, no disabling the check, no
-   soft-skip. If a failure is genuinely external (upstream outage, flaky infra),
-   confirm that with evidence and surface it honestly instead of fixing around
-   it.
-5. **Follow the run.** While the run is still in progress, re-check it
+2. **Cluster the failures by error message.** Group the failing jobs by their
+   actual failing line, not by job name. Jobs whose messages differ in anything
+   but the interpolated identifiers (host, app, port, path) belong in separate
+   clusters.
+3. **Coordinate every cluster.** Run the `democracy` skill's Lineage and Peer
+   protocol for each cluster before fixing it: claim it, ask the lineage
+   whether someone already fixes it, and take their fix or keep yours. Keep
+   investigating while you wait for answers.
+4. **Download artifacts per cluster.** Use the `ci-artifacts` skill for the
+   mechanics — it covers per-job logs while a run is still in progress, which
+   bundle to pull, and the grep hygiene that keeps a false positive from
+   becoming a root cause. For each cluster, fetch every artifact of
+   one representative job: reports, rescue diagnostics, inventories, container
+   logs. Pull a second member's artifacts only when the representative's
+   evidence does not explain the whole cluster. The job log usually names an
+   artifact path and nothing more; the assertion text, the server-side
+   exception and the state dumps are inside the artifact. Do this even when the
+   log looks conclusive, because a log that explains the symptom rarely
+   explains the cause.
+5. **One funnel per cluster.** Hand every cluster you claimed in step 3 to the
+   `funnel` skill: one agent per cluster, working in its own worktree on its own
+   branch created from the exact current HEAD, with that cluster as its only
+   concern, the artifact paths of step 4 in its brief and a time cap for its
+   interim report.
+   Steps 6 to 8 run inside that sidetree, so no cluster's edits land under
+   another cluster's work or under a running gate or deploy. Run clusters in
+   parallel only when their fixes touch different files and the machine has
+   room. A split cluster (step 7) gets a funnel of its own.
+6. **Dialectic per cluster.** For EACH cluster, invoke the `dialectic` skill:
+   form a thesis about the root cause from evidence (the job log, its artifacts,
+   the code at the run's commit, git history), attack it with independent
+   skeptics, and iterate to a ~99% thesis.
+7. **Distinguish shared vs hidden causes.** A cluster is a hypothesis, not a
+   proof: if the dialectic shows one cluster splitting into two causes, split it.
+   When a job hides a second failure behind the first, keep going until the job
+   is actually green, not just past the first error.
+8. **Fix at the root, through the funnel.** Apply the real fix for each proven
+   root cause in the cluster's sidetree, with a test and a negative control as
+   the `funnel` skill demands. The fix enters the main line only at the funnel's
+   bar (at least 90 % fix confidence, under 5 % break risk) after its
+   independent review; below the bar the cluster ends as a proposal for the
+   operator, never as a merge. Never mask a failure: no retry-until-pass, no
+   disabling the check, no soft-skip. If a failure is genuinely external
+   (upstream outage, flaky infra), confirm that with evidence and surface it
+   honestly instead of fixing around it. Report every fix, every proposal, and
+   every abandoned attempt to the same agents through the `democracy` Peer protocol,
+   then remove the sidetree.
+9. **Tune what ran out of time.** Only for a cluster whose jobs died on their
+   time budget (timed out, or cancelled by the runner's limit), or when the
+   operator asks: hand the job log that ran furthest to the `tune` skill. Its
+   candidates run through funnels of their own, separate from the cluster's fix
+   sidetree, and never delay or block the fix.
+10. **Follow the run.** While the run is still in progress, re-check it
    periodically and triage each newly failed job as it appears. The run is done
    only when it has finished and every failure has a verified fix.
 
@@ -38,7 +93,20 @@ root cause is proven.
 
 - Executed evidence beats reasoning: read the actual failing log line and the
   artifact, not the job title.
+- A derived source is not evidence. A conversation summary, your own earlier
+  message, a cluster table you built ten minutes ago, or a subagent's report
+  proves nothing on its own. Only the job log, the artifact, the code at the
+  run's commit, and command output you just ran count. Quote them literally; if
+  you cannot quote it, you do not know it.
+- Re-derive after a context compaction. A summary carried across a compaction
+  boundary preserves your conclusions but not the evidence under them, and a
+  cluster assignment that was wrong stays wrong while reading as settled fact.
+  Before acting on any pre-compaction attribution, rebuild it from the job logs.
 - Classify each failure: a real defect (fix it), a flake or infra hiccup (prove
-  it is transient before dismissing), or already-fixed-by-a-later-commit (verify
-  the fix is present in the run's commit before claiming it).
-- Report a per-job verdict: root cause, the evidence that proves it, and the fix.
+  it is transient before dismissing), or already-fixed-by-a-later-commit. For
+  that last class the comparison is `<run-sha>..HEAD`, never the run's commit
+  alone: the run cannot contain a fix that landed after it, so looking there
+  can only ever confirm the failure. Name the commit that carries the fix.
+- Report a per-job verdict: root cause, the artifact path and line that prove
+  it, the fix, the cluster's sidetree branch, and the funnel verdict (merged or
+  proposal). A verdict that cites only the job log has not finished step 4.

skills/tune/SKILL.md

@@ -0,0 +1,192 @@
+---
+name: tune
+description: >
+  Find and apply performance optimizations (CI, deploy, build, gate, hot
+  paths) without reducing logic, coverage or correctness. Trigger on /tune,
+  when a job dies on its time budget, when a pipeline or deploy grows slower,
+  or asked where time goes.
+---
+
+# Tune
+
+One rule outranks every optimization: **nothing that reduces logic, coverage or
+correctness counts as a speed-up.**
+
+## Once per session: listen first
+
+The first time this skill runs in a session, invoke the `active-listening`
+skill before measuring anything, and ask three questions through the host's
+structured question mechanism. Offer each as a checklist (multi-select) with
+suggestions, and allow free text:
+
+1. **What to examine.** Suggestions: CI wall-clock, deploy duration, gate and
+   test runtime, image pulls and build caches, per-item loops and process
+   spawns, idempotency (work repeated on a second run), network round trips,
+   resource use (CPU, memory, disk, I/O), and language or runtime choice for
+   hot paths.
+2. **Which performance boundaries to keep.** Suggestions: time budgets per job,
+   deploy or gate; resource caps (memory, CPU, disk headroom); a minimum saving
+   per change (default 10 s per run); the measurement source that counts as
+   the verdict.
+3. **Which limits apply to optimizations.** Suggestions: the scope that may be
+   changed (files, roles, services); whether new dependencies, toolchains or
+   languages may be introduced; whether infrastructure or CI configuration may
+   change; the merge bar (default: the `funnel` skill's 90 % confidence and
+   under 5 % break risk); a time cap per delegated agent (default 60 minutes).
+
+Keep the answers for the rest of the session and do not ask again. Work only
+inside them; a candidate outside them becomes a proposal.
+
+When another skill (triage, observe) or an autonomous run invoked tune, skip
+the questions: examine the handed-over log, apply the defaults above, and ask
+only when an operator-only fact blocks.
+
+## Forbidden, whatever it saves
+
+- Dropping a test, a spec, a play, a drill or a verification pass.
+- Raising a timeout or budget so a slow thing fits instead of getting faster.
+- Swallowed failures, retry-until-pass, a soft skip, a narrowed assertion.
+- Trading error semantics, credential masking, concurrency safety or a lint's
+  intent for speed. A per-item failure stays loud and names its item.
+
+A change that makes the clock smaller by testing less is reported to the
+operator as a coverage cut for them to decide, never applied as a tuning.
+
+## Measure first
+
+Never tune what has not been measured, and read numbers from logs, not by eye.
+
+- **Task profilers** (Ansible `profile_tasks` and similar) print the duration
+  of the *previous* task under the *next* task's header. Pair each header with
+  the following timestamp line, or read the end-of-run recap.
+- **Build logs** (BuildKit): pair `#N [service x/y] RUN …` with `#N DONE Xs`
+  by step number; `CACHED` marks a hit.
+- **Gates**: per-target wall-clock tables and failed-target lines. An exit code
+  piped through `tee` is not a verdict.
+- **Code paths**: a profiler (py-spy, cProfile, perf, flame graphs) tells
+  whether time goes to CPU, to I/O and waits, or to process start-up.
+- Stream every run to a log file and compare runs by their logs; never re-run
+  to recover a lost number.
+- **Rank by fixed cost x count.** Measure the per-call fixed cost (one
+  application console boot, one package-manager call, one container exec) and
+  multiply by how often the run pays it. A one-second boot paid twenty-eight
+  times is a candidate; a sixty-second download paid once is not.
+- **The baseline is the newest log of the current code.** An older log may
+  still carry the step a previous optimization replaced, and a saving measured
+  against it is fiction.
+
+## Invalid comparisons
+
+Discard a before/after pair, not just its noise, when:
+
+- Another gate, deploy or heavy job shared the machine during either run.
+- The two runs differ in image or cache state. A cold build after a cache prune
+  or a Dockerfile edit is expected: before calling a cold build a defect,
+  compare the instruction text and the base image digest across both logs.
+- One run pays a one-time cost (first install, migration, purge, model
+  download) the other does not.
+- A long wait hides retries or a failure; count retry lines before calling it
+  slow.
+- A fresh-install pass is compared with an update pass. Analyse each pass of a
+  multi-pass run separately.
+
+## Before you optimize
+
+- **Search every branch** (the merge-fix skill's `find_fix.py -S <symbol> --path <path>`) for a change
+  that already removes or reshapes the step. A fix on a sibling branch can make
+  the whole candidate worth zero.
+- A step that is long by design (a backup and restore drill, an end-to-end
+  suite) is not a candidate. Its cost buys its guarantee.
+- Apply the session's saving floor: a smaller saving is listed as "below
+  floor" and dropped.
+- Pruning build caches to free disk costs a cold rebuild of every custom image
+  on the next run. Name that cost before anyone prunes.
+
+## Coordinate every cost cluster
+
+A cost cluster is one place the time goes: one step, one hot path, one
+repeated call, named by its log line and its number. Before investigating or
+implementing a cluster, run the `democracy` skill's Peer protocol for it with
+every agent session on this machine, not only the branch lineage.
+
+- **The first to identify a cluster works it.** "First" is the `democracy`
+  claim `cluster/<slug>`, whose `--work` names the cluster's log line and
+  number; between machines, the earliest announcement by message time. A
+  claim without a measurement does not count.
+- **Someone was earlier:** send them your measurements and findings, then move
+  on to the next cluster. Never build a second optimization of the same
+  cluster.
+- **A claim ends** when its holder reports the result, a proposal or an
+  abandoned attempt and releases it, or when the operator reassigns it.
+
+## Levers that usually pay
+
+- **Batch per-item process spawns**: N calls that each boot an interpreter or
+  an application console become one process running N commands (one app
+  console boot, one module, one batched API request). Keep each item's failure
+  named and the exit code honest.
+- **Skip no-op work** a previous step already did, such as a separate enable
+  after an install that already enabled.
+- **Idempotency flip-flops**: any `changed` on a second consecutive run.
+- **Image pulls and builds**: pull only what the host lacks; keep build caches
+  warm.
+- **Overlap waits with work** only where concurrent execution is proven safe.
+  Schema migrations and lock-holding steps are usually not.
+
+## Language and runtime
+
+Look for language optimizations where they make sense, for example replacing a
+Python hot path with Rust:
+
+- **Only for measured CPU-bound work.** When the profile shows the time in
+  computation inside the process (parsing, hashing, rendering, tight loops),
+  a compiled language can win by an order of magnitude. When the time goes to
+  process start-up, network round trips or waiting, batching in the current
+  language wins first, and a rewrite changes nothing.
+- **Prefer the narrowest cut**: rewrite the hot function as an extension
+  module (for Python and Rust: PyO3 and maturin) or a small binary behind the
+  same interface, before rewriting a whole tool.
+- **Count the total cost**: a toolchain in CI, builds per target architecture,
+  shipping binaries to every host, the team's ability to maintain the code,
+  and test parity with the old implementation.
+- **Prove it on a prototype**: the same input, the same machine state, a before
+  and an after number, and the old test suite passing against the new code.
+- A language change is applied only when the session's limits allow new
+  languages or toolchains; otherwise it is submitted as a proposal with the
+  prototype's numbers.
+
+## Delegating an optimization
+
+Hand every optimization to an agent through the `funnel` skill: one sidetree
+per candidate, branched from an exact commit, with a time cap and "measure
+first, report the time split before implementing". The agent probes live
+systems read-only and never starts gates or deploys. A broad brief without a
+cap can run for hours without a word; at its cap, collect the agent's interim
+findings and let it run on.
+
+Before merging, run independent skeptics through the `dialectic` skill. The
+antithesis must try to show that the candidate removes coverage, hides a
+failure, or only moves the cost somewhere the measurement does not look.
+
+## The loop
+
+1. Measure, and name the single biggest cost with its log line and number.
+2. Coordinate the cluster with the other agents; work it only when you
+   identified it first, otherwise hand over your findings and take the next.
+   Then form one candidate for it, after the branch search and the floor check.
+3. Harden it with the `dialectic` skill.
+4. Funnel it through a sidetree; merge what reaches the bar, submit the rest as
+   proposals. Re-measure from the same source under the same conditions and
+   report a before and an after number.
+5. Repeat until the next candidate is worth less than the run that measures it.
+
+## Output
+
+One table, biggest saving first:
+
+| Candidate | Before | After | Source | Verdict |
+
+Rejected candidates stay in the table with the reason they fell: below floor,
+coverage cut, outside the session's limits, invalid comparison, made moot by
+another branch, or cap reached without a measured result. Proposals carry what
+would close their gap.

tests/test_autotune.py

@@ -0,0 +1,123 @@
+"""Validate the autotune reminder hook and its settings registration."""
+
+from __future__ import annotations
+
+import json
+import shutil
+import subprocess
+import tempfile
+import unittest
+from pathlib import Path
+
+REPO_ROOT = Path(__file__).resolve().parents[1]
+SKILL = REPO_ROOT / "skills" / "autotune" / "SKILL.md"
+HOOK = REPO_ROOT / "skills" / "autotune" / "hooks" / "reminder.sh"
+PATCHER = REPO_ROOT / "scripts" / "enable-plugins.js"
+
+
+def _run_hook(stamp: Path, interval: str = "3600") -> subprocess.CompletedProcess:
+    return subprocess.run(
+        ["bash", str(HOOK)],
+        capture_output=True,
+        text=True,
+        check=True,
+        env={
+            "PATH": "/usr/bin:/bin",
+            "HOME": str(stamp.parent),
+            "AUTOTUNE_STAMP": str(stamp),
+            "AUTOTUNE_INTERVAL_SECONDS": interval,
+        },
+    )
+
+
+class TestAutotuneSkill(unittest.TestCase):
+    def test_skill_is_trigger_only(self):
+        text = SKILL.read_text(encoding="utf-8")
+        self.assertIn("name: autotune", text)
+        self.assertIn("multiSelect: false", text)
+
+
+class TestSkillPersistence(unittest.TestCase):
+    """Both skill writers must persist to the skills repository AND the live dirs."""
+
+    def test_autotune_names_every_target(self):
+        text = SKILL.read_text(encoding="utf-8")
+        for target in (
+            "SKILLS_REPO",
+            "skills/<name>/SKILL.md",
+            "~/.claude/skills/",
+            "~/.agents/skills/",
+        ):
+            self.assertIn(target, text)
+
+    def test_autoskill_routes_to_the_same_persistence(self):
+        text = (REPO_ROOT / "skills" / "autoskill" / "SKILL.md").read_text(
+            encoding="utf-8"
+        )
+        for target in ("Persistence", "~/.claude/skills/", "~/.agents/skills/"):
+            self.assertIn(target, text)
+
+
+class TestAutotuneHook(unittest.TestCase):
+    def setUp(self):
+        self.tmp = tempfile.TemporaryDirectory()
+        self.addCleanup(self.tmp.cleanup)
+        self.stamp = Path(self.tmp.name) / ".claude" / ".autotune-stamp"
+
+    def test_first_run_hints_and_stamps(self):
+        result = _run_hook(self.stamp)
+        self.assertIn("/autotune", result.stdout)
+        self.assertTrue(self.stamp.is_file())
+
+    def test_second_run_is_silent_within_interval(self):
+        _run_hook(self.stamp)
+        self.assertEqual(_run_hook(self.stamp).stdout, "")
+
+    def test_hint_returns_after_the_interval(self):
+        _run_hook(self.stamp)
+        self.assertIn("/autotune", _run_hook(self.stamp, interval="0").stdout)
+
+    def test_corrupt_stamp_does_not_crash(self):
+        self.stamp.parent.mkdir(parents=True, exist_ok=True)
+        self.stamp.write_text("not-a-timestamp\n", encoding="utf-8")
+        self.assertIn("/autotune", _run_hook(self.stamp).stdout)
+
+
+@unittest.skipUnless(shutil.which("node"), "node not installed")
+class TestSettingsRegistration(unittest.TestCase):
+    def setUp(self):
+        self.tmp = tempfile.TemporaryDirectory()
+        self.addCleanup(self.tmp.cleanup)
+        self.settings = Path(self.tmp.name) / "settings.json"
+
+    def _patch(self) -> dict:
+        subprocess.run(
+            ["node", str(PATCHER), str(self.settings)], check=True, capture_output=True
+        )
+        return json.loads(self.settings.read_text(encoding="utf-8"))
+
+    def test_hook_registered_once(self):
+        self._patch()
+        data = self._patch()
+        entries = json.dumps(data["hooks"]["UserPromptSubmit"])
+        self.assertEqual(entries.count("autotune/hooks/reminder.sh"), 1)
+
+    def test_existing_hooks_preserved(self):
+        self.settings.write_text(
+            json.dumps(
+                {
+                    "hooks": {
+                        "UserPromptSubmit": [
+                            {"hooks": [{"type": "command", "command": "true"}]}
+                        ]
+                    }
+                }
+            ),
+            encoding="utf-8",
+        )
+        data = self._patch()
+        self.assertEqual(len(data["hooks"]["UserPromptSubmit"]), 4)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_ci_tools.py

@@ -0,0 +1,110 @@
+"""Exercise ci_failures clustering and find_fix's ref search."""
+
+from __future__ import annotations
+
+import importlib.util
+import shutil
+import subprocess
+import sys
+import tempfile
+import unittest
+from pathlib import Path
+
+REPO_ROOT = Path(__file__).resolve().parents[1]
+CI_FAILURES = REPO_ROOT / "skills" / "ci-artifacts" / "scripts" / "ci_failures.py"
+FIND_FIX = REPO_ROOT / "skills" / "merge-fix" / "scripts" / "find_fix.py"
+
+
+def _load(path: Path):
+    spec = importlib.util.spec_from_file_location(path.stem, path)
+    module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(module)
+    return module
+
+
+class TestCiFailures(unittest.TestCase):
+    def setUp(self):
+        self.ci = _load(CI_FAILURES)
+
+    def test_jobs_differing_only_in_identifiers_share_a_cluster(self):
+        one = "2026-10-30T10:00:00.1Z setup ok\n##[error]Timeout on host 10.0.0.12 after 300s\n"
+        two = "\x1b[31m2026-10-30T11:00:00.1Z ##[error]Timeout on host 10.0.0.47 after 299s\x1b[0m\n"
+        other = "PLAY RECAP failed=0\nfatal: unable to reach registry\n"
+        groups = self.ci.cluster([("a", one), ("b", two), ("c", other)])
+        self.assertEqual(list(groups.values()), [["a", "b"], ["c"]])
+
+    def test_command_echo_and_retries_are_skipped_and_task_named(self):
+        text = (
+            '##[group]Run make deploy || echo "failed"\n'
+            "make deploy\n"
+            "##[endgroup]\n"
+            "FAILED - RETRYING: wait (3 retries left)\n"
+            "TASK [web-app-y : Probe] ****\n"
+            "Traceback (most recent call last): recovered on retry\n"
+            "TASK [web-app-x : Wait for health] ****\n"
+            'fatal: [localhost]: FAILED! => {"msg": "timeout 120"}\n'
+            "##[error]Process completed with exit code 2.\n"
+        )
+        self.assertEqual(
+            self.ci.signature(text),
+            'TASK [web-app-x : Wait for health] **** fatal: [localhost]: FAILED! => {"msg": "timeout <n>"}',
+        )
+
+    def test_lint_finding_beats_make_error_and_later_steps(self):
+        text = (
+            "Ran 41 tests in 1.0s\n"
+            "OK\n"
+            "UP017 [*] Use `datetime.UTC` alias\n"
+            "  --> skills/democracy/scripts/council.py:92:40\n"
+            "Found 1 error.\n"
+            "make: *** [Makefile:15: test] Error 1\n"
+            "##[error]Process completed with exit code 2.\n"
+            "Post job cleanup.\n"
+            "SHA256 digest of uploaded artifact is 0123456789abcdef\n"
+        )
+        self.assertEqual(self.ci.signature(text), "UP<n> [*] Use `datetime.UTC` alias")
+
+    def test_generic_exit_code_line_is_not_the_signature(self):
+        text = "Error: disk full\n##[error]Process completed with exit code 1.\n"
+        self.assertEqual(self.ci.signature(text), "Error: disk full")
+
+
+@unittest.skipUnless(shutil.which("git"), "git not installed")
+class TestFindFix(unittest.TestCase):
+    def setUp(self):
+        self.tmp = tempfile.TemporaryDirectory()
+        self.addCleanup(self.tmp.cleanup)
+        self.repo = Path(self.tmp.name)
+        self.env = {
+            "PATH": "/usr/bin:/bin",
+            "HOME": str(self.repo),
+            "GIT_AUTHOR_NAME": "t",
+            "GIT_AUTHOR_EMAIL": "t@t",
+            "GIT_COMMITTER_NAME": "t",
+            "GIT_COMMITTER_EMAIL": "t@t",
+        }
+        self._git("init", "-q", "-b", "main")
+        self._git("commit", "-q", "--allow-empty", "-m", "fix: probe in head")
+        self._git("switch", "-q", "-c", "side")
+        self._git("commit", "-q", "--allow-empty", "-m", "fix: probe on side")
+        self._git("switch", "-q", "main")
+
+    def _git(self, *args: str) -> None:
+        subprocess.run(["git", *args], check=True, capture_output=True, env=self.env, cwd=self.repo)
+
+    def test_only_commits_outside_head_are_candidates(self):
+        result = subprocess.run(
+            [sys.executable, str(FIND_FIX), "--grep", "probe"],
+            capture_output=True,
+            text=True,
+            check=True,
+            env=self.env,
+            cwd=self.repo,
+        )
+        self.assertIn("hits=2 in_head=1 candidates=1", result.stdout)
+        self.assertIn("fix: probe on side", result.stdout)
+        self.assertNotIn("probe in head", result.stdout)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_council.py

@@ -0,0 +1,88 @@
+"""Exercise the democracy council script: election, staleness, release, gate."""
+
+from __future__ import annotations
+
+import json
+import subprocess
+import sys
+import tempfile
+import unittest
+from pathlib import Path
+
+REPO_ROOT = Path(__file__).resolve().parents[1]
+COUNCIL = REPO_ROOT / "skills" / "democracy" / "scripts" / "council.py"
+
+
+class TestCouncil(unittest.TestCase):
+    def setUp(self):
+        self.tmp = tempfile.TemporaryDirectory()
+        self.addCleanup(self.tmp.cleanup)
+        self.home = Path(self.tmp.name) / "home"
+        self.root = Path(self.tmp.name) / "council"
+        self.sessions = self.home / ".claude" / "sessions"
+        self.sessions.mkdir(parents=True)
+        self._live("s1", "One")
+        self._live("s2", "Two")
+
+    def _live(self, sid: str, name: str) -> None:
+        (self.sessions / f"{sid}.json").write_text(
+            json.dumps({"sessionId": sid, "name": name}), encoding="utf-8"
+        )
+
+    def _run(self, sid: str, *args: str, stdin: str = "") -> subprocess.CompletedProcess:
+        env = {
+            "PATH": "/usr/bin:/bin",
+            "HOME": str(self.home),
+            "AGENTS_COUNCIL_ROOT": str(self.root),
+            "CLAUDE_CODE_SESSION_ID": sid,
+        }
+        return subprocess.run(
+            [sys.executable, str(COUNCIL), *args],
+            capture_output=True,
+            text=True,
+            env=env,
+            input=stdin,
+            check=False,
+        )
+
+    def test_first_claim_wins_and_second_is_refused(self):
+        self.assertEqual(self._run("s1", "claim", "work/x", "--work", "w").returncode, 0)
+        second = self._run("s2", "claim", "work/x", "--work", "w")
+        self.assertEqual(second.returncode, 3)
+        self.assertIn('"session": "s1"', second.stdout)
+
+    def test_dead_holder_is_stale_and_can_be_taken_over(self):
+        self._run("s1", "claim", "work/x", "--work", "w")
+        (self.sessions / "s1.json").unlink()
+        self.assertEqual(self._run("s2", "claim", "work/x", "--work", "w").returncode, 4)
+        self.assertEqual(self._run("s2", "takeover", "work/x", "--work", "w").returncode, 0)
+        self.assertIn('"session": "s2"', (self.root / "work/x/claim.json").read_text())
+
+    def test_takeover_of_a_live_holder_is_refused(self):
+        self._run("s1", "claim", "work/x", "--work", "w")
+        self.assertEqual(self._run("s2", "takeover", "work/x", "--work", "w").returncode, 3)
+
+    def test_only_the_holder_releases(self):
+        self._run("s1", "claim", "work/x", "--work", "w")
+        self.assertEqual(self._run("s2", "release", "work/x").returncode, 3)
+        self.assertEqual(self._run("s1", "release", "work/x").returncode, 0)
+        self.assertFalse((self.root / "work/x").exists())
+
+    def test_gate_blocks_unclaimed_edits_in_a_git_worktree_only(self):
+        repo = Path(self.tmp.name) / "repo"
+        (repo / ".git").mkdir(parents=True)
+        inside = json.dumps({"session_id": "s1", "tool_input": {"file_path": str(repo / "f")}})
+        outside = json.dumps(
+            {"session_id": "s1", "tool_input": {"file_path": str(self.home / "f")}}
+        )
+        self.assertEqual(self._run("s1", "gate", stdin=inside).returncode, 2)
+        self.assertEqual(self._run("s1", "gate", stdin=outside).returncode, 0)
+        self._run("s1", "claim", "work/x", "--work", "w")
+        self.assertEqual(self._run("s1", "gate", stdin=inside).returncode, 0)
+
+    def test_invalid_office_is_a_usage_error(self):
+        self.assertEqual(self._run("s1", "claim", "../x", "--work", "w").returncode, 2)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_dream.py

@@ -0,0 +1,140 @@
+"""Validate the dream reminder hook and its settings registration."""
+
+from __future__ import annotations
+
+import json
+import shutil
+import subprocess
+import tempfile
+import unittest
+from pathlib import Path
+
+REPO_ROOT = Path(__file__).resolve().parents[1]
+SKILL = REPO_ROOT / "skills" / "dream" / "SKILL.md"
+HOOK = REPO_ROOT / "skills" / "dream" / "hooks" / "reminder.sh"
+PATCHER = REPO_ROOT / "scripts" / "enable-plugins.js"
+
+
+def _run_hook(
+    cwd: Path, stamp: Path | None = None, interval: str = "43200"
+) -> subprocess.CompletedProcess:
+    env = {
+        "PATH": "/usr/bin:/bin",
+        "HOME": str(cwd),
+        "DREAM_INTERVAL_SECONDS": interval,
+    }
+    if stamp is not None:
+        env["DREAM_STAMP"] = str(stamp)
+    return subprocess.run(
+        ["bash", str(HOOK)],
+        capture_output=True,
+        text=True,
+        check=True,
+        cwd=str(cwd),
+        env=env,
+    )
+
+
+class TestDreamSkill(unittest.TestCase):
+    def test_skill_is_trigger_only(self):
+        text = SKILL.read_text(encoding="utf-8")
+        self.assertIn("name: dream", text)
+        self.assertIn("multiSelect: false", text)
+
+
+class TestDreamHook(unittest.TestCase):
+    def setUp(self):
+        self.tmp = tempfile.TemporaryDirectory()
+        self.addCleanup(self.tmp.cleanup)
+        self.cwd = Path(self.tmp.name)
+        self.stamp = self.cwd / ".claude" / ".dream-stamp"
+
+    def test_first_run_hints_and_stamps(self):
+        result = _run_hook(self.cwd, self.stamp)
+        self.assertIn("/dream", result.stdout)
+        self.assertTrue(self.stamp.is_file())
+
+    def test_second_run_is_silent_within_interval(self):
+        _run_hook(self.cwd, self.stamp)
+        self.assertEqual(_run_hook(self.cwd, self.stamp).stdout, "")
+
+    def test_hint_returns_after_the_interval(self):
+        _run_hook(self.cwd, self.stamp)
+        self.assertIn("/dream", _run_hook(self.cwd, self.stamp, interval="0").stdout)
+
+    def test_corrupt_stamp_does_not_crash(self):
+        self.stamp.parent.mkdir(parents=True, exist_ok=True)
+        self.stamp.write_text("not-a-timestamp\n", encoding="utf-8")
+        self.assertIn("/dream", _run_hook(self.cwd, self.stamp).stdout)
+
+    def test_outside_a_repository_it_stays_silent(self):
+        self.assertEqual(_run_hook(self.cwd).stdout, "")
+
+    @unittest.skipUnless(shutil.which("git"), "git not installed")
+    def test_stamp_is_per_repository(self):
+        for name in ("one", "two"):
+            repo = self.cwd / name
+            repo.mkdir()
+            subprocess.run(
+                ["git", "init", "-q", str(repo)], check=True, capture_output=True
+            )
+            self.assertIn("/dream", _run_hook(repo).stdout)
+            self.assertTrue((repo / ".git" / ".dream-stamp").is_file())
+            self.assertEqual(_run_hook(repo).stdout, "")
+
+    @unittest.skipUnless(shutil.which("git"), "git not installed")
+    def test_linked_worktrees_share_the_stamp(self):
+        repo = self.cwd / "main"
+        tree = self.cwd / "tree"
+        env = {
+            "PATH": "/usr/bin:/bin",
+            "HOME": str(self.cwd),
+            "GIT_AUTHOR_NAME": "t",
+            "GIT_AUTHOR_EMAIL": "t@t",
+            "GIT_COMMITTER_NAME": "t",
+            "GIT_COMMITTER_EMAIL": "t@t",
+        }
+        repo.mkdir()
+        for args in (
+            ["init", "-q"],
+            ["commit", "-q", "--allow-empty", "-m", "init"],
+            ["worktree", "add", "-q", str(tree)],
+        ):
+            subprocess.run(
+                ["git", *args], check=True, capture_output=True, env=env, cwd=str(repo)
+            )
+        self.assertIn("/dream", _run_hook(repo).stdout)
+        self.assertEqual(_run_hook(tree).stdout, "")
+
+
+@unittest.skipUnless(shutil.which("node"), "node not installed")
+class TestSettingsRegistration(unittest.TestCase):
+    def setUp(self):
+        self.tmp = tempfile.TemporaryDirectory()
+        self.addCleanup(self.tmp.cleanup)
+        self.settings = Path(self.tmp.name) / "settings.json"
+
+    def _patch(self) -> dict:
+        subprocess.run(
+            ["node", str(PATCHER), str(self.settings)], check=True, capture_output=True
+        )
+        return json.loads(self.settings.read_text(encoding="utf-8"))
+
+    def test_hook_registered_once(self):
+        self._patch()
+        data = self._patch()
+        entries = json.dumps(data["hooks"]["UserPromptSubmit"])
+        self.assertEqual(entries.count("dream/hooks/reminder.sh"), 1)
+        self.assertEqual(entries.count("autotune/hooks/reminder.sh"), 1)
+        gate = json.dumps(data["hooks"]["PreToolUse"])
+        self.assertEqual(gate.count("democracy/scripts/council.py"), 1)
+        self.assertEqual(gate.count("democracy/scripts/watch.py"), 1)
+        self.assertEqual(entries.count("democracy/scripts/watch.py"), 1)
+        post = json.dumps(data["hooks"]["PostToolUse"])
+        self.assertEqual(post.count("democracy/scripts/watch.py"), 1)
+        self.assertEqual(gate.count("subagent-model/scripts/log.py"), 1)
+        self.assertEqual(post.count("subagent-model/scripts/log.py"), 1)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_lock.py

@@ -12,6 +12,8 @@ LOCK_FILE = REPO_ROOT / "skills-lock.json"
 
 HASH_RE = re.compile(r"^[0-9a-f]{64}$")
 REQUIRED_FIELDS = ("source", "sourceType", "skillPath", "computedHash")
+DESCRIPTION_WORDS = 40
+LISTING_WORDS = 1300
 
 
 class TestSkillsLock(unittest.TestCase):
@@ -61,6 +63,16 @@ class TestSkillsLock(unittest.TestCase):
                     "description:", frontmatter, "frontmatter missing description"
                 )
 
+    def test_descriptions_fit_the_listing_budget(self):
+        total = 0
+        for skill_md in sorted((REPO_ROOT / "skills").glob("*/SKILL.md")):
+            frontmatter = skill_md.read_text(encoding="utf-8").split("---", 2)[1]
+            words = len(frontmatter.split("description:", 1)[1].split()) - 1
+            total += words
+            with self.subTest(skill=skill_md.parent.name):
+                self.assertLessEqual(words, DESCRIPTION_WORDS)
+        self.assertLessEqual(total, LISTING_WORDS)
+
     def test_first_party_skills_do_not_shadow_locked_skills(self):
         locked = set(self.lock["skills"].keys())
         for skill_dir in sorted((REPO_ROOT / "skills").glob("*/")):

tests/test_optimize.py

@@ -0,0 +1,31 @@
+"""The self-improving skills must share the objective held by autotune."""
+
+from __future__ import annotations
+
+import unittest
+from pathlib import Path
+
+REPO_ROOT = Path(__file__).resolve().parents[1]
+SKILLS = REPO_ROOT / "skills"
+ROUTERS = ("autoskill", "confidence")
+
+
+class TestOptimizeObjective(unittest.TestCase):
+    def test_autotune_names_the_three_axes(self):
+        text = (SKILLS / "autotune" / "SKILL.md").read_text(encoding="utf-8")
+        self.assertIn("## Objective", text)
+        for axis in ("**Tokens**", "**Time**", "**Quality**"):
+            self.assertIn(axis, text)
+
+    def test_routers_point_at_it(self):
+        for skill in ROUTERS:
+            text = (SKILLS / skill / "SKILL.md").read_text(encoding="utf-8")
+            self.assertIn(
+                "`autotune` skill's **Objective**",
+                text,
+                f"{skill} does not route to the autotune objective",
+            )
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_subagent_model.py

@@ -0,0 +1,107 @@
+"""Exercise the subagent-model log: spawn hook, feedback, sandbox persist, report."""
+
+from __future__ import annotations
+
+import json
+import subprocess
+import sys
+import tempfile
+import unittest
+from pathlib import Path
+
+REPO_ROOT = Path(__file__).resolve().parents[1]
+LOG_PY = REPO_ROOT / "skills" / "subagent-model" / "scripts" / "log.py"
+
+
+class TestSubagentModelLog(unittest.TestCase):
+    def setUp(self):
+        self.tmp = tempfile.TemporaryDirectory()
+        self.addCleanup(self.tmp.cleanup)
+        self.base = Path(self.tmp.name)
+        self.log = self.base / "state" / "subagent-model.jsonl"
+
+    def _run(self, *args: str, stdin: str = "", log: Path | None = None) -> subprocess.CompletedProcess:
+        env = {"SUBAGENT_MODEL_LOG": str(log or self.log), "CLAUDE_CODE_SESSION_ID": "s1"}
+        return subprocess.run(
+            [sys.executable, str(LOG_PY), *args], capture_output=True, text=True, env=env, input=stdin, check=False
+        )
+
+    def _spawn(self, description: str, prompt: str, **tool: str) -> None:
+        payload = {"session_id": "s1", "tool_input": {"description": description, "prompt": prompt, **tool}}
+        self.assertEqual(self._run("spawn", stdin=json.dumps(payload)).returncode, 0)
+
+    def _feedback(self, description: str, completed: str = "yes", redo: str = "no", tests: str = "none") -> None:
+        result = self._run(
+            "feedback", "--description", description, "--completed", completed, "--tests", tests, "--redo", redo
+        )
+        self.assertEqual(result.returncode, 0, result.stderr)
+
+    def _lines(self) -> list[dict]:
+        return [json.loads(text) for text in self.log.read_text(encoding="utf-8").splitlines()]
+
+    def _report(self) -> dict[str, list[str]]:
+        rows = self._run("report").stdout.splitlines()[1:]
+        return {row.split("\t")[0]: row.split("\t") for row in rows}
+
+    def test_spawn_logs_class_model_and_effort_or_the_defaults(self):
+        self._spawn("find callers", "task-class: lookup\nFind every caller.", model="haiku", effort="low")
+        self._spawn("fix it", "Find the root cause.")
+        first, second = self._lines()
+        self.assertEqual((first["task_class"], first["model"], first["effort"]), ("lookup", "haiku", "low"))
+        self.assertEqual((second["task_class"], second["model"], second["effort"]), ("unclassified", "default", "default"))
+
+    def _pending_feedback(self) -> str:
+        blocked = self.base / "file"
+        blocked.write_text("", encoding="utf-8")
+        result = self._run(
+            "feedback", "--description", "d", "--completed", "yes", "--tests", "none", "--redo", "no",
+            log=blocked / "log.jsonl",
+        )
+        self.assertTrue(result.stdout.startswith("pending: "), result.stdout)
+        return result.stdout
+
+    def _persist(self, command: str, stdout: str, session: str = "s1") -> None:
+        payload = {"session_id": session, "tool_input": {"command": command}, "tool_response": {"stdout": stdout}}
+        self.assertEqual(self._run("persist", stdin=json.dumps(payload)).returncode, 0)
+
+    def test_sandboxed_feedback_is_printed_and_stored_by_the_persist_hook(self):
+        stdout = self._pending_feedback()
+        self._persist("python3 /x/skills/subagent-model/scripts/log.py feedback --description 'd'", stdout)
+        self.assertEqual(self._lines()[0]["kind"], "feedback")
+
+    def test_persist_rejects_pending_lines_it_did_not_get_from_a_bare_log_call(self):
+        stdout = self._pending_feedback()
+        line = json.loads(stdout[len("pending: "):])
+        call = "/x/skills/subagent-model/scripts/log.py feedback --description d"
+        for command, output, session in (
+            ("cat ci.log", stdout, "s1"),
+            (f"{call}; cat ci.log", stdout, "s1"),
+            (f"{call} | tee /tmp/x", stdout, "s1"),
+            (f"echo $({call})", stdout, "s1"),
+            (call, stdout, "other-session"),
+            (call, stdout + stdout, "s1"),
+            (call, "pending: " + json.dumps({**line, "extra": 1}), "s1"),
+            (call, "pending: " + json.dumps({**line, "completed": "yes"}), "s1"),
+            ("/x/skills/subagent-model/scripts/log.py followup --description d", stdout, "s1"),
+        ):
+            self._persist(command, output, session)
+        self.assertFalse(self.log.exists())
+
+    def test_report_qualifies_a_row_only_at_ninety_percent_over_twenty_rated_runs(self):
+        for i in range(20):
+            self._spawn(f"q{i}", "task-class: lookup", model="haiku", effort="low")
+            self._feedback(f"q{i}", redo="yes" if i < 2 else "no")
+        for i in range(19):
+            self._spawn(f"r{i}", "task-class: mechanical-edit", model="haiku", effort="low")
+            self._feedback(f"r{i}")
+        self._run("followup", "--description", "q5", "--text", "that list missed a caller")
+        report = self._report()
+        self.assertEqual(report["lookup"][3:], ["20", "20", "17", "85%", "no"])
+        self.assertEqual(report["mechanical-edit"][3:], ["19", "19", "19", "100%", "no"])
+        self._spawn("r19", "task-class: mechanical-edit", model="haiku", effort="low")
+        self._feedback("r19")
+        self.assertEqual(self._report()["mechanical-edit"][-1], "yes")
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_update.py

@@ -0,0 +1,46 @@
+"""update.sh must reach every locked source and install for Claude Code only."""
+
+from __future__ import annotations
+
+import json
+import shutil
+import subprocess
+import tempfile
+import unittest
+from pathlib import Path
+
+REPO_ROOT = Path(__file__).resolve().parents[1]
+UPDATE = REPO_ROOT / "scripts" / "update.sh"
+
+
+@unittest.skipUnless(shutil.which("jq") and shutil.which("bash"), "jq or bash missing")
+class TestUpdate(unittest.TestCase):
+    def setUp(self):
+        self.tmp = tempfile.TemporaryDirectory()
+        self.addCleanup(self.tmp.cleanup)
+        self.bin = Path(self.tmp.name)
+        self.log = self.bin / "calls.log"
+        npx = self.bin / "npx"
+        npx.write_text(f'#!/bin/sh\ncat >/dev/null\necho "$@" >> "{self.log}"\n', encoding="utf-8")
+        npx.chmod(0o755)
+        for tool in ("jq", "sort"):
+            (self.bin / tool).symlink_to(shutil.which(tool))
+
+    def test_every_source_is_updated_for_claude_code_only(self):
+        lock = json.loads((REPO_ROOT / "skills-lock.json").read_text(encoding="utf-8"))
+        sources = sorted({entry["source"] for entry in lock["skills"].values()})
+        subprocess.run(
+            ["bash", str(UPDATE)],
+            check=True,
+            capture_output=True,
+            env={"PATH": f"{self.bin}:/usr/bin:/bin"},
+            stdin=subprocess.DEVNULL,
+        )
+        calls = self.log.read_text(encoding="utf-8").splitlines()
+        self.assertEqual([c.split()[-1] for c in calls], sources)
+        for call in calls:
+            self.assertIn("--agent claude-code", call)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_watch.py

@@ -0,0 +1,202 @@
+"""Exercise the democracy resource watch: stages, projection, block, admit, alerts, caches."""
+
+from __future__ import annotations
+
+import importlib.util
+import json
+import os
+import subprocess
+import sys
+import tempfile
+import time
+import unittest
+from pathlib import Path
+
+REPO_ROOT = Path(__file__).resolve().parents[1]
+WATCH = REPO_ROOT / "skills" / "democracy" / "scripts" / "watch.py"
+LIMITS = {"warn": 40, "stop": 15, "critical": 12}
+
+
+def _load():
+    spec = importlib.util.spec_from_file_location("watch", WATCH)
+    module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(module)
+    return module
+
+
+class TestStage(unittest.TestCase):
+    def setUp(self):
+        self.watch = _load()
+        self.cfg = {"thresholds_gb": LIMITS, "projection_minutes": 30}
+
+    def test_thresholds(self):
+        now = time.time()
+        for free, stage in ((50, "ok"), (30, "warn"), (14, "stop"), (5, "critical")):
+            self.assertEqual(self.watch.stage_for(free, [], self.cfg, now), stage)
+
+    def test_cpu_and_ram_percentages(self):
+        self.assertEqual(self.watch.cpu_busy_percent((100, 40), (200, 60)), 80.0)
+        meminfo = "MemTotal:       1000 kB\nMemFree:  100 kB\nMemAvailable:    250 kB\n"
+        self.assertEqual(self.watch.mem_used_percent(meminfo), 75.0)
+
+    def test_fast_fall_escalates_one_stage(self):
+        now = time.time()
+        self.assertEqual(self.watch.stage_for(32, [[now - 600, 48]], self.cfg, now), "stop")
+        self.assertEqual(self.watch.stage_for(32, [[now - 600, 32.1]], self.cfg, now), "warn")
+
+
+class TestWatchCommands(unittest.TestCase):
+    def setUp(self):
+        self.tmp = tempfile.TemporaryDirectory()
+        self.addCleanup(self.tmp.cleanup)
+        self.base = Path(self.tmp.name)
+        self.root = self.base / "council"
+        self.config = self.base / "config.json"
+        self.cache = self.base / "cache"
+        self.cache.mkdir()
+        self.cfg = {
+            "disk": str(self.base),
+            "thresholds_gb": LIMITS,
+            "projection_minutes": 30,
+            "interval_seconds": 0,
+            "cache_interval_seconds": 86400,
+            "heavy_commands": ["^make compose-deploy", "^make swarm-"],
+            "never_block": ["^make swarm-down"],
+            "cleanup": [],
+            "worktree_cleanup": [],
+            "worktrees_command": "true",
+            "worktree_marker": "Makefile",
+            "busy_processes": ["sleep"],
+            "cache_dirs": [str(self.cache)],
+            "cache_budget_percent": 3,
+            "slot_need_gb": {"swarm": 30, "test": 0.001},
+            "notify": ["true"],
+            "load_limits": {"cpu_percent": 101, "mem_percent": 101, "sample_seconds": 0.1, "kinds": ["test"]},
+        }
+        self._write_config()
+
+    def _write_config(self):
+        self.config.write_text(json.dumps(self.cfg), encoding="utf-8")
+
+    def _run(self, *args: str, stdin: str = "") -> subprocess.CompletedProcess:
+        env = {
+            "PATH": str(self.base),
+            "HOME": str(self.base),
+            "AGENTS_COUNCIL_ROOT": str(self.root),
+            "AGENTS_COUNCIL_CONFIG": str(self.config),
+        }
+        return subprocess.run(
+            [sys.executable, str(WATCH), *args],
+            capture_output=True, text=True, env=env, input=stdin, check=False,
+        )
+
+    def _stage(self, stage: str) -> None:
+        self.root.mkdir(exist_ok=True)
+        (self.root / "watch.json").write_text(json.dumps({"stage": stage}), encoding="utf-8")
+
+    def _bash(self, command: str) -> str:
+        return json.dumps({"tool_input": {"command": command}})
+
+    def test_block_only_heavy_jobs_at_stop_and_never_teardown(self):
+        self._stage("stop")
+        self.assertEqual(self._run("block", stdin=self._bash("make compose-deploy apps=x")).returncode, 2)
+        self.assertEqual(self._run("block", stdin=self._bash("make swarm-down")).returncode, 0)
+        self.assertEqual(self._run("block", stdin=self._bash("ls")).returncode, 0)
+        self._stage("warn")
+        self.assertEqual(self._run("block", stdin=self._bash("make compose-deploy")).returncode, 0)
+
+    def test_block_ignores_heavy_words_inside_quotes_and_heredocs(self):
+        self.cfg["heavy_commands"] = [r"\bmake\s+(-C\s+\S+\s+)?(compose-deploy|test|swarm-\S+)(\s|$)"]
+        self._write_config()
+        self._stage("stop")
+        message = "$(cat <<'EOF'\nfix: run \"make test\" and make swarm-zombie\nEOF\n)"
+        for command in (
+            'git commit --no-verify -m "fix: passes the vars to make swarm-zombie app=x"',
+            "grep -n 'make test' Makefile",
+            f'git commit --no-verify -m "{message}"',
+        ):
+            self.assertEqual(self._run("block", stdin=self._bash(command)).returncode, 0, command)
+        for command in (
+            "make -C x swarm-zombie app=y",
+            "env FOO=1 make swarm-zombie",
+            'make compose-deploy apps="web-app-x"',
+        ):
+            self.assertEqual(self._run("block", stdin=self._bash(command)).returncode, 2, command)
+
+    def test_admit_keeps_the_stop_floor(self):
+        self.cfg["thresholds_gb"] = {"warn": 0, "stop": 0, "critical": 0}
+        self._write_config()
+        self.assertEqual(self._run("admit", "--need-gb", "0.001").returncode, 0)
+        self.assertEqual(self._run("admit", "--need-gb", "1e9").returncode, 3)
+
+    def test_admit_for_a_load_kind_also_needs_cpu_and_ram_below_the_limits(self):
+        self.cfg["thresholds_gb"] = {"warn": 0, "stop": 0, "critical": 0}
+        self._write_config()
+        self.assertEqual(self._run("admit", "--kind", "test").returncode, 0)
+        self.cfg["load_limits"]["cpu_percent"] = 0
+        self._write_config()
+        denied = self._run("admit", "--kind", "test")
+        self.assertEqual(denied.returncode, 3)
+        self.assertIn("cpu", denied.stdout)
+        self.assertEqual(self._run("admit", "--need-gb", "0.001").returncode, 0)
+
+    def test_warn_alert_reaches_each_session_once(self):
+        self.cfg["thresholds_gb"] = {"warn": 1e9, "stop": -1, "critical": -2}
+        self._write_config()
+
+        def hook(session: str) -> str:
+            payload = {"session_id": session, "hook_event_name": "UserPromptSubmit"}
+            return self._run("watch", stdin=json.dumps(payload)).stdout
+
+        self.assertIn("RESOURCE WARN", hook("s1"))
+        self.assertEqual(hook("s1"), "")
+        self.assertIn("RESOURCE WARN", hook("s2"))
+
+    def test_cache_trim_evicts_least_recently_used_first(self):
+        old, new = self.cache / "old", self.cache / "new"
+        old.write_bytes(b"x" * 4096)
+        new.write_bytes(b"y" * 4096)
+        os.utime(old, (1_000_000, 1_000_000))
+        os.utime(new, (2_000_000, 2_000_000))
+        st = os.statvfs(self.base)
+        self.cfg["cache_budget_percent"] = (4096 + 100) / (st.f_blocks * st.f_frsize) * 100
+        self._write_config()
+        self.assertEqual(self._run("cleanup", "--caches").returncode, 0)
+        self.assertFalse(old.exists())
+        self.assertTrue(new.exists())
+
+    def test_full_cleanup_reaches_only_marked_running_worktrees(self):
+        marked, foreign = self.base / "marked", self.base / "foreign"
+        for tree in (marked, foreign):
+            tree.mkdir()
+        (marked / "Makefile").write_text("", encoding="utf-8")
+        self.cfg["worktrees_command"] = f"echo {marked}; echo {foreign}; echo {marked}"
+        self.cfg["worktree_cleanup"] = ["echo x >> {worktree}/cleaned"]
+        self._write_config()
+        self.assertEqual(self._run("cleanup", "--full").returncode, 0)
+        self.assertEqual((marked / "cleaned").read_text(encoding="utf-8"), "x\n")
+        self.assertFalse((foreign / "cleaned").exists())
+
+    def test_full_cleanup_skips_a_worktree_where_a_busy_process_runs(self):
+        idle, gated = self.base / "idle", self.base / "gated"
+        for tree in (idle, gated):
+            (tree / "sub").mkdir(parents=True)
+            (tree / "Makefile").write_text("", encoding="utf-8")
+        gate = subprocess.Popen(["sleep", "60"], cwd=gated / "sub")
+        self.addCleanup(gate.wait)
+        self.addCleanup(gate.kill)
+        self.cfg["worktrees_command"] = f"echo {idle}; echo {gated}"
+        self.cfg["worktree_cleanup"] = ["echo x >> {worktree}/cleaned"]
+        self._write_config()
+        self.assertEqual(self._run("cleanup", "--full").returncode, 0)
+        self.assertTrue((idle / "cleaned").exists())
+        self.assertFalse((gated / "cleaned").exists())
+
+    def test_without_config_every_command_is_a_no_op(self):
+        self.config.unlink()
+        result = self._run("status")
+        self.assertEqual((result.returncode, result.stdout), (0, ""))
+
+
+if __name__ == "__main__":
+    unittest.main()