Match now builds asks, choices, decision rows and rule requests from the inbox items, beside commits and commands, so its card count follows the Tasks badge. A decision card shows its options with the recommended one marked; a pick is released with the same single passkey, and the hub posts the answer of a decision row to the row's agent itself and keeps the row off the stack until its question changes. A choice cannot be rejected; a rule card's accept opens its row, its reject carries the feedback. Every card shows the scores its text carries as labels, value included; outside a commit's score line only an emoji-led score counts. Answered decision rows leave the badge and show as answered in the inbox. Requirement 012 records the operator's amendment of 2026-11-19 and decision 11.
🎯 Fix: 92 %
💥 Break: 4 %
💸 Tokens: –
⏱️ Velocity: –
🛡️ Security: 100 %
🏆 Score: 88
🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 %
Created-with: https://s.veen.world/skills
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
test_english flagged a quoted German operator pick in requirement 021 and the umlaut in the gibberlink width probe; the doc now says it in English and the probe spells the same character as a named escape. kvb-git-hotfix SKILL.md went to 603 words with the trailer rule; the sync paragraph is tightened back under the 600-word cap, which also clears the budget test.
🎯 Fix: 97 %
💥 Break: 1 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 96
🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 %
Created-with: https://s.veen.world/skills
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Regenerate patches/tokeneconomizer.patch from the published fix branch (microsoft/TokenEconomizer#261, fixes#260): the background te starts as python -E -s -X utf8 -c with the plugin dir first on sys.path, the aider probe runs in an empty temp dir, and temp and settings files open with O_NOFOLLOW. Requirement 021 decision 9 and its acceptance criteria now name the issue, the PR and the rejected PYTHONSAFEPATH.
🎯 Fix: 95 %
💥 Break: 2 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 93
🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 %
Created-with: https://s.veen.world/skills
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A Direct/Select switch in the header (ids grant-direct, grant-select; ViewStore approval.mode) decides whether a grant button acts at once or adds its item to a selection that a tray grants under one passkey signature; rules and red gates still act at once. The review sheet shows every file in one scrolling stack whose next file opens as the previous one ends (openOnScroll moves to page-diff.js and serves Match too). The grant bar boots before the header is measured, so --head counts it. The inbox denial sheet takes an optional reason for every requester; it shares page-inbox.js hunks with the selection code, so both land in this one commit.
Fix stays below 90: the header ids and the measure order fix e2e failures of the aborted final run of 2026-11-17 that the master gate has not rerun yet. Accepted MEDUSA false positives (security.py accept after kvb-think-criticize, 2026-11-17): page-inbox.js PQC007 EXA010; page-match.js EXA010.
🎯 Fix: 85 %
💥 Break: 5 %
💸 Tokens: –
⏱️ Velocity: –
🛡️ Security: 100 %
🏆 Score: 81
🚦 Gate: ⛔ fix 85 % < 90
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
staged_diff masks only the secret rule hits and seals each masked file's clear patch apart; reviews and asks store the sealed patches next to their diff, delete them once the item leaves pending, and the hub sweeps orphans. POST /api/diffs/<kind>/<id>/reveal/sign and /reveal hand the clear patches to a signed request; page-diff.js offers Reveal per hidden file and Reveal all, keeps the clear text in the page only and forgets it once the item leaves the inbox. Requirement 019, unit, hub and e2e tests.
Accepted MEDUSA false positives (security.py accept after kvb-think-criticize, 2026-11-17): approval.py FTSCAN-231 WEB-SSRF RH005; permission_hook.py MM-SCAN-058 WEB-SSRF RH005; staged_diff.py SAST-ENV-001 AI-BACKDOOR-006 B603; hub.py MEX-SCAN-1167 INF-SCAN-589; page-load.js EXA002; hub_case.py TC001-TC009 INF-SCAN-2057/2206/2440/2457 EXA002 EXA006 PL002 B603 FTSC-SCAN-089.
🎯 Fix: 92 %
💥 Break: 4 %
💸 Tokens: –
⏱️ Velocity: –
🛡️ Security: 100 %
🏆 Score: 88
🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
make install clones microsoft/TokenEconomizer at the commit in plugins-lock.json, applies patches/tokeneconomizer.patch (child CLI under PYTHONSAFEPATH, temp files opened with O_EXCL|O_NOFOLLOW; upstream issue microsoft/TokenEconomizer#260), installs the plugin for Claude Code and, with codex on the PATH, for Codex, and sets toolprune=propose with a protect list and microskills=envfacts globally. A dirty clone stays untouched and fails the install; a host without git or python3 skips the step. Requirement 021, README and six install tests; the council-root install test stubs the step.
🎯 Fix: 91 %
💥 Break: 4 %
💸 Tokens: –
⏱️ Velocity: –
🛡️ Security: 100 %
🏆 Score: 87
🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Requirement 018: real ggwave 0.4.0 vendored and pinned, an isolated encoder in a sandboxed iframe with its own CSP, Gibberlink as a radio mode and as the fallback where speech cannot play, self-identifying frames of at most 140 bytes, and one of four decodable protocols times five stereo positions per agent. Decision 5 records the evidence that narrowed the six audible protocols to four.
🎯 Fix: 96 %
💥 Break: 1 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 95
🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The navbar time menu goes; the rates panel holds the presets, a two-handle span slider over the hub's history, replay and Live, and the custom From/To range. A custom range becomes a window length plus an end point, so live windows keep their length. The rates chip lists every metric, and the panel wraps instead of spilling at 390 px. Unit and e2e (Chromium, Firefox, 1920/1366/390) cover the window, the slider and the requests.
🎯 Fix: 94 %
💥 Break: 4 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 90
🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The small local model heard the two-word hallo welt clip as English, both
the recording and an espeak-ng rendering; the espeak-ng sentence Hallo
Welt, heute teste ich die Spracheingabe. is detected as German. The
integration test checks the language and the start of the transcript, and
013 decision 8 records the change (operator 2026-11-17).
🎯 Fix: 95 %
💥 Break: 2 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 % (the WAV fixture is binary, not scanned)
🏆 Score: 93
🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
001 names the install proof (the migration test's stub install and a docker
build of orchestrator/ without INFINITO_ARTEFACT_BASE); 002 decision 10
hands the sky extraction to cosmos requirement 001, Skills only reviews the
switch; 010 decision 6 caches semgrep and gitleaks findings per file, with
their configs as cross-file inputs.
🎯 Fix: 95 %
💥 Break: 1 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 94
🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
test_code_graph_real.py runs only with KVB_CODE_GRAPH_INTEGRATION=1 and a
permanent daemon, from the operator's command line: a fresh clone is
indexed once by the hook's helper and reused by a second hook call, and an
additional root indexed by the helper is checked for a watch that outlives
the helper. The second test fails on 0.12.1, which drops the watch when
the helper's session closes; 009 decision 12 keeps that criterion open
until an upstream release after 0.12.1 (operator 2026-11-17).
🎯 Fix: 90 %
💥 Break: 1 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 89
🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Phase C of 012: the Match overview lists every decided card with flip,
edit and back, and one passkey signature releases them all through the
inbox. An approved operator command is bound to the payload hash its card
showed (match_item in the signed set): the hub refuses a stale snapshot or
a changed payload file at release and again before it queues the job. A
rejected commit review carries its feedback as a radio call to the card's
agent, which the hub verifies and records as the review's rejection. Reject
feedback shows line by line, an empty one as such; the arrow keys are in
the help; 012 counts every waiting inbox entry in the Tasks badge.
Accepted MEDUSA false positives (kvb-think-criticize 2026-11-17):
MEDUSA-MM-SCAN-058 signing.py:335 and :337 (pla of plan), EXA010
page-match.js:409 (passkey in a title), EXA006 matching.py:49 (agent then
requester_of), STG002 page-constants.js:79 (U+2212 minus as a label).
🎯 Fix: 92 %
💥 Break: 4 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 % (style-match.css not covered by MEDUSA, reviewed by hand)
🏆 Score: 88
🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Test Squelch plays the burst of a radio row at the All radio volume times
the squelch, like the test buttons of the four tone rows; the threshold row
has none (operator 2026-11-17). The radio set e2e asserts the test buttons
per knob row and that the burst lights the lamp through the bandpass filter
without speech; 004 names the rule.
🎯 Fix: 95 %
💥 Break: 2 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 93
🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Operator request 2026-11-17: the time range slider, replay and rate unit move
into the Rates per period panel with every rate over the chosen window and a
chip of 2 to 9 metrics (015); Priority, Day/Night and Status join the agents
view row (016); an info button hides a chart legend per Home tile and per view
(017). All three are implemented after the other open skills requirements.
🎯 Fix: 95 %
💥 Break: 1 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 94
🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
test_english flagged the umlauts that are Morse characters: morse.js and test_hub_morse.py now write them as unicode escapes (same strings at runtime), requirement 004 names them A, O and U with umlaut. test_lock pins lock version 2, the format make install writes since 2026-11-15; transcend.py and update.sh read only the skill entries, whose shape tests stay green.
🎯 Fix: 97 %
💥 Break: 1 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 96
🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Serial item 3: radio Morse mode, WPM speed, per-agent pitch and the 0-100 % speech threshold (86d539a). Tests run once after the install, by the operator's order 2026-11-15.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Morse keys every picked row whole: class prosign (SOS for MAYDAY), DE with the sender's clear name and the full text, after PARIS timing at the hub's morse.wpm (5-40, default 20) and in the sender's own 550-850 Hz tone from the same sha256 slot as its voice. A higher class cuts a keying row, which keys again whole after it. The speech threshold runs 0-100 % in steps of 10, 100 always open, 0 never. The History card moves into page-radiolog.js to keep page-radioview.js under 500 lines.
🎯 Fix: 85 %
💥 Break: 7 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 79
🚦 Gate: ⛔ fix 85 % < 90, break 7 % > 5
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Committed serial items: e2e files split to <= 500 lines (d8b1c95) and the scoped right-click context menu (ded7c9a). Tests run once after the install, by the operator's order 2026-11-15.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Probe sandboxes gain the channels, quietBubbles and known.now the merged branches added; the hub view keeps queue_jobs apart from the job list; the image ships sandbox_paths.py; kvb-match writes pages into the council root pages folder; the install test scaffolds the council parts and agent roots; skill texts move detail into their side files to stay under the word caps.
🎯 Fix: 88 %
💥 Break: 4 %
💸 Tokens: 98 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 86
🚦 Gate: ⛔ fix 88 % < 90
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Operator pick 2026-11-14: every tests/e2e file at most 500 lines, so Quality's line limit and
medusa's per-file scanner timeout hold. test_orchestrator_e2e.py (3032 lines),
test_radio_layout_e2e.py (1258) and test_radio_set_e2e.py (504) become shared helper modules
(hub_e2e_kit, hub_e2e_views, hub_e2e_radio, hub_e2e_board, hub_e2e_inbox, hub_e2e_plan,
radio_layout_kit, radio_layout_probes, radio_layout_focus_probes, radio_set_kit) and topic test
modules (test_hub_radio_e2e, test_hub_board_e2e, test_hub_inbox_e2e, test_hub_plan_e2e,
test_radio_focus_e2e); the longest file is now 485 lines. All 98 e2e test methods keep their
names and bodies (AST multiset compared before and after); 40 of the 55 moved tests change
module or class, so their ids change. The 21 importers and requirement 004 follow.
Security acceptances (kvb-think-criticize with an independent skeptic, moved unchanged code):
MEDUSA-INF-SCAN-1475, -1616, -2330, -2844, -2970, -3199 radio_layout_kit.py 19 (fixture agent
name Beacon); 19 MEDUSA-INF-SCAN rules hub_e2e_kit.py 208 (mkstemp-backed NamedTemporaryFile);
B603 hub_e2e_kit.py 211 (list argv, no shell, the repo's own node drivers).
🎯 Fix: 88 %
💥 Break: 4 %
💸 Tokens: –
⏱️ Velocity: –
🛡️ Security: ~100 %
🏆 Score: 84
🚦 Gate: ⛔ fix 88 % < 90
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The approval hook binds a hub approval to a plain git commit of the staged index only; commits that add files from the working tree, amend, take a pathspec, run in a chain or inside a shell wrapper fall back to the normal dialog. Every git call of the hook runs with an environment allowlist. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 93 %
💥 Break: 3 %
💸 Tokens: –
⏱️ Velocity: –
🛡️ Security: 100 %
🏆 Score: 90
🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Requirement 013 and its implementation: page-mic.js puts a microphone on every textarea and text input, records with MediaRecorder and inserts the transcript at the cursor; Escape cancels. /api/stt transcribes with the local whisper.cpp model ggml-small-q8_0 (pinned to commit 5359861c and its sha256) in a per-request temp dir, capped at 60 s and 5 MiB, and returns German or English only, retranscribing a clip detected as another language in both and keeping the surer one. Without a model the button is disabled and names the install row. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 72 %
💥 Break: 12 %
💸 Tokens: –
⏱️ Velocity: –
🛡️ Security: 100 %
🏆 Score: 63
🚦 Gate: ⛔ fix 72 % < 90, break 12 % > 5
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Requirement 012 plus its first two phases: the kvb-match skill (match.py add, list, show) feeds the existing review queue, /api/match serves the cards and local-only stale and snapshot posts, and payload files are read only as regular files under /tmp within the sandbox view and 64 KiB. The card at #tasks/match shows face, name, age in days, repository, branch, worktree and files that open while scrolling; right-click or long press marks a line, stale cards cannot be accepted. Accept, reject and the passkey release follow in phase C after the screenshot feedback. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 75 %
💥 Break: 8 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 95 %
🏆 Score: 66
🚦 Gate: ⛔ fix 75 % < 90, break 8 % > 5; security 95 % < 100: ask the operator before the commit
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
rates.py folds the token, commit and score journals into per-hour and per-day rates for the header chips and the rates page; /api/rates drops from about 1950 ms to 380-830 ms on a year of data. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 75 %
💥 Break: 10 %
💸 Tokens: –
⏱️ Velocity: –
🛡️ Security: 95 %
🏆 Score: 64
🚦 Gate: ⛔ fix 75 % < 90, break 10 % > 5; security 95 % < 100: ask the operator before the commit
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
One rule table replaces the two lists: each allow, ask and deny rule shows its hits from the extracted dry-run matcher, ask patterns the matcher never grants read never granted instead of unused, and the table scrolls in its own container below 600 px. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 85 %
💥 Break: 10 %
💸 Tokens: 100 %
⏱️ Velocity: 103 %
🛡️ Security: 100 %
🏆 Score: 74
🚦 Gate: ⛔ fix 85 % < 90, break 10 % > 5; velocity 103 % > 100: ask the operator before the commit
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The radio shows the device card on the left and the speak and history cards on the right from 45 to 61 rem of height, stacking below that; only the history scrolls. History rows get stable keys (sent-row id, else time, sender and occurrence), and focus moves to the nearest row when the focused one disappears. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 85 %
💥 Break: 12 %
💸 Tokens: 60 %
⏱️ Velocity: 45 %
🛡️ Security: 100 %
🏆 Score: 100
🚦 Gate: ⛔ fix 85 % < 90, break 12 % > 5
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
graph.py indexes a repository into codebase-memory-mcp on first use and keeps auto_index on, so every session starts with a graph; agents.py reports its state. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 88 %
💥 Break: 5 %
💸 Tokens: –
⏱️ Velocity: –
🛡️ Security: 100 %
🏆 Score: 84
🚦 Gate: ⛔ fix 88 % < 90
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
speakRows queues all speech rows of a poll before the single redraw, so a MAYDAY behind other rows is never lost, and a draw that throws shows a toast instead of stopping the pump. Late and stale rows both bubble. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 80 %
💥 Break: 5 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 76
🚦 Gate: ⛔ fix 80 % < 90
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The cleanup runs pkgmgr branch cleanup --local and offers deletion only for ancestry-merged branches; squash or PR merges stay a dry-run preview. A signed branch whose ref vanished without a pkgmgr delete becomes gone (deleted outside this run, or after an interrupted apply) and is shown apart from deleted and failed; an Unknown --branch answer for a vanished ref repeats the run once without it. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 88 %
💥 Break: 6 %
💸 Tokens: –
⏱️ Velocity: –
🛡️ Security: 100 %
🏆 Score: 83
🚦 Gate: ⛔ fix 88 % < 90, break 6 % > 5
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
councilroot.py resolves one durable council root for every script and migrates the old /tmp root under the held locks: a preflight conflict moves nothing, each legacy file is renamed to a staging name before it is copied so a late writer is merged by the catch-up, id-less journals merge by line multiset, a differing whole file is kept beside its namesake, and a crash marker makes install copy the skills and report. One settings-file list, managed drop-ins included, serves councilroot.py and queue.py. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 88 %
💥 Break: 7 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 82
🚦 Gate: ⛔ fix 88 % < 90, break 7 % > 5
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Token-saving requirements picked by the operator on 2026-11-14: the code
graph is initialised automatically per repository, security scan results
are cached per file by content, and green test results are reused only
under an exact key. Implementation follows once the running lanes land;
the shared result store is requirement 003 of the quality repository.
🎯 Fix: 95 %
💥 Break: 1 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 94
🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Stars now pin each resources chart (hardware, tokens, combined overlay) with its chip selection, the artifacts tree and single artifacts, Agent priority, Waits on Operator and a single agent card as live Home tiles. A long artifact id pins as <kind>#<digest>, the view store keys selections by digest, refuses pins it cannot keep and Home shows a gone tile with unpin. Fixtures use synthetic operator-example-01 paths; requirement 008 lists the new pins.
🎯 Fix: 91 %
💥 Break: 4 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 87
🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
voicePace and readingPace set each row's floor, span and duration in one place: the spoken rest reveals the unread words over the speech audio, a procedure word reveals none, a burst and silent reading reveal the rest at reading pace, and wordsRead never goes below the floor. A sound that fails or is dropped still ends cleared. Requirement 003 W6 states it; probes cover quiet, burst, fallback, cut, auto, check, silent, rejected and faulty rows.
🎯 Fix: 92 %
💥 Break: 4 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 88
🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Requirement 001 S6: the hub gets a Firewall view of the Claude Code permission and sandbox settings. The operator signs each change with the passkey; a host settings writer (systemd path unit) applies only exact, signed changes to allowlisted settings files through O_NOFOLLOW directory and file descriptors, and a timer refreshes the view. Every signed text and every page sink refuses or marks hidden characters: Cc, Cf, Zl, Zp, every space but U+0020 and the Default_Ignorable set, with U+FE0E/U+FE0F allowed only after one of the 359 non-ASCII emoji bases of Unicode 16 (shared table, validated at import, the same pair rule on the page). Removal of a deny, ask or denyRead entry is exempt only as an exact single remove. The permission hook prints the hub's refusal reason, cleaned of hidden characters. Accepted MEDUSA false positives (independent review, operator pick): 38 this round, mainly the Unicode defence tables read as attack patterns, generic MM-SCAN-058 heuristics, WEB-FLASK-004 at view.py:213 (ints from the validated table via tojson), EXF26-TOOL-004 on the non-secret WebAuthn challenge, PRIV-SCAN-060 on the office-action shape check and PQC007 on a picker key.
🎯 Fix: 95 %
💥 Break: 3 %
💸 Cost: –
⏱️ Time: –
🛡️ Security: 100 %
🏆 Score: 92
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>