kvb-org-operator collects the steps that wait on a human across all agents: commands under a deny or unconfirmed ask rule, anything outside the sandbox (keys, permission settings, foreign hosts, root), steps the agent rules reserve for the operator (push, release, tags, reboot) and human-bound ones (hardware key, login, second factor, purchase, decision). Sources are the own session, the kvb-org-rasci register and one message per live peer. Done steps drop out, duplicates merge, the rest is ordered by dependency and printed as a table plus one copyable bash block, then recorded as operator/<slug> register tasks. Agents never run a listed command or hand it to a peer. Operator order 2026-11-03; four descriptions trimmed for the listing budget.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
kvb-skill-compile finds the steps of a skill whose result follows from its inputs alone (fixed command sequences, parsing, counting, thresholds, format checks, bookkeeping) and turns them into tested scripts in the repository that owns the skill: skills/<skill>/scripts/ with a test under tests/ in the skills repository, that repository's own convention elsewhere, and an upstream proposal for third-party skills. The prose shrinks to the call. Wired into kvb-skill-tune (finding and shape option), kvb-skill-dream step 7, kvb-skill-auto, kvb-skill-transcend and kvb-skill-essence. Four descriptions are trimmed to stay inside the 1300-word listing budget.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
kvb-skills-dream, -tune, -auto, -essence and -transcend become kvb-skill-*, and tests/test_naming.py now requires the category skill. enable-plugins.js registers the reminder hooks under the new names and repoints hook commands of the previous kvb-skills-* paths as well as the older autotune/dream paths; test_dream covers both generations. References in kvb-check-confidence, kvb-org-perform, kvb-org-rasci, kvb-transcend, the tests and the README organigram and skill map follow. The header comments of both reminder hooks and enable-plugins.js are dropped.
BREAKING CHANGE: /kvb-skills-dream, /kvb-skills-tune, /kvb-skills-auto, /kvb-skills-essence and /kvb-skills-transcend are now /kvb-skill-*.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
kvb-create-requirement asks for the context, runs kvb-think-listen and kvb-think-brainstorm, then drafts one requirement with a user story, operator-confirmed decisions, a Mermaid approach flowchart with emoji phases, a test loop and an operator feedback checkpoint per stage, checkbox acceptance criteria grouped by area, and a Tests group with unit, integration and e2e (n/a with a reason). It writes only on the operator's Write it and stops with an offer to hand over to kvb-create-plan. kvb-think-brainstorm generates options through seven fixed lenses, scores them on value, effort and risk, and hands the best two or three over. kvb-create-feature becomes kvb-think-gaps: it still finds and ranks missing work but delegates every pick to kvb-create-requirement, so the requirement template lives in one place. Operator order 2026-11-03.
BREAKING CHANGE: /kvb-create-feature is now /kvb-think-gaps.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Adds kvb-transcend (collector), kvb-skills-transcend (into the skills repo) and kvb-code-transcend (into the current repo). transcend.py scans the own scratchpad, peer scratchpads and the agent homes for scripts, tests and skills the skills repo does not ship, skips secret-named and oversized files, and remembers carried/dropped decisions by content digest in the gitignored .state/transcend.json, so a rescan offers only new or changed candidates. Wired into kvb-skills-tune (own scripts), kvb-code-tune step 6 (measurements) and kvb-skills-dream step 7. Seven descriptions are tightened to stay inside the 1300-word listing budget.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The operator dropped the conversation shortcuts (sobu, soco, socobu, socon, sona, sote) as unnecessary. Deletes the skill and tests/test_shortcuts.py, drops the tokens from the kvb-code-no-comments triggers, the shortcut branch from kvb-skills-auto step 3, the shortcuts row option from kvb-skills-tune, and the nodes and edge from the README organigram and skill map.
BREAKING CHANGE: the shortcut tokens no longer expand; use /kvb-git-commit-next and /kvb-git-commit-no-verify.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
kvb-git-commit-no-verify gains a step between the audits and git commit: the message right before the commit call names the worktree's absolute path, the branch, the fix confidence (kvb-check-confidence) and the break risk (kvb-check-break-risk). kvb-git-commit-next names the block in its hand-over step. Operator order 2026-11-03, after a commit in the #1324 worktree was rejected for omitting the path. Also replaces the stale advocate name with kvb-check-legal.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Operator rule: a hotfix gate (a branch from the default branch that fixes it) takes the next free gate or test slot before every other line; everything else keeps its WSJF rank, and a running gate is never cut short for a hotfix. Written into the chair's queue in kvb-org-organize and the grant step of kvb-org-wsjf.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
kvb-cleanup asks every peer to report and remove its own unused worktrees and volumes, inventories each worktree's size, dirty state, push state and whether its HEAD is already in an integration line, ranks such clean worktrees as medium risk, and removes slot worktrees through the teardown target and sidetrees through git worktree remove without --force. kvb-git-branch-gc runs its dry run with pkgmgr branch gc --sizes --min-age 24 --merged-into <line> and shows Merged into and Size.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
kvb-org-wsjf: the chair asks its subordinates for Fibonacci estimates of business value and complexity, rasci.py estimate records them per party, and WSJF = median value / median complexity ranks the tasks. rasci.py wsjf prints the WSJF table with OKR and the task id; the register's show takes its Prio from that rank (an operator --prio pin first) and adds a WSJF column. Four descriptions were tightened to keep the listing budget.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
rasci.py keeps the organisation's tasks in <council root>/rasci.json: RASCI roles, objective with key results, priority, worker, start, end, workdir, branch, tools and artifacts; done is refused while a key result is open. council.py writes every claim, takeover and release through, and show lists the live claims as one row per task with R, A, S, C and I columns. kvb-org-artefacts manages the artifacts in the same table for kvb-cleanup. The org, plan, triage, tune, cleanup, branch-gc and dream skills now record into and read from the register; five descriptions were tightened to keep the listing budget.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
All 38 first-party skills move to kvb-<category>-<name> with the categories think, create, code, ci, git, check, org and skills; kvb-cleanup and kvb-help are the only uncategorized names. tests/test_naming.py pins the schema, the Agent Skills name rules and the README organigram. enable-plugins.js repoints hook commands of renamed skills in settings.local.json so a stale script path cannot block tools.
BREAKING CHANGE: the old skill names and slash commands (/commit-next, /dream, /autotune, ...) are gone; use their kvb- successors listed in the README organigram.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Every run now examines each measured hot path for the most efficient language and framework fit and for unnecessary recursion, and reports the result even when clean. Framework overhead joins the language section; changes stay bound to the session's limits.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Before investigating or implementing a cost cluster (one step, hot path or
repeated call, named by its log line and number), tune now runs the
coordinate skill and asks every other agent session on the machine whether
the cluster is already identified. The earliest claim that carries the
measurement works it; the others hand over their findings and move on, so
no cluster gets two competing optimizations. A claim ends with a result, a
proposal, an abandoned attempt or an operator reassignment.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Every cluster's failing run is also a timing sample. New step 9 hands one job log per cluster to the tune skill: the job of the cluster that ran furthest, because its timings cover the most phases. Tune works under its own rules and the session's limits, and its candidates run through funnels of their own, separate from the cluster's fix sidetree, so they never delay or block the fix. A log the failure cut short is tuned for the phases it covers, naming those it does not reach. "Follow the run" becomes step 10; observe's reference to step 1 is unchanged.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A portable tuner: nothing that reduces logic, coverage or correctness counts as a speed-up. Once per session it asks through active-listening, as checklists, what to examine, which performance boundaries hold and which limits apply to optimizations, and works only inside the answers. It measures from logs (profile_tasks durations sit under the next task's header, BuildKit steps pair by number), ranks candidates by fixed cost times count, discards invalid comparisons (shared machine, differing cache state checked by instruction text and base digest, one-time costs, fresh versus update passes), and searches every branch before optimizing. A change of language, such as a Python hot path in Rust, is considered only for measured CPU-bound work, counted at its full toolchain and shipping cost, and applied only where the session's limits allow new languages. Every optimization runs through the funnel skill and is hardened with dialectic.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Each failure cluster is first coordinated with the agents on related branches through the coordinate skill, so a fix that already exists elsewhere is taken instead of duplicated. Every claimed cluster then goes to the funnel skill: one agent in its own worktree, branched from the exact current HEAD, with that cluster as its only concern, the cluster's artifact paths in its brief and a hard time cap. Dialectic, the shared-versus-hidden split and the fix run inside that sidetree. A fix reaches the main line only at 90 % fix confidence and under 5 % break risk after independent review; below that the cluster ends as a proposal. The per-job verdict now names the sidetree branch and the funnel verdict. Steps are renumbered; observe's reference to step 1 is unchanged.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Every delegated change works in its own worktree, branched from an exact commit with a hard time cap, and enters the main line only at 90 % fix confidence and under 5 % break risk, after tests, a negative control and an independent dialectic review. When that bar is realistically out of reach, the agent submits a proposal with the evidence that would close the gap instead of a merge.
After the merge the sidetree is torn down in a fixed order: its jobs, its stacks with volumes, the files its containers left (counted before the worktree removal, which otherwise fails halfway after git dropped the registration), the worktree by name without a broad prune, the merged branch (a remote branch only once its commits are reachable from a pushed one), its reservations and claims, and its temporary files.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Two agents fixing the same failure on two branches cost a duplicate investigation and then a merge conflict between two fixes, and a fix nobody hears about gets triaged again. The skill maps the branches this one inherits from or passes its commits to, asks their agents before fixing whether the failure is known or fixed, claims the fix only when nobody does or hands it to the line where the cause lives, and reports the commit and its evidence afterwards. Silence is never agreement, and a peer is never asked to run what this session is denied.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The infinito-nexus 16.0.0 message used "-" bullets on top of a
CHANGELOG.md whose older entries used "*". The standalone lint passed,
but MD004's default "consistent" style takes the marker of the first
list in the file, so the repository's own markdown lint reported every
older list and the pre-push gate refused the push.
The message now takes the marker the target CHANGELOG.md already uses,
and step 4 also lints a copy of CHANGELOG.md with the entry inserted,
since rules like MD004 and MD024 only fire across the whole file. Both
lint runs pass --no-globs so a config with its own globs does not lint
the whole tree as well.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
archify (tt-a1i/archify) joins the locked skills. The computed hashes of
the seven caveman and six ponytail skills move to their current upstream
content.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
