claude/.claude/tasks/TODO.md

TODO

2026-09-25 — default profile = full + magic-MCP residue scrub (feature/default-profile-full)

User: "retirer l'API de magic 21st … mettre un profil par défaut … full". Live magic wiring already gone (BDR-093); residue = prose + one MAGIC_API_KEY= line in ~/.claude/.env (deleted, user go). Plan + contract: .claude/tasks/plans/2026-09-25-default-profile-full-1254.md, .claude/tasks/contracts/2026-09-25-default-profile-full-1254.md.

• D1 chore commit e196328 (orchestrator): magic residue out of .env.example (unstaged: git add .env* denied, user stages), .gitleaks.toml, install-plugins.sh 8.7 comment, plugins.lock.json note, lib/profile.sh comments + usage NOTE, profile-set-managed.test.sh header, README (one history sentence, bashrc-wrapper claim dropped).
• D2 feat 0d035fc + 1bbdad0 (feater executor, /feat gates): DEFAULT_PROFILE="full", active_profile(), reset = set full, current default line, gstack off reads the default, statusline fallback, install Step 11 applies the default when none selected, SKILL.md + Makefile help, lib/tests/profile-default.test.sh.
• D3 verify: gates.sh floor MET, verifier CONFORME 13/13, security PASS, make test 236 green + 2 pre-existing T16a; doc sync 0926cc7 (README + CHANGELOG, P1-P6 user-approved); BDR-101 LRN-170 LRN-171 EVAL-031. UNMERGED — human gate. Merged into develop 1ee6cf6 (user go 2026-09-25); .env.example committed by the user (16fea11). Open for the user: first bash lib/profile.sh reset on this machine to make the live state = full (cache absent today), then a new session. Follow-up (LOW, security gate): charset-check the cached profile name / <prof> argument (^[A-Za-z0-9_-]+$) before it becomes a path in read_profile() and install Step 11 — pre-existing, not a blocker.

2026-09-24 — root causes of the day's errors → mechanisms (feature/guardrail-evasion-citers)

User: "détecte pourquoi tu as fait ces erreurs et corrige-les". Evidence: scratch run-rc.sh carries GIT_CONFIG_GLOBAL=/dev/null inline = the denied form my E2 brief ordered ("exported first"); the 200-file rule and the density pass were patched from memory, never from a consumer grep. BDR-100, EVAL-030.

• R1 settings.json hard_deny "Routing around a guardrail" (wrapper/alias/ heredoc/Makefile target/env file/other shell/other agent = same action; refusal → report + wait; brief ordering a refused form is wrong).
• R2 refusal clause in 14 agents (executors + reviewers) + CLAUDE.global.md sub-agent rule; hermetic tests only via make test [suite=].
• R3 Makefile make test suite=<file> — the export lives in the Makefile.
• R4 lib/tests/doctrine-citers.test.sh: CLAUDE.md "Section" / § Label citations must resolve; flip-tested; first run fixed rest-api-node.md.
• R5 doctrine "After code changes" step 4: changed rule/heading/label/ threshold → grep every citer, same commit; thresholds in one lib file.
• R6 verify: census 5/5, make test 168/170 (T16a pre-existing), suite= OK, shellcheck clean, CLAUDE.global.md 287 lines. UNMERGED — human gate. Residual: the content-aware PreToolUse guard (BLK-022) is still the missing deterministic floor for scripts run by a command; static deny stays string-based.

2026-09-24 — C2 coherence: 30 doctrine/skill tensions resolved (feature/c2-coherence)

Audit by 3 read-only analysts (doctrine+rules, skills A-H, skills I-W), 39 raw pairs → 30 unique, spot-checked by grep. User approved all four groups + G3 as recommended. C3 (superpowers) closed: no over-trigger in 29 sessions / 126 turns (2 brainstorming calls, both warranted), ~800 tok fixed/session → keep, re-measure in 30 days with the same transcript script.

• WP-A doctrine (CLAUDE.global.md): 3 compress-on-demand → via /prune-memory; 4 deploy → /deploy; 5 one ask policy; 12 BDR-068 exception clause; 13 memory commit: exemption vs aiguillage, both written; 14 chore = maintenance without new behaviour; 17 hotfix on develop → bugfix; 22 skill plan file satisfies the planning rule; 23 mandated executors exempt from the delegation rule; 24 journal line exempt from the approval gate. Stay < 320 lines.
• WP-B lib bug (7): _gitflow_init_existing socle commit blocked on main by the live global pre-commit → socle on chore/gitflow-adopt off main, merged --no-ff (merge exempt), branch deleted; T2c with a simulated global hook.
• WP-C E1 gitflow-family skills: capitalize/close --no-push text (11), memory missing → create (21), gitflow SKILL exception line (12), § Language ×5 (2), hotfix aiguillage bugfix-on-develop (17) + design-gate skip (25), feat/bugfix/ hotfix executor wording (23), ship-feature .gsd/STATE.md (27), init-project graphify gate (1) + memory bootstrap (21), aiguillage table rows (/doc, /commit-change, seo/web-validate/refactor) (18,19), doc STEP 0 aiguillage (19), commit-change asks branch type (14).
• WP-D E2: onboard graphify gate (1) + STEP 2.6 rewrite (7) + add gsd/continue (28); tour push wording (10), BREAKING → needs decision (15), doc-syncer two-mode (26); deploy push_deploy_tags (8); release-candidate tag-only push gate + release-executor + its test (9).
• WP-E E3: client-handover gate + script path (16, 29); seo/web-validate/refactor aiguillage step (18); pdf-translate sudo (30); verify-secure-loop inline-fix removal under locks (20); design-gate.md extensions/impeccable/anim list (6).
• WP-F verify: make test, shellcheck, doctor, banner; review full diff; BDR-099 (C2 resolutions) + LRN-163? no: LRN-169 (audit method) + journal; C2/C3 ticked in the 2026-08-25 block. Merge on user go.

2026-09-24 — CLAUDE.global.md density pass (chore/claude-global-density)

• 352 → 270 lines, −15% words, compression only (BDR-031/062 principle), headings verbatim, graphify § byte-identical (feature/graphify-threshold-banner pending). Dropped on purpose: release-candidate / audit-delta / init-project+onboard routing lines. Vocabulary diff audited: no rule lost. make test unchanged, banner clean, doctor 0 errors. BDR-098. Merged into develop abec66e (user go 2026-09-24).

2026-09-24 — graphify threshold signal: inform from 200 code files, user decides (feature/graphify-threshold-banner)

User: "graphify seulement à partir de 200 fichiers de code… tu informes, je décide". Grounded in LRN-162 measurements (robin_petier scratch copy: AST 2.3 s, 0 tokens, query 2-3k tokens, .claude/ noise). Alternatives rejected in BDR-097.

• G1 lib/graphify-gate.sh: tracked code-file count (AST extension set, vendored trees excluded), ≥ 200 + no graph → one banner-sized line, rc 0; silent rc 1 otherwise. GRAPHIFY_MIN_CODE_FILES override.
• G2 lib/tests/graphify-gate.test.sh 11 checks: not-a-repo, 199/200, graph present, vendored, untracked, override, subdirectory, non-code.
• G3 hooks/session-start.sh: compute after the gitflow reconcile, print after the hooks-refreshed line: 🕸️ graphify? N code files ≥ 200, no graph + → /graphify (AST, seconds) — you decide.
• G4 doctrine: CLAUDE.global.md § graphify threshold sentence; plugin-advisor thresholds no longer pre-enable graphify; CHANGELOG.
• G5 BDR-097, LRN-162, journal. shellcheck clean. Live: this repo silent (74), robin_petier fires (214). Merged into develop 10532e3 (user go 2026-09-24); registry conflicts resolved keeping both sides. Pilot (not started, user's call): robin_petier graph + .graphifyignore + gitignore graphify-out/ + GRAPHIFY_FORCE=1 graphify update . in the gitflow post-commit hook when a graph exists.

2026-09-24 — branch deletion guard: never main/develop, never unmerged (feature/branch-delete-guard)

User rule (after the 21/09 wipe, same family as BDR-095): auto-delete of a branch is accepted ONLY once it is merged into develop or main; main and develop are never deleted. Finding that motivates it: since BDR-095 start pushes -u origin, so git branch -d now checks "merged into its UPSTREAM" (origin/
, always in sync via post-commit) instead of "merged into HEAD" — its safety valve is dead. _gitflow_delete only survived because finish chains it after a successful merge.

• D1 lib/gitflow-test.sh T22 (lib): -d alone deletes an unmerged branch whose upstream is in sync (premise proof); gitflow_delete refuses main/develop (rc 6) and an unmerged branch (rc 5), deletes a merged one; gitflow_merged_into_base predicate; T23 (hook): git branch -D develop|main, update-ref -d, branch -m develop all BLOCKED from a working branch; a merged feature deletes fine; gitflow.protect false opt-out; commit/checkout unaffected; T19d/T20 iterate the 4 hooks.
• D2 lib/gitflow.sh: gitflow_merged_into_base <br> (ancestor of develop OR main, fail closed when neither exists); gitflow_delete = protected refusal + merged check + git branch -d; CLI verbs delete <br>, merged <br>, hooks; 4th hook reference-transaction (refuses deletion of refs/heads/main|develop in prepared state, sh, opt-out gitflow.protect); hook names in one GITFLOW_HOOKS array (write, emit, reconcile, T19d, doctor all read it).
• D3 settings.json: static deny git branch -d|--delete|-dr|-rd *, git branch -m|-M main|develop *; hard_deny "branch deletion outside gitflow.sh delete/finish, any deletion/rename of main/develop, local or remote"; "Disarming" entry covers every hook file; environment protected-branches line updated. guard-bash.test.sh T8w flips to deny. Leave the user's uncommitted feedbackDrafts line out of the commit.
• D4 doctrine: CLAUDE.global.md gitflow section (delete only via the lib, main/develop never, -d no longer protects); skills/gitflow/SKILL.md table + delete op + failure rows rc 5/6.
• D5 doctor.sh hook loop reads gitflow.sh hooks; regenerate .githooks/ + githooks/ (both tracked) with the 4th hook.
• D6 docs: templates/settings/SETTINGS.md, README line, CHANGELOG.
• D7 make test, shellcheck, doctor; BDR-096 + LRN + journal. Verified 2026-09-24: gitflow-test 152/154 (2 pre-existing T16a), T22 12/12 + T23 11/11, shellcheck clean incl. emitted hook, doctor 4/4 hooks match. Merged into develop b2e252e (user go 2026-09-24). BDR-096, LRN-161.
• D8 (user go 2026-09-24, feature/remote-branch-cleanup) _gitflow_delete_remote: after the local delete, remote tip read + re-checked against develop/main, then push origin --delete; best effort (skip: no origin / NO_PUSH / autopush=false; loud: unreachable, unmerged remote tip). T24 9/9, 161/163. Live on the 2 stale merged remotes: origin/feature/branch-delete-guard + origin/feature/destructive-guardrails removed by gitflow.sh delete (both tips verified merged), bases untouched. Merged into develop 91859fe (user go 2026-09-24); finish removed its own remote copy.

2026-09-22 — destructive guardrails after the 21/09 wipe (feature/destructive-guardrails)

Incident 2026-09-21 00:21 on the old server: a reviewer sub-agent (atlast SDD, opus) traced lftp mirror --reverse --delete against a local file:// tree; the target resolved to a real path, mirror --delete did rm -r (ignores --exclude) on everything uid 1000 owned: home, ~/.claude, NAS (uid=1000), 15 Gitea repos (Gitea ran as bchanot). The 17/09 classifier prose (hard_deny "deploy", soft_deny rsync --delete) named neither lftp nor a local trace; the orchestrator's brief authorized the trace; auto mode is inherited by sub-agents. 4 days of faunosteo never pushed. User decisions: Claude NEVER deploys (explains only), lftp has no use in session; layer A (OS, restic, NAS) and layer B (sandbox + managed settings) are the user's; this branch = layer C (config repo) + auto-push.

• G1 lib/tests/guard-bash.test.sh (214 cases, SKIPs while the hook is absent): transfer tools, mirror/sync delete, recursive rm outside cwd/tmp or via variable, chmod/chown -R, sudo, disk tools, docker privileged/system mounts/volume drops, git history destruction, forbidden write zones, guardrail tampering, nested forms (bash -c, &&, docker compose run … lftp), script files run by the command; allow list of ordinary commands.
• G2 BLOCKED (BLK-022, safety classifier withheld the body) hooks/guard-bash.sh: PreToolUse Bash, exit 2 + reason, logger trace, fail-closed without jq.
• G3 settings.json (hook registration = unpushed-guard only, guard-bash pending): static permissions.deny (lftp/ftp/sftp, rsync --delete, chmod/chown -R, sudo/doas/pkexec, dd/mkfs/shred/…, docker prune/volume rm/down -v/--privileged/docker.sock, git push --delete/--mirror/:ref, branch -D, filter-branch, reflog expire, stash clear/drop, xargs rm, pipe-to-shell), hook registration, new hard_deny (destructive tool against a local path, brief ≠ user authority), soft_deny reworded (docker items promoted, discard of uncommitted work), environment lines updated.
• G4 lib/gitflow.sh (+ post-merge: git merge skips post-commit, T18f) : start pushes the branch (-u origin), post-commit hook emitted + installed with pre-commit (push every commit, --follow-tags, timeout, GITFLOW_NO_PUSH=1 opt-out, never fails the commit), install-hook/emit-hook cover both; .githooks/post-commit in this repo; gitflow-test.sh T18.
• G5 hooks/unpushed-guard.sh on SessionStart + Stop: warns when the branch is ahead of origin or has no upstream; test.
• G6 doctrine: CLAUDE.global.md Security "Destructive tools & data loss" + gitflow auto-push line; the 4 read-only agents get the "trace by reading, never by running" clause.
• G7 docs: templates/settings/SETTINGS.md (hook tier, ask caveat), CHANGELOG, BDR-095, LRN-160, journal. make test + shellcheck.
• G8 hooks everywhere, no per-project step (user go 2026-09-22): global core.hooksPath ~/.claude/githooks set by make link from a generated githooks/; gitflow reconcile-hooks at session start refreshes a lagging .githooks/; opt-outs gitflow.protect / gitflow.autopush; pre-commit exempts .githooks/**; doctor check; hermetic GIT_CONFIG_GLOBAL=/dev/null in make test + 2 suites; deny on the env bypass forms; T18h T19d T20 T21. Verified after the /tmp cleanup: gitflow 127/129 (2 pre-existing T16a), review-guards G5 caught this repo's stale .githooks/ (refreshed via install-hook), shellcheck clean, doctor "Scratchpad" check added. OPEN for the user: make link (sets the global core.hooksPath; denied to the agent), and launch claude with TMPDIR=$HOME/.cache/claude-tmp in dtach_claude(). → make link DONE (global core.hooksPath = ~/.claude/githooks, reconcile 2026-09-24); TMPDIR in the launcher still open (BLK-021). Out of scope here (user's side): restic append-only, lxd group, NAS mount, managed-settings.json + sandbox, per-project accounts, docker rootless.

2026-09-22 — impeccable install repaired: global scope + agents + rotted pin (feature/21st-cli-migration)

User: make plugin never installs impeccable, it just prints "run it yourself"; running it by hand needs --scope=global to land right, and then /impeccable init is still required. Three separate defects, all confirmed:

1. Pin rotted. npx -y impeccable@3.2.0 skills install → Download failed: invalid zip data, rc 1. The CLI fetches its skill dist at install time and that release's artifact is gone. 3.6.1 / 4.0.5 / 4.1.0 all work. That rc 1 is the "run manually" warn the user sees.
2. Wrong scope + half the payload dropped. The step staged --scope=project in a tmpdir and mv'd only the skill dir, silently discarding the 4 impeccable-* subagents the installer also writes. --scope=global writes ~/.claude/skills/impeccable + ~/.claude/agents/impeccable-*.md, and both are symlinks INTO this repo, so a global install is the repo install. Verified in a sandbox HOME.
3. /impeccable init never surfaced. It writes per-project PRODUCT.md (design context the skill reads); it runs in the agent chat, so install can only announce it and the design gate has to check it.

• T1 install-plugins.sh Step 8d rewritten: global scope, no staging, pin→latest fallback with a loud bump-the-lock warn, park-aware (profile may hold impeccable in skills-disabled), symlink precondition guard, agent count + skill version reported, init hint printed. Harness-tested against a fake HOME with repo-shaped symlinks: happy path OK, park/restore OK. Caught + fixed there: find stops at the ~/.claude/agents symlink without -L, so the agent count read 0 while 4 agents were installed.
• T2 update-all.sh impeccable block: same shape. bash -n only, NOT run end to end.
• T3 plugins.lock.json: 3.2.0 → 4.1.0 + honest note (pin covers the CLI only; skill dist 4.3.1 and engine 0.1.5 have their own tracks).
• T4 .gitignore: agents/impeccable-*.md (machine-owned, tracked dir); drop skills-external/impeccable/. link.sh: impeccable out of EXTERNAL_SKILLS (nothing to symlink any more). git check-ignore confirms both paths.
• T5 lib/design-gate.md §5: suggest-only PRODUCT.md / /impeccable init check, same shape as the §4 animation-library check.
• T6 duplicate project-scope install: already gone at resume (user ran rm -rf .claude/skills .claude/agents before restarting).
• T7 CHANGELOG (Added/Changed/Fixed) + BDR-094 + LRN-159 + BLK-021 + journal. make test green except the 2 pre-existing gitflow T16a FAILs (gitleaks binary absent on this host), shellcheck clean. Merged into develop 2026-09-22 (33e0899, gitflow finish on user go), pushed.

Residual, probed and fixed (round 3): with a copy already installed a rotted pin DOES exit 0 ("Could not check for skill updates: invalid zip data … Existing skills were left unchanged"), and so does a genuine rerun of a good pin ("Skills are up to date (v4.3.1)"). Both leave SKILL.md byte-identical, so a before/after version compare cannot separate them. imp_install (Step 8d and update-all.sh) now captures the installer output and fails on Download failed|Could not check for skill updates, whatever the exit code. Harness on the extracted step, sandbox HOME, real installer: fresh install; rotted pin over a copy → fallback fires; same pin rerun → no false warn; parked copy + rotted pin → fallback, then returned to skills-disabled/. update-all.sh: bash -n + shellcheck only.

OPEN for the user:

• /tmp is a tmpfs with a per-user quota and the dead session's scratchpad holds 5.9 GB of probe HOMEs. Writes to /tmp fail with EDQUOT: the likely cause of the "every command exits 1" shell death (BLK-021). Free it: rm -rf /tmp/claude-1000/-home-bchanot-Documents-claude/fefd277c-e143-4d51-b589-a566641079b5 (the agent's rm -rf under /tmp is denied). This round ran tests and the harness with TMPDIR under ~/.cache.
• skills/synced/ (4.4 MB, untracked, not ignored): claude.ai's synced skills, written through the ~/.claude/skills symlink. Decide whether to gitignore it; not touched here. → /tmp freed by the user 2026-09-22; skills/synced gitignored 87b2615 (reconcile 2026-09-24).

2026-09-22 — 21st: magic MCP → CLI + skills (feature/21st-cli-migration)

User: "remplacer pour 21st, il n'y a plus besoin de mcp / api, mais juste en cli". Upstream confirmed (@21st-dev/cli 1.17.1 README): the CLI supersedes @21st-dev/magic; auth is 21st login (browser token in ~/.config/21st), no API key; 21st install-skill = alias of 21st skills install --global. Gates answered by user: 5 design skills in profiles (registry + design-sync parked), make plugin auto-installs the CLI + offers login on TTY only, missing 21st CLI trips the design gate (magic's old required-manual slot).

Blocker found + solved: 21st skills install --global REFUSES to write through a symlinked path (assertNoSymlinkComponents), and ~/.claude/skills IS a symlink → repo/skills. Verified live: "Refusing to access symbolic link …/.claude/skills". → install into a staged HOME (mktemp), move each skill to skills-external/21st-*/ (impeccable pattern), symlink from there.

• T1 install-plugins.sh STEP 8.7: magic block → 21st CLI (npm i -g, pinned via plugins.lock.json) + staged skills install → skills-external/21st-*, TTY-gated 21st login, pack disabled by default.
• T2 lib/toggle-external.sh: managed tool magic (mcp) → 21st (skill pack, glob-derived from skills-external/21st-*), drop load_env.
• T3 profiles + profile.sh: magic mcp → 5 externals + 21st cli in design/web/web-full/full; GATE-BLOCK 21st 21st-ui-build; MANAGED_EXTERNALS += the 5; MANAGED_MCPS emptied (kept as a live allowlist, mcp type machinery stays generic).
• T4 lib/design-tool-gate.sh + lib/design-gate.md: manual-step hint magic/MAGIC_API_KEY → 21st/npm i -g + 21st login; PATH repair extended to the npm-global bin dir (21st lives in nvm's bin, the existing repair only fires when claude itself is unresolvable).
• T5 doctrine + docs: CLAUDE.global.md design toolchain, README (drop the magic callback-injection section + the MCP env-var worked example), .env.example, link.sh MAGIC_API_KEY warning, .gitleaks.toml allowlist, update-all.sh, .gitignore, settings.json (drop 4 mcp__magic__*; the outward-facing verbs landed in autoMode.soft_deny, NOT ask — LRN-153 says ask is inert under auto mode).
• T6 lib/tests/profile-set-managed.test.sh retargeted (mcp fixture → 21st external pack), make test + shellcheck green.
• T7 CHANGELOG + BDR-093 + LRN-158 + journal. Also cleaned along the way: dead magic branches in profile.sh enable/disable_skill, skills/profile/SKILL.md. OPEN for the user: npm i -g @21st-dev/cli then 21st login (Bash(npm install -g *) is denied to the agent). Merged into develop 2026-09-22 (33e0899), pushed. → 21st CLI installed (nvm bin; reconcile 2026-09-24); 21st login state not verifiable here.

2026-09-17 — /deploy hand-back: one-line commands + post-deploy test list (feature/deploy-oneline-tests)

User: commands in the /deploy checklist arrive broken across lines (cannot copy-paste), and the hand-back stops at the deploy steps — wants, after the checklist, a list of things to test by hand about THIS delta + suggestions. Evidence: zenquality runbook step 3 carries a \-continued psql; game runbook has 200-350 char command lines the model re-wraps at display (80-char code style pressure). Method: writing-skills RED/GREEN on a scratch fixture repo (4 fresh agents, skill body as instructions, gate pre-approved).

• D1 RED baseline: 4 runs on the current skill, record wrapped commands + absence of a test list + rationalizations
• D2 SKILL.md: physical-line rule (checklist, bootstrap, learn patch; join legacy \ continuations at instantiation), post-deploy tests recipe (manual checks + suggestions, derived from the delta), hand-back order checklist → tests → report request; Rules / mistakes / red flags
• D3 templates/deploy/PROCEDURE.md style header + test-prompts.json
• D4 GREEN: re-run 4 fresh agents on the edited skill, compare shape
• D5 CHANGELOG [Unreleased] Changed; report; offer capitalize (EVAL + LRN) Milestone 2026-09-17: RED 4/4 (3 sonnet + 1 opus) reproduced the \ continuation verbatim, no re-wrap of 200+ char lines, no test list; GREEN 4/4 joined the continuation, kept long lines whole, printed the tests block in the recipe's shape (grant gap as a Suggestion, never patched). Branch feature/deploy-oneline-tests, uncommitted, awaiting user. Registries: EVAL + LRN drafts proposed, not written.

2026-09-16 — docker + node framed by the classifier (feature/automode-docker-node)

User: docker exec -i supabase_db_game psql … -f - < supabase/verify/*.sql | tail must run unprompted under auto mode; same for node/npm/npx when the package is declared and effects stay in the cwd; "ajoute du soft deny pour bien le cadrer". Findings: ask is inert under auto (LRN-146 re-verified on 2.1.273 with a node -e probe; the docs claim otherwise for content-scoped rules); the real gate is the built-in Remote Shell Writes / Production Reads classifier rules; a static Bash(node *) allow rule is suspended under auto (wildcarded interpreter), so autoMode.allow prose is the only lever for node. User approved the design and the ask removal explicitly (S6 override for this change, diff reviewed on the branch).

• A1 settings.json — drop 4 docker + node -e from ask; new autoMode.allow ($defaults + local dev containers + project-local node); 2 soft_deny entries (docker data destruction, undeclared node packages); model bump committed separately
• A2 templates/settings/SETTINGS.md — autoMode.allow tier row + why a static interpreter allow rule cannot do it; LRN-146 re-verify note
• A3 CHANGELOG [Unreleased] Changed
• A4 verify (2026-09-16, all green; critique printed nothing): jq, claude auto-mode config, doctor.sh, live docker exec in game
• A5 registries written 2026-09-17: LRN (doc vs observed ask under auto, 2.1.273; autoMode.allow = exception tier; wildcarded-interpreter allow suspended), BDR-090 addendum

2026-09-16 — ask, don't guess: orchestrators ask about open choices (feature/ask-dont-guess)

User: the orchestrators (ship-feature, feat, hotfix, bugfix, init-project) settle choices they should ask about ("cet icône, plutôt à gauche ou à droite ?"), even mid-run. Diagnosis: contract-interview STEP 2 only fires on gaps (outcome / scope / constraints), so a taste choice never triggers a question; feat:153 and bugfix:165 tell the orchestrator to "make the decision HERE" on NEED-DECISION. Decisions (user, 2026-09-15/16): global rule changes for all work, hotfix included; classes VISIBLE / PUBLIC NAME / SCOPE ask, internal technical choices never. Spec: docs/superpowers/specs/2026-09-16-ask-dont-guess-design.md; plan: docs/superpowers/plans/2026-09-16-ask-dont-guess.md (9 tasks, lock-first).

• P1 lib/contract-interview.md — STEP 2 CLARIFY (pass A gaps, pass B open choices), MID-RUN CLARIFICATION, HOW TO ASK; 9 locks in contract-verifier.test.sh
• P2 CLAUDE.global.md:51-55 — "Ask rather than guess" replaces the one-question rule; bug line reconciled
• P3 skills/feat/SKILL.md — pass B at STEP 1, NEED-DECISION routed on class
• P4 skills/bugfix/SKILL.md — pass B at STEP 3, NEED-DECISION routed on class
• P5 skills/hotfix/SKILL.md — pass B at LOCATE, tagged BLOCKED relayed; lock loops-light.test.sh:84
• P6 skills/ship-feature STEP 2 + skills/init-project contract §/STEP 3
• P7 agents/interviewer.md — visible/public/scope item never (assumed)
• P8 agents/{feater,bugfixer,hotfixer}.md — CLASS tag; 3 locks in gates.test.sh
• P9 make test green (2026-09-16), CHANGELOG, TODO tick; manual behavioral check still OPEN before merge
• P10 registries written 2026-09-17: BDR (supersedes the one-question rule), LRN (taste is invisible to a gap-only trigger; fresh re-dispatch cost favors plan-time questions)

2026-09-15 — align config + deployment on the hand-edited settings.json (feature/automode-config-alignment)

User edited global settings.json by hand: 4 destructive rules moved deny→ask (rsync, kill -9, killall, pkill), 4 removed from ask (xargs, sed, cp, mv — coherent with auto mode's Bash-first workflow; the .env-scoped cp/mv/xargs deny rules still stand), and an autoMode.environment block added. Two defects found: (1) the environment block describes atlast (bin/deploy.sh lftp/FTP to OVH, quote-request data, "no remote configured") but lives in the user-scope file symlinked to ~/.claude/settings.json by link.sh:21 — so every project gets atlast's facts; claude-config itself has a Gitea remote, contradicting the block. (2) no "$defaults" sentinel, so the built-in classifier environment entries are replaced, not extended. Third finding: LRN-146 records, verified in session, that ask rules raise no prompt under defaultMode: auto — the deny→ask move therefore traded a static block for a classifier decision. User decisions (2026-09-15): atlast block → atlast's own settings.local.json, global block rewritten machine-generic; the 4 destructive rules → autoMode.soft_deny (the section that actually binds under auto mode) instead of ask.

• T1 global settings.json — machine-generic autoMode.environment with $defaults; new autoMode.soft_deny with $defaults + the 4 destructive rules; drop those 4 from permissions.ask
• T2 /home/bchanot/Documents/atlast/.claude/settings.local.json — receives the atlast-specific autoMode.environment (gitignored, personal scope); verify project-scope autoMode is honored
• T3 templates/settings/SETTINGS.md — document the autoMode block (environment / soft_deny / hard_deny / allow, $defaults semantics, classifyAllShell) + the "ask ≠ prompt under auto" caveat that makes soft_deny the right tier
• T4 README.md — magic-MCP paragraph claims the ask tier makes every mcp__magic__* call "require a live confirmation and never auto-execute"; false under auto mode per LRN-146. Correct the claim, flag the soft_deny option to the user (don't decide it)
• T5 doctor.sh — permissions section is blind to autoMode, now a live security surface. Add a check: block present, $defaults inherited, no foreign absolute project path hardcoded
• T6a CHANGELOG (Added/Changed/Fixed under [Unreleased])
• T6b registries BDR-090 + LRN-153 + journal — drafted, awaiting user approval → written: BDR-090 + LRN-153 present in the registry body (reconcile 2026-09-24).
• T7 verify: make test, bash doctor.sh, shellcheck NOT in scope: the 3 dirty skills/graphify/* files (pre-existing, unrelated) — never staged.

Second pass (2026-09-15, user decisions)

User confirmed the ask removals were deliberate (/permissions), asked for the diff vs develop and for guards where the removals left a hole. Answered: writes outside cwd → soft_deny; in-place edits beyond one named file → soft_deny; inline interpreters + xargs → soft_deny when they delete or write outside cwd; hard_deny for secret exfiltration, prod deploy, disarming guardrails (history rewrite NOT retained, so a rebase then an ordinary push stays uncovered); extend the static deny family to the .env readers; classifyAllShell stays false; intent clears a soft block for the CURRENT TURN only.

• S1 permissions.deny +10 reader rules (sed awk cut tr sort uniq diff od xxd strings vs .env*) — 6 of them were in allow
• S2 autoMode.soft_deny — 7 rules + the intent-scope line
• S3 autoMode.hard_deny — 3 rules, "adding a restriction is fine, removing one is not"
• S4 SETTINGS.md — tier-choice table + scope-of-intent section
• S5 CHANGELOG — Changed rewritten, new Security block
• S6 CONSEQUENCE confirmed by user 2026-09-15: the hard_deny guardrail rule means I can no longer edit a deny/soft_deny/hard_deny list to REMOVE an entry. Tightening stays allowed. Future permission loosening goes through /permissions or the user's own edit.

Third pass (2026-09-15) — F1-F3 done + graphify untracked

Worst finding was not the duplication: local deny still carried rsync kill -9 killall pkill, the four the user moved OUT of global deny. deny wins across sources, so autoMode.soft_deny was a dead letter in THIS repo. Local allow also held sed *, cp *, python3 - — an allow rule short-circuits the classifier, punching a hole through the same soft_deny rules.

• G1 skills/graphify/{SKILL.md,references/,.graphify_version} gitignored + git rm --cached. Written by graphify claude install since ~/.claude/skills symlinks to skills/; a fresh clone gets them from make plugin. test-prompts.json is hand-written for darwin, stays tracked. Trade-off documented in CLAUDE.md: an upstream release can now change the skill prompt with no diff to review.
• G2 .claude/settings.local.json 14.6 KB -> 6.2 KB. deny + ask dropped whole, allow 185 -> 98 (81 duplicates of the global, 6 policy conflicts: sed *, cp *, python3 -, Read(//home/bchanot/**), WebSearch, a leftover injection-test payload). Every non-permissions key was a verbatim copy of the global, hooks included. Backup: .audit/settings.local.json.bak-* (gitignored, the file itself is not in git).

Follow-up found while doing this (fixed in the third pass above)

.claude/settings.local.json (gitignored, 14.6 KB) is a near-complete shadow copy of the global settings.json at a HIGHER precedence tier: 185 allow / 30 ask / 106 deny, plus its own cleanupPeriodDays, attribution, statusLine, enabledPlugins, extraKnownMarketplaces, effortLevel, remoteControlAtStartup, inputNeededNotifEnabled, skipAutoPermissionPrompt — all identical to the global today, so the duplication is invisible until the global drifts, which it just did (no autoMode, 106 deny vs 116). It defeats the config-guard premise (hand-curated settings.json) with a file nobody reviews.

• F1 WebSearch sits in global ask and in local allow — in this repo it never reaches the ask tier. Intended or drift?
• F2 local hooks block registers bash ~/.claude/hooks/config-protection.sh on PreToolUse/Bash. That script does not exist, in hooks/ or in ~/.claude/hooks/. Dead hook firing on every Bash call here.
• F3 decide: prune the local file down to the session-accumulated allow rules only, dropping every key that merely restates the global, or keep the copy deliberately and document why.

2026-08-25 — darwin fresh baseline: 32 skill-systems + 23 agents (feature/darwin-optimize-20260825)

User: /darwin-skill all skills and agents (background). Fresh-from-zero (results.tsv wiped 2026-06-23, journal 2026-06-30). Scope per BDR-015/043 + LRN-070: personal skills only, external/gstack OUT. EVAL-004 applied: eval unit = skill+dispatched-agents SYSTEM, agents get own rows. LRN-018: judges emit per-dim scores, totals recomputed main-thread. v2.1 keep/revert = paired same-judge majority, absolute scores triage-only.

• T1 Phase 0+0.5: gitflow branch, results.tsv header, 7 new test-prompts.json (capitalize deploy gitflow pdf-translate reconcile release-candidate tour), runtime scan (2 minor hits). find-docs EXCLUDED — machine-owned ctx7 (BDR-053, gitignored) → 31 systems.

• T2 Phase 0.5 gate PASSED: reuse prompts as-is; dim8 full_test on candidates only (baseline dry_run); Phase 2 set = ALL units <80.

• T3 Phase 1 baseline DONE: 7 blind judges, 54 rows (31 skills + 23 agents), mean 83.4, 13 units <80, ~25 verified findings (hotfix destructive restore, onboard/onboarder contract, init-project allowed-tools, skills-perso 8/32 detection...).

• T4 Phase 1 gate PASSED: user picked the set — proven by Phase 2 running 13/13 units, 0 reverts (DARWIN-2026-08-26.md:23). Ticked by reconcile 2026-09-01.

• T5 Phase 2 DONE: 13/13 units, 12 rounds kept 3-0, 0 reverts + bug pass 8 commits kept 3-0 (2 skeptic residuals amended). make test green.

• T6 Phase 3 DONE: report .claude/audits/DARWIN-2026-08-26.md + card PNG (playwright fallback). Capitalize pending user approval. Branch UNMERGED — human gate. → both residuals stale: capitalized a15854a, merged 726464f (reconcile 2026-09-01).

2026-08-25 — user permanent rules: writing + web build + web security (feature/user-writing-web-rules)

User supplied 4-block rule text (écris / site / code / vérification); asked: coverage check, conflict check, integrate. Verdict: security CORE already in CLAUDE.global.md §Security (parameterized queries, env-var secrets, AuthN/AuthZ, fail closed) — NOT duplicated. NEW: writing-style block, design anti-default list, site done-checklist, web-app specifics (RLS, service key, IDOR, cookie flags, rate limit, field minimization). Placement: global at 308/320 budget → rules/ instead.

• R1 rules/writing-style.md — always-on (no paths:), scope carve-outs (registries caveman, code comments, skill templates) + self-check
• R2 rules/web-building.md — paths: web globs; anti-defaults + done checklist (report missing, never invent) + skill pointers
• R3 rules/web-security.md — paths: code globs; web-app specifics extending §Security, zero dup of the core
• R4 CLAUDE.md (project) — amend always-on doctrine line (320-budget exception → rules/), feeds C2 audit
• R5 capitalize BDR-085 + journal + CHANGELOG
• merge → develop 5ec7bfa — human gate passed (reconcile 2026-08-25)

2026-07-30 — adapt config for Claude 5 family / Opus 5 (feature/opus5-config-tuning)

User: Opus 5 "needs more freedom" → research (official migration guide + web + registres) confirms: over-delegates (inverts LRN-030 Opus 4.8 trait), over-verifies if told to verify, literal instruction following, scope expansion named regression, harness already injects anti-delegation on Opus 5 (#80988). Plan: .claude/tasks/plans/2026-07-30-opus5-config-tuning-1238.md — to be challenged by 3 blind plan-challengers (opus pins → Opus 5), then executed on feature branch. NO merge (human gate). Challenged 2026-07-30: correctness CONCERNS(4) · robustness FATAL(5, 1 BLOCKER: symlink-live deployment) · simplicity CONCERNS(4) — all fixes adopted as prescribed (plan §5bis, v2 items below).

• W0 branch first (eab2a10 parent); hook regex validated on scratch copy (bash -n + shellcheck + 5 replays, HOME sandboxed) before live write
• W1 delegation block v2 (when-guidance + gates carve-out + scoped don't-redo) — 0f7b565
• W2 "staff engineer" bar line deleted — 0f7b565
• W3 finish-whole-task folded into Deviations (+ gone-WRONG→STOP) — 0f7b565
• W4 deliverable-length rule — 0f7b565
• W5 line budget: 308/320
• W6 hook \bux\b dropped, \bui\b kept + F10 must-fire lock, D11 quiet row flip-tested (fire before/quiet after) — eab2a10, suite 22/0
• W7 plan-challenger :82-83 reworded → [MINOR] routing, census row — c3d3f4d, 44/0
• W8 BDR-081 + LRN-139 + journal + CHANGELOG
• W9 final gate: make test full suite — green except known T6c (darwin-skill residual → chantier 4 below), 2026-07-30
• W10 merged on explicit user signal — 709cf9b (2026-07-30 13:28), branch deleted; confirmed post-merge this session

2026-07-30 — Claude 5 follow-on chantiers (user directive, checkpoint between each)

Order fixed, one branch per chantier, no merge without per-chantier signal.

• C1 dé-prescription seo-analyzer.md + geo-analyzer.md — DONE 2026-08-02. Census-first 71 locks flip-proven (9681b46) → rewords under audience×range invariant (adafa35 seo, c7646a9 geo) → controlled before/after dogfood: judge-replay on frozen signals + templates + fresh collects + e2e judge + blind reader = 42/42 both sets, zero contract regression, recall improved. Plan challenged 4 passes (FATAL/FATAL/CONCERNS + confirmation FATAL(9), all closed by name). BDR-082 + LRN-140. Evidence .audit/dogfood-baseline/ (19 artifacts). Branch feature/seo-geo-deprescription UNMERGED — human gate. → merged 5488c48, branch deleted (reconcile 2026-08-25). Residual for gate: §6bis dynamically-unverified list (FULL branches, apply path — census-locked statically); FULL/aggressive dry-run = user option; nested-CLI dogfood blocked by monthly spend limit (inline used).
• C2 self-contradiction audit CLAUDE.global.md + own skills: list rule pairs in tension, propose resolution per pair, apply after user OK. /doctor as assistant, not authority. → DONE 2026-09-24: 30 pairs, all resolved on feature/c2-coherence (BDR-099).
• C3 superpowers: MEASURE first (skill-invocation log over sessions) whether "1% chance → MUST invoke" over-triggers; if yes, options + trade-offs (disable plugin / softer house rule / live with) — user decides. → DONE 2026-09-24: measured 2/126 turns, both warranted → keep, re-measure in 30 days (LRN-169).
• C4 hygiene: reinstall darwin-skill — DONE (reconcile 2026-08-25: ~/.agents/skills/darwin-skill present, T6c green, make test exit 0).

2026-07-22 — auto-purge transient superpowers artifacts at finish (feature/gitflow-auto-purge-transient)

User: transient planning artifacts (docs/superpowers/{specs,plans}) leak into develop; BDR-065 "post-merge cleanup" is DOCTRINE ONLY (no code) — manual chore, already missed once (655e364). Decision (user 2026-07-22, 2 recommended picks): keep committed-during-run (SDD worktree + reviewers read them), AUTOMATE the delete at gitflow finish. NO gitignore (would break superpowers' git add of the spec → no travel to SDD worktree). .claude/tasks/{contracts,plans} stay versioned (durable, referenced by decisions.md e.g. BDR-076). Universal via the ~/.claude/lib → repo lib symlink: every project's finish gets it.

• lib/gitflow.sh: _gitflow_purge_transient (clean-precheck → git rm → scoped commit -- paths; best-effort, NEVER aborts finish; opt-out GITFLOW_PURGE_TRANSIENT=0) wired into finish feature|bugfix pre-merge; purge-transient CLI verb.
• lib/gitflow-test.sh T17 a/b/c/d (purge+recover-from-history via --full-history+git show, no-op when absent, opt-out keeps, chore scope). Also fixed 2 pre-existing SC2034 warnings (T16 gl_out/noleaks_out).
• Gate: shellcheck lib/*.sh CLEAN + make test exit 0 (gitflow 106/0, full suite green). Universal via ~/.claude/lib → repo lib symlink (verified).
• CLAUDE.md §Transient planning artifacts: → "AUTO-PURGED by gitflow finish".
• Capitalize: BDR-065 Amendment (2026-07-22) in body + LRN-138 present (reconcile 2026-08-25).

2026-07-20 — pending merge gates (reconcile)

• merge feature/profile-managed-externals → develop (BDR-079 profile symmetry + /doc clean pass: README/USAGE/ARCHITECTURE.md) — 37c79f0
• merge chore/purge-transient-docs → develop (docs/ transient purge 655e364 + reconcile e75ea79) — reaches main at next release
• Makefile help text: profile-list help lists 5/10 profiles (:57) — 1-line hotfix. (test glob :31 FIXED — has run-*.sh, reconcile 2026-08-25) Re-verified OPEN 2026-09-01: lib/profiles/ has 10, Makefile:57 lists 5 (backend, full, seo, web-full, web missing). Re-verified OPEN 2026-09-24: still 10 vs 5 (Makefile:60 now).

2026-07-20 — profile ↔ toggle-external symmetry (feature/profile-managed-externals, BDR-079)

Audit verdict: gstack on-demand + design enable already work; DISABLE side missing — set backend leaves emil/frontend-design/design-motion/impeccable active + magic registered. Doc claims auto-toggle both ways (only enable true).

• profile.sh: MANAGED_EXTERNALS (emil-design-eng, frontend-design, design-motion-principles, impeccable — union of profile usage) + MANAGED_MCPS (magic) allowlists; cmd_set refactored to 4 trim helpers (disable_{gstack,plugins,externals,mcps}_not_in).
• profile.sh enable_skill external: from-source fallback (ln -sf skills-external/<name>) mirroring toggle-external.
• Texts: cmd_set info line, usage() NOTE (stale "NOT toggled automatically"), header; skills/profile/SKILL.md Mechanism+tradeoffs.
• Hermetic test lib/tests/profile-set-managed.test.sh — 16/0: gstack on-demand, external from-source, park/restore round-trip, magic add/remove via claude shim, non-managed untouched.
• Gate: shellcheck OK + make test exit 0 (review-guards 5/0). BDR-079 + journal + CHANGELOG done. Merged 37c79f0 (2026-07-20).

2026-07-20 — ctx7 coverage extension (feature/ctx7-coverage, BDR-078)

Close the 4 gaps from the ctx7 coverage audit: /feat //bugfix + ad-hoc coding never consult ctx7; fast-libs list hardcoded 3×; zero deterministic backstop.

• (d) lib/fast-libs.sh — single source of truth: detect + cache-status verbs; JS (package.json exact/scoped keys) + Python; 7-day cache freshness. LC_ALL=C sort (locale-independent order).
• (c) hooks/ctx7-reminder.sh — UserPromptSubmit, once-per-session sentinel, fires only when fast-libs detected; settings.json registration (2nd ctx7 surface, deliberate refinement of BDR-053).
• (a) find-docs description — before-writing-code trigger (fast-moving libs, even without a doc question) + cache-first rule in body.
• (b) feater.md + bugfixer.md — fast-lib docs rule (read fresh cache, else ctx7 fetch max 2 topics, else NOTES cache miss + proceed).
• consumers → lib: ship-feature STEP 0c, init-project STEP 5c, onboard STEP 3.5 detection blocks point at fast-libs.sh.
• lib/tests/fast-libs.test.sh (lib verbs + hook fire/sentinel/quiet) — 11/0, auto-discovered by the make test glob.
• Gate: shellcheck + make test green (review-guards 5/0). BDR-078 + journal + CHANGELOG done. Merged 8ee7d19, shipped v1.2.0.

2026-07-19 — Opus-pin dispatched judgment agents (branch feature/opus-pin-audit-agents)

Goal: session model (Fable) = orchestration + inline reflection ONLY. Every DISPATCHED subagent pinned. Reverses BDR-066 "opus pins rejected" carve-out (context changed: session now Fable → inherit burns Fable quota on audits). User approved: opus for judgment agents, drop local opus pin.

• Pin model: opus — analyzer, plan-challenger, seo-analyzer, geo-analyzer, validator-analyzer (5 dispatched judgment agents). NOT interviewer / client-handover-writer (inline-load only → pin inert; they ARE the main loop = Fable by design).
• lib/challenge-plan.md — rewrite MODEL note (was "do NOT pin").
• agents/plan-challenger.md — rewrite ORCHESTRATOR PROTOCOL model note.
• skills/onboard/SKILL.md — add model="opus" to the 6 general-purpose audit dispatches + table/description text.
• skills/tour/SKILL.md Phase B — text: analyzer opus-pinned / general-purpose with model="opus".
• skills/client-handover/SKILL.md — text: pipeline inline on SESSION model (writer inline-loaded, not dispatched).
• lib/tests/model-routing.test.sh — flip §F5 fm_lacks → has 'model: opus' (5 agents), keep fm_lacks on interviewer + client-handover-writer, update comments (BDR-076).
• .claude/settings.local.json — drop "model": "opus-4-8[1m]" (local, gitignored; Fable default from settings.json applies).
• Tests: model-routing + loops-light + shellcheck + make test.
• Memory: BDR-076 append + journal line. Commit (feat + chore); merged 17fbe51, shipped v1.2.0 (reconcile 2026-07-20).

2026-07-17 — STATUS seo/geo parity (branch bugfix/seo-geo-integrity — MERGED to develop, 92301fe; "UNMERGED" note was stale, corrected 2026-07-19 W0)

PHASE 1 — integrity: DONE 7/7. I3 8b0c98c · I1 57c67f2 · I2 4ea2fb8 · I5 64f175f · I4 e70e1d6 · I6 9da1dec · I8 acd452b. Plus 9cd7b51 (A1+A2, two process anomalies surfaced by dogfooding /harden at zenquality.fr from the wrong CWD). PHASE 2 — free wins: W3 fe93b79 · W1 a6d423b · W2 DEFERRED (see below). H1 DONE (url-guard 7d6aa09) · C1 DONE (sitemap verb, C1a/b/c). Branch MERGED to develop (92301fe), shipped in v1.2.0 (reconcile 2026-07-20).

Plan corrections made while executing (the plan was wrong 4×)

• B3 KILLED — GSC Links API does not exist. Verified against the API reference: Search Console v1 exposes exactly Search Analytics, Sitemaps, Sites, URL Inspection. A subagent hallucinated it; I doubted it in the plan and the doubt was right. (Its follow-on — "so Common Crawl is the only free source, and the 70/100 cap is mandatory" — was ALSO wrong: see B1/B2 KILLED below. Common Crawl is a 17 GB dead end, and Bing's GetUrlLinks is the only viable free source, first-party only.)
• I1 was an over-correction — "Off-page has ZERO data" was overstated (relayed from a subagent, unverified). Brand mentions ARE gathered (STEP 6). Narrowed the axis definition instead of N/A-ing it; weights untouched to avoid churning historical scores twice.
• I6 framing was wrong — I claimed 3× that the stats "drive axis weights". They do not; weight tables carry no citations. They drive Tier recommendations and, worse, land in CLIENT reports via the "Cite sources" rule. Reality was worse than my false version.
• W1 was the wrong shape — plan said "richresults verb"; a new verb means a 2nd POST to the same endpoint for a payload already received. Extended inspect() instead.
• H1 moved up (was AXE 5) — it is a PREREQUISITE of C1, not a follow-up. Today only $DOMAIN (user-typed) is interpolated. After C1, N URLs from a REMOTE sitemap flow into shell commands and fetch targets.

B1/B2 (Common Crawl backlinks) — KILLED 2026-07-17, measured not assumed

The plan said Common Crawl was the free backlink source and the 70/100 cap was therefore mandatory. Both premises are dead:

• domain-edges.txt.gz = 17.3 GB gzipped (+879 MB vertices, +2.3 GB ranks), measured live via HEAD. Finding one domain's inbound links means scanning all of it, per audit. Non-viable, and abusive toward a nonprofit.
• The implementation everyone cites (claude-seo commoncrawl_graph.py:169) caps at 500 MiB = 2.9% of the edges file, and reports what that arbitrary slice held as a backlink profile. A random sample presented as a measurement — the exact failure class this branch exists to remove. We nearly copied it.
• B2 dies with B1: nothing to cap. CONSEQUENCE: I1's narrowed Off-page axis (brand mentions only, backlinks + authority declared unauditable in §14) is the FINAL state, not a placeholder. Its §14 line was corrected — it used to point at Common Crawl as "nearest free source", which is a 17 GB dead end. RAISES W2's VALUE: Bing's GetUrlLinks is now the ONLY free viable backlink source. First-party only (never a competitor), still blocked on the client's Bing account.

W2 (Bing) — DEFERRED, blocked on a real-world test

Killed after 4 challenge rounds. User's model: client sites live on CLIENT Bing accounts, so a per-user API key means one key per client account. OAuth is the right model but is a swamp:

• Redirect URI rejects ALL local forms (http/https/127.0.0.1 — user tested)
• Refresh tokens are rotated + single-use, self-described non-compliant with OAuth 2.0 → store rewrite on every call, AND our parallel seo/geo dispatch would race the rotation → invalid_grant, dead token
• Undocumented "anti-forgery token" failure on refresh, unanswered on Q&A
• MS's own advisor recommends falling back to the API key
• Doc contradicts itself on grant_type and the token endpoint; no library REVIVAL CONDITION: a client already on Bing adds the user as a Read-Only user → test in ~10 min whether the single API key sees DELEGATED sites (undocumented, nobody knows). If yes → W2 is cheap and clean (one key, client-owned verification, revocable, read-only, zero OAuth). If no → dead. Value forgone meanwhile: Bing/DDG/Ecosia query stats + index status + first-party backlinks. Real but modest; C1 dwarfs it.

2026-07-16 — PLAN seo/geo parity vs claude-seo (superseded by the STATUS above)

Source: audit of github.com/AgriciDaniel/claude-seo (11.5k★, MIT, v2.2.0, 5 mo old, 185/197 commits single author). Verdict: cherry-pick, never install (install.sh:49 overwrites our skills/seo/; uninstall.sh:45 glob seo-*.md deletes our seo-analyzer.md 42K it never installed; extensions/*/install.sh:42 wipes settings.json on parse error; skills/seo/SKILL.md:119 injects Skool upsell footer into deliverables). Their code is real (render_page.py 428 l Playwright, url_safety.py 622 l SSRF, 326 tests, 320 pass) — adapt to our fetch.sh contract, do NOT copy wholesale (no fail-open, no tokenstore, no JSON shape).

Framing: their plus-values map onto OUR integrity gaps — report claims more than it measured. Same bar we held their README to. Seam: lib/seo-data/fetch.sh verbs (accounts|crux|queries|inspect|forget)

• fail-open {"status":"degraded"} + fixtures + tests. Everything below lands as NEW VERBS. No new architecture.

AXE 0 — Integrity (no new deps, hours) — the score currently lies

• I1 Off-page axis scores 10-15% of FULL with ZERO data source (no API, no index) → today fabricated, and it feeds /client-handover. Immediate fix: extend existing LOCAL N/A — requires FULL audit pattern to FULL, redistribute weights. Data upgrade later (AXE 3). Honesty now, data after.
• I2 VSI (Visual Stability Index) listed in CWV thresholds but NO path retrieves it — neither CrUX nor PSI expose it. Phantom signal → remove or source.
• I3 SAFETY /geo standalone: geo/SKILL.md (125 l) has no STEP 0, no confirmed-NAP collection — but geo-analyzer OWNS JSON-LD NAP. Standalone /geo on a local business can write unverified NAP with zero LRN-032 protection. Real bug, not cosmetic.
• I4 Security headers counted 3× (seo-analyzer STEP 4 scores them in Technical axis; depth-matrix.md says drop unless indexability; /harden re-audits /100 with 3 validators). Contradiction between dedup rule and agent spec → pick one owner.
• I5 Report says "audit", measured 5-15 sampled pages. State coverage % explicitly in §0 until AXE 2 lands.

AXE 1 — Free wins on auth we ALREADY have (fetch.sh verbs)

• W1 richresults verb — GSC URL Inspection already returns richResultsResult; our OAuth already carries the scope. Programmatic rich-results validation on real Google data. BEATS claude-seo: their README:314 "dual validator (Rich Results Test + Markup Validator)" is FALSE — grep of all .py = zero calls, they are hyperlinks a human clicks. Today our JSON-LD validity is LLM-read only.
• W2 bing verb — Bing Webmaster API, free. Closes the Google/Bing asymmetry (Google = full OAuth layer, Bing = manual checklist) while /geo targets ChatGPT Search, which indexes via Bing. Strategic, not cosmetic.
• W3 sameas resolution check — trivial curl loop. entity-seo.md lists "sameAs pointing to dead profiles" as a known error class and never checks it. ~10 lines.

AXE 2 — Coverage (biggest lever: ~97% of a 500-page site unseen today)

• C1 crawl verb — sitemap-driven URL discovery (we ALREADY fetch sitemap.xml) + deterministic sampling + coverage % reported. No Chromium, no paid API. Turns "5-15 LLM-chosen pages" into measured coverage. Tradeoff vs claude-seo's link-following 500-page crawl: cheaper, but misses unlinked/unsitemapped pages — accept + disclose.
• C2 Dupe/cannibalization detection — becomes possible once N pages in hand: compare titles/H1/canonicals across the set. Free, unblocked by C1.
• C3 Internal-link graph — orphan pages + 3-click depth are TODAY stated as checks with no command to compute them. C1 unblocks real computation.

AXE 3 — Off-page real (upgrades I1) — SUPERSEDED, see B1/B2 KILLED above

• B1 backlinks verb — Common Crawl hyperlinkgraph KILLED: edges file measured at 17.3 GB gzipped. Non-viable per audit; the reference impl caps at 500 MiB = 2.9% of the graph and calls the remainder a backlink profile.
• B2 Honest cap at 70/100 KILLED with B1: nothing left to cap. I1's narrowed axis is the final state.
• B3 VERIFY FIRST: GSC Links API. Subagent claimed "available, OAuth already there" — I doubt it: Search Console API v3 has no links endpoint (links report is UI-only AFAIK). Verify before planning on it. Do not assert.

AXE 4 — SPA blindness (dep decision — needs arbitrage)

• R1 render verb — Playwright, GATED on SPA detection (STEP 2 already detects framework + rendering mode). Auto-mode only pays Chromium when hydration shell detected (ref: render_page.py:226 logic, adapt not copy).
• R2 ARBITRAGE: heavy dep (Chromium ~300MB) vs our bash+curl purity. Cheaper honest alternative: on SPA, REFUSE to score on-page rather than score it wrong (today: curl reads source, not hydrated DOM → every meta/JSON-LD/heading/img grep is blind, compensated only by a §0 flag).

AXE 5 — Hardening + regression (lower priority)

• H1 SSRF guard on curl paths — both agents curl user-supplied domains. Our own CLAUDE.md doctrine says "never trust user input". url_safety.py (622 l, obfuscated-IPv4 decode, DNS pinning) is a solid reference.
• H2 drift baseline (SQLite) — SEO.md Historique keeps only date+score+ key changes. Their seo-drift is on-page regression detection, NOT rank tracking (common misread). Optional.

NOT DOING (explicit, with reason)

• Keyword volumes → Google Ads Tier 3 needs ACTIVE ad spend (~$150-300/mo); without spend the API returns buckets ("1K-10K"). Their own detect_tier() never even returns 3 (google_auth.py:642-724 caps at 2) + google-ads absent from requirements.txt. Not worth it.
• Real AI SoV (ChatGPT/Perplexity citation tracking) → paid everywhere (SE Ranking/Profound/DataForSEO). Our current honest "not testable, here's what we measured instead" disclosure BEATS faking it. Keep.
• Installing the plugin / +33 skills namespace → see destructive paths above.

Keep (already beats claude-seo — do not regress)

FR legal (LCEN/RGPD-ePrivacy/DGCCRF L121-1 — their whole repo: 2 hits, and dma-consent-mode-v2.md:27 tells the agent to stay out) · fix-bundle + ownership matrix + serial apply (their 18 agents are report-only, no ownership discipline) · trajectory-to-17/20 + honest code ceiling (theirs is flat 0-100, no legal axis) · llms.txt honest framing · NAP anti-dup-seed (LRN-032).

2026-07-16 — /close auto-persist memory (feature/close-auto-persist, BDR-068)

• STEP 5C: auto-finish chore→develop + push when capitalize/close branched off develop
• --no-push escape hatch; WORKING-branch + rc-3 skip; graceful push-fail
• aiguillage exception note + BDR-068
• merge feature/close-auto-persist → develop (human gate)

2026-07-16 — SHIPPED v1.0.0 first public release (BDR-067)

• versioning reset 4.0.0→1.0.0, CHANGELOG pre-release-history banner
• deleted v4.0.0 tag + stale release/1.0.0 branch (git-cherry: nothing orphaned)
• merged to main + develop, tagged v1.0.0, pushed origin (main=dc4f78b)
• USER: flip Gitea repo visibility to public (repo → Settings) — done (user confirmed)
• NEXT release continues from 1.0.0 (→ 1.0.1 / 1.1.0), NEVER back to 4.x (BDR-067)

2026-07-16 — model-routing edge fixes (bugfix/model-routing-edge-fixes)

Post-merge ronde (4 big-model audits: dispatch-graph INTACT, loops CLOSE, tiering CORRECT, data-flow client-handover wired). Fixing the edge findings the ronde surfaced. Branch off develop, unmerged — human gate.

• F1 (real bug) feater applier carve-out — /seo,/geo dispatch feater as L1 applier with NO CONTRACT, but feater mandates "read CONTRACT FIRST" (hotfixer has the carve-out, feater didn't) → mirror hotfixer.md:16-45.
• F5 (guard) census: lock the ABSENT model: pin on seo/geo/validator- analyzer + client-handover-writer (stray sonnet pin would silently downgrade a live audit, uncaught).
• F4 (cleanup) drop interviewer's inert model: sonnet (reflection role, inline-loaded by gated init-project) + census guard.
• F2 (tier) /refactor inline-load → true-dispatch refactorer (sonnet pin was inert). refactorer verified dispatch-safe (no Ask/Agent, input=target).
• F3 (gate) /analyze add MODEL GATE (inline-loads the analyzer reflection agent, was ungated + undocumented). census: +analyze gated, +refactor excluded.
• verify: census 57/0, shellcheck clean (my files), full suite green; NO merge.

2026-07-15 — model routing (feature/model-routing)

Spec + plan in docs/superpowers/ (transient, BDR-065). BDR-066. Branch unmerged — human gate.

• gate lib/model-check.sh + lib/model-gate.md (flip-tested) wired ×12
• pins: hotfixer/feater sonnet, analyzer un-pinned; SDD model:"sonnet"; web-validate → hotfixer L1; census guard model-routing.test.sh
• /feat re-arch: reflection inline → feater sonnet executor (partial supersede BDR-050)
• WAVE 2 (user directive): doc/status dispatch (sonnet/haiku pins effective); /hotfix split like /feat (joins gated 12→13, hotfixer dual-use executor); /commit-change → sonnet commit-changer (propose/apply, gates relocated); /release-candidate → sonnet release-executor (human gates + version decision kept in dispatcher); census 36/0. Exclusion list now commit-change/doc/status/release-candidate.
• DOGFOOD (manual, next sessions): /feat live run — plan closes decisions, dispatch carries sonnet, verify loop in main loop; gate STOP on a sonnet session (LRN-079 class, not automatable here). Also dogfood /hotfix split + /commit-change propose/apply + /release-candidate spans.
• Explore agent: kept as built-in (inherits session = opus/fable). User call — search feeds reflection, silent-incompleteness risk → deserves the big model. Custom sonnet Explore.md created then reverted (built-in already inherits + no owned prompt).
• WAVE 3 (user directive): /bugfix split + /code-clean split → reflection inline (behind existing gate), execution → sonnet executors. bugfixer = pure fix+regression exec (BUGFIX-EXEC REPORT, no Agent/AskUserQuestion); code-cleaner = PHASE-2 exec (refactor now runs on sonnet — inline-load pin was inert). Both skills STAY gated. census wave-3 + loops-light repoint (guarded). Supersedes BDR-050 bugfix carve-out.
• WAVE 4 — client-handover (branch feature/client-handover-dispatch, off develop). Shape FLIPPED to REDACTION-ONLY (full read: nested audits must run big either way since /seo,/harden,/web-validate are gated → whole-writer buys ~0 extra sonnet work for ~7 extra gate-yields). Design: parent (client-handover-writer, inline=big) keeps STEP 1-8 pipeline + ALL gates native + builds a PACKAGE; new sonnet handover-doc-writer does STEP 9-16 pure write+render, gate-free. Tasks 19-22 in plan. + MODEL GATE on skill.

2026-07-08 — full back-merge release/1.0.0→develop (chore/backmerge-release-full)

Genèse : la revue avait porté ~5/19 commits ; back-merge complet demandé. Cherry-pick par catégorie, 1 commit atomique/item, make test après chaque code. Branche non mergée (gate humain).

• A CODE (5 cherry-picks, make test GREEN chacun) : 095d881 drop find-skills (5a1fff5), a1093ca TTY-guard make-update (ce07e55, prouvé EOF exit1→exit0), 4c5e862 rtk version-guard (3049250, complète le pont e58037c déjà porté — fichiers/concerns distincts), c76479f design-motion sync (82ce02c), e65796f SC1091 lint (fcdb157, shellcheck 0 SC1091).
• B JOURNAL : cherry-pick direct conflicte (tails journal divergents) → STOP honoré, fallback note consolidée sous journal 2026-07-08. TODO /deploy ca9fa8f skip (release-specific).
• C DÉCISION/DOUBLON tous skip vérifiés : 93e43c0 attribution + ae8ad86 model (opus[1m]=Opus4.8) déjà sur develop ; a623514/74d3804/2b4e740 registres déjà backfillés (run revue) ; 188a9a7 docs → backlog /doc ci-dessous.
• D fork version 1eb5b08/eb93050 intouchés — version.txt reste 4.0.0.
• GATE FINAL : 23/23 commits release-only classifiés, 0 code orphelin, 0 entrée registre manquante ; make test GREEN + review-guards 5/0. Capitalize LRN-117 structurel.

Backlog (issu du back-merge)

• /doc — README develop ne documente pas semgrep / scan-secrets / verify+secure pipeline / ctx7 (delta de 188a9a7, non porté car base README divergente job3 + CHANGELOG version-entangled). Une passe /doc doit combler ces sujets sur le README réécrit de develop.
• release-drift advisory (LRN-117) — check qui liste les commits develop..release/* touchant du CODE fonctionnel (exclut merges, .claude/**, version.txt/CHANGELOG) pour revue de back-merge. Advisory, PAS un gate make-test dur : les cherry-picks landent avec de nouveaux SHA → le commit source reste dans le range → équivalence "déjà porté ?" non fiable automatiquement (faux positifs). Cible : étape release-finish ou /reconcile, pas run-review-guards.

2026-07-08 — review remediation (chore/review-remediation)

Genèse : .audit/review-release-1.0.0.md (revue adversariale des 9 jobs). GO user, ordre imposé. Déviation justifiée : 1 branche (pas 1/EP) car le gate fil-rouge (step 6) grep toute la surface et n'est vert qu'avec A1/A4/A5 déjà appliqués. Commits atomiques, branche non mergée (gate humain). EP-A3/A6 = décisions user tranchées (combler / option b).

• EP-A1 (BLOQUANT) trailer bugfixer/feater/hotfixer (56018df) + grep étendu = 0 autre
• EP-A2 (P0) hook réinstallé gitleaks (d4526e6) + 3 gates verts + root-cause (générateur édité, jamais réinstallé)
• EP-A4 quote YAML seo-analyzer:3 + security-auditor:3 (5a0fc16) + gate yaml.safe_load tous agents
• EP-A5 geo own-policy PERMISSIVE (f0111e1), user-approved, grep==0
• EP-A8 smoke /seo+/geo réel PROUVÉ — AUTO llms.txt + sitemap.xml atterrissent sur disque (no-op infirmé)
• FIL-ROUGE run-review-guards.sh 5 gardes (4e83f39), user-approved, à dents
• EP-A3 backfill LRN-098/101 (7cd82cf/a01250b) + EVAL-015 (38cc821) + BLK-016 (8e9ff33) + PORT rtk e58037c (416b68f) car fix absent+bug live sur develop
• EP-A6 (option b) seuil 280→320 + BDR-062 (1be9036)
• EP-A7 documentaire + M5 → EVAL-022 (capitalize cc4f161)
• Capitalize LRN-113/114/115/116 + BDR-062 + EVAL-021/022 + journal (cc4f161)
• GATE FINAL : make test GREEN (exit 0) + A2 secret BLOCKED (gitleaks) + A8 AUTO landed + review-guards 5/0
• Branche chore/review-remediation NON mergée (gate humain). Résidu noté : e65796f (SC1091 lint) non back-mergé, hors scope.

2026-07-08 — job9 sub-agent architecture corrections (chore/job9-agents)

Genèse : .audit/job9-report.md (agents/*.md frontmatter+body, verify-loop, dispatch graph, read-only). Premise correction confirmed CC v2.1.203 : nesting SUPPORTED since v2.1.172, cap 5, Agent tool required in tools: to nest. User decision: path b (version-robust) for the version-floor. One commit/item.

PART 1 — MISROUTED (trivial frontmatter):

• A — commit-changer: drop unused Agent from tools (0ede52c)
• B — verifier: pin model: sonnet (ea6c126)
• C — security-auditor: pin model: sonnet (1c270e6)
• D — plugin-advisor: haiku → sonnet (5ab6c21)
• GATE P1 — smoke green: verifier CONFORME, sec-auditor BLOCK(2), advisor ACTION REQUIRED; verdict grammar intact, mode honored. No revert.

PART 2 — VERSION-FLOOR (path b) — CONTRACT APPROVED, DONE:

• 5 — seo+geo analyzers → fix-bundle→L1 (a5a7b54/6df42e4); /seo STEP 1.5 (c498b93), /geo dispatch+apply (70fb3b4), dispatcher tier-tolerance (212f9aa); /harden already path-b (untouched), /onboard audit-only (untouched). GATE PASSED: make test green + 4 smokes (A bundle-no-edit, B AUTO lands on disk no-confirm, C GATED withheld→applied post-accord, D onboard report-only zero-fix).
• 6 — BDR-060 orchestration floor v2.1.172 supersedes implicit v2.1.83 premise (BDR-004:133 kept — auto-mode floor, append-only + factually correct). BDR-061 path-b doctrine. PART 3 — IMPLICIT-HANDOFF (tight scope, 2 sites) — DONE:
• 7 — H2 INLINE-LOAD verb @ code-cleaner + scaffolder (87d63bf/af9656f), drop unused Agent from code-cleaner
• 8 — H1 code-cleaner→refactorer named artifact .claude/audits/CODE-CLEAN-SCOPE.md

Capitalize DONE: LRN-112 (nesting) + BDR-060 (floor) + BDR-061 (path-b) + journal.

• commit-changer template Co-Authored-By stripped (5a3de92, isolated) — contradicted no-attribution ban since creation
• FOLLOW-UP next cycle: cross with J4-16 (lib-layer lock) — verify no other agent/template carries a banned attribution trailer (Co-Authored-By/ Claude-Session/--trailer) Branch unmerged, human gate.

2026-07-07 — job8 third-party security hardening (chore/job8-hardening)

Genèse : .audit/job8-report.md (magic MCP/plugins/gstack/external skills/trust chain, read-only). A/B/C/D exécutés (3 commits), branche non mergée, gate humain.

• A — permissions.ask += 4 mcp__magic__* tools, allow reste vide (BDR-059)

• B — component_builder couvert par A ; risque documenté README + LRN-110

• C — darwin-skill réinstallé pinné (tree complet, HEAD détaché SHA 7c7b790), git-commit large-scope documenté comme risque accepté (pas de patch sur code tiers pinné) — BDR-058, LRN-109

• D — pr-review-toolkit / example-skills inchangés, confirmé

• Re-audit surfaces C/D (ui-ux-pro-max, autres plugins) — single-observer CLEAN sans passe verifier (Fable-5 épuisé mi-job8), à re-vérifier au prochain cycle d'audit sécurité si le scope magic/darwin revient.

• MAGIC_API_KEY rotation toujours en attente (résiduel job7, non job8)

2026-07-07 — job7 secrets: triage backstops (chore/job7-secrets)

Genèse : .audit/job7/ALL-REDACTED.json (triage secrets multi-repo + ~/.claude). GITEA_TOKEN déjà rotaté (transcript 960bd2cf). MAGIC rotation prévue après (A). Fixtures git-game #5/#6 confirmées synthétiques (test-secret-*). Règle : jamais manipuler une valeur de secret — edits sur les mécanismes seulement.

• A.1 Provenance MAGIC_API_KEY dans ~/.claude.json : confirmée — seul writer = lib/toggle-external.sh:191 (claude mcp add magic --scope user --env API_KEY="$MAGIC_API_KEY"), appelé par install-plugins.sh (jamais un claude mcp add direct). Aucun autre writer (grep repo-wide).
• A.2 Doc Claude Code (agent claude-code-guide) : ${VAR} supporté dans env/command/args/url/headers de mcpServers, y compris scope user (~/.claude.json). Pas de envFile, pas de flag mcp add pour une référence — édition manuelle requise. Voie SUPPORTÉE retenue. Décision utilisateur : wiring MAGIC_API_KEY → wrapper claude() scopé dans ~/.bashrc (source .env en subshell, jamais exporté globalement) plutôt qu'un export global (surface minimale, cohérent BDR-026).
  • ~/.bashrc : fonction claude() wrapper (subshell source ~/.claude/.env, exec — vérifié : la var n'atteint QUE le subshell/exec, jamais le shell parent). Hors repo (dotfile perso).
  • ~/.claude.json mcpServers.magic.env.API_KEY → "${MAGIC_API_KEY}" (diff keys-only montré avant écriture ; jq surgical edit, jamais Read direct — la valeur n'a jamais traversé mon contexte). Backup fait pendant l'édition supprimé aussitôt vérifié (aurait été un 6e leak).
  • lib/toggle-external.sh:191-192 — --env 'API_KEY=${MAGIC_API_KEY}' (référence littérale, single-quoted). claude mcp add direct au flag bloqué par le classifieur auto-mode (self-modification non sollicitée, respecté) — non testé live ; claude mcp list confirme la syntaxe est bien reconnue ("Missing environment variables: MAGIC_API_KEY" — attendu, cette session a démarré avant le wrapper bashrc).
  • Doc README : section "Adding an MCP server that needs a secret" + piège --env + pattern wrapper à copier
  • Vérif manuelle : claude mcp list (read-only) — magic reconnaît ${MAGIC_API_KEY}, encore connecté (session pré-existante) ; nécessite un restart terminal (source ~/.bashrc) + Claude Code pour confirmer end-to-end — résiduel, à faire par l'utilisateur
• A.3 Scrub backups .claude.json.backup.* — les 5 originaux (78af0e36 @ job7 triage) déjà auto-rotés (ring-buffer natif) ; des 5 COURANTS, 2 encore en clair (créés avant le fix, pendant cette session) → scrubbés jq (mode 600 restauré, changé par erreur via mv). grep 78af0e36 : 0 hors .env (backups + .claude.json confirmés propres).
• A.4 Signaler à l'utilisateur : rotation MAGIC maintenant (après commit A)
• B. Redaction dumps d'env — hooks/rtk-rewrite.sh étendu : pipeline simple (pas de ;/&/||) + printenv/env en tête sans VAR=... cmd derrière → append | sed -E 's/^([A-Za-z_]*(TOKEN|API_KEY|SECRET|PASSWORD|PASSWD) [A-Za-z_]*)=.*/\1=REDACTED/'. env VAR=x cmd intact. Compound bail (;/&/||) — jamais de pipe attaché au mauvais segment.
  • lib/tests/rtk-rewrite.test.sh — 3 cas + garde compound
  • make test vert (96/96 gitflow-test + suite complète)
• C. Backstop gitleaks (8.30.1 confirmé installé — protect non listé dans --help mais fonctionne encore ; gitleaks git --staged = sous-commande documentée retenue à la place)
  • .gitleaks.toml racine — allowlist 3 classes job7 (vérifiées empiriquement contre les vrais fichiers : marketplace.json sha 40-hex, ws-protocol nonce, test-secret-[0-9-]+) + 4e entrée (^|/)\.env$ (pas un faux positif — c'est le vault canonique BDR-026 ; exclu du bruit, pas de la détection)
  • pre-commit gitflow (lib/gitflow.sh _gitflow_emit_pre_commit) — gitleaks git --staged après guard root/merge, non-bloquant si absent
  • lib/gitflow-test.sh T16 — faux secret (AKIA random) sur feature branch → bloqué ; commit propre passe ; PATH sans gitleaks → warn + pass. 96/96 vert.
  • make scan-secrets — repo (git history) + dir ~/.claude, redacted JSON → .audit/ (--redact vérifié : Match/Secret redacted dans le report, pas juste les logs). Repo : 0 (attendu). ~/.claude : 18 hits restants, 8 fichiers — voir D (5 déjà dans le triage job7, 3 NOUVEAUX non couverts par la spec initiale, à trancher)
• D. Purge (GO explicite par item) — état réel après make scan-secrets :
  • transcript 960bd2cf…jsonl (generic-api-key, GITEA déjà rotaté) — GO utilisateur → rm fait
  • ide/27929.lock — déjà rotée toute seule (fichier absent, session finie). REMPLACÉE par ide/20429.lock (NOUVEAU, session active en cours) — NE PAS rm (verrou live) ; candidat allowlist de classe (ide/*.lock structurel, pas un secret) si le pattern se confirme
  • cleanupPeriodDays — champ confirmé exact (agent claude-code-guide, code.claude.com/docs/en/settings.md) : défaut 30, min 1, scope doc = "session files" (transcripts + orphaned subagent worktrees) — PAS explicitement backups/file-history/paste-cache (gap doc, donc ne remplace pas les scrubs manuels A.3/D). Diff montré, confirmé via AskUserQuestion (1er essai bloqué par le classifieur auto-mode : diff affiché en texte ne vaut pas confirmation explicite — correct) → settings.json 30→7 appliqué.
  • NOUVEAU (hors spec initiale, découvert par make scan-secrets) : paste-cache/7d48f52c7499c1a7.txt (sourcegraph-access-token, 2) — GO utilisateur ("Claude rm maintenant") → rm fait, jamais lu. Transcript f1c9c474-...jsonl (generic-api-key, 8) — PAS choisi par l'utilisateur parmi les options (auto-inspect / TODO / rm) → laissé intact, à trancher ; ni lu ni caractérisé (règle job7). [sans objet : transcript auto-roté (cleanupPeriodDays=7), absent du disque — reconcile 2026-07-20]
  • NOUVEAU (bruit, pas un item D) : transcript de CETTE session (4b5c02a9-...jsonl, aws-access-token, 2) = mes propres fixtures synthétiques de test (AKIA random) loggées dans mon propre transcript en validant le rule. Pas un vrai secret, rien à purger.
• Gate final : make test + make scan-secrets propre + table étape/commit/gate + capitalize (BDR secrets-par-référence, MAJ BDR-026, LRN piège claude mcp add --env). NOTE : make scan-secrets sur ~/.claude ne sera pas "propre" tant que f1c9c474-...jsonl (8 hits, non tranché) reste — résiduel connu, pas un échec du job.

2026-07-05 — /deploy UX patch (feature/deploy-next-style)

Feedback user au 1er run réel (bchanot-cv, EVAL-016) : NEXT.sh une commande par ligne (style session — ssh ouvre la box, la suite s'exécute dessus, local = "(from your machine)") + hand-back AFFICHE la checklist inline (aussi aux re-hand-back). Step = bloc (header + lignes jusqu'à ligne vide), @delta gouverne le bloc entier.

• skills/deploy/SKILL.md — grammaire bloc-étape + shape rule + print inline
• templates/deploy/PROCEDURE.md — restylé session
• bchanot-cv runbook restylé, committé, pushé (bd7f6e4, develop sync)
• settings.json +inputNeededNotifEnabled (layout committé inchangé)
• Capitalize EVAL-016 + journal
• Re-dogfood run 2 (résidus bchanot-cv) : le print inline AVANT AskUserQuestion ne s'affichait PAS → leçon LRN-102 (texte avant un tool call peut ne jamais rendre ; le dernier texte du tour est le seul affichage garanti)
• PASS 2 (feature/deploy-inline-checklist) : checklist DISPLAY-ONLY — plus de fichier NEXT.sh du tout (jetable, PENDING+runbook régénèrent partout) ; hand-back TERMINE le tour par la checklist, aucun tool call après ; resume à froid = régénère + ré-affiche. Skill+template+CHANGELOG.
• Re-dogfood pass 2 VALIDÉ (deploy run 2, b24c58b marqué 2026-07-05-2) : checklist copiée depuis la conversation, deploy OK, CSP hash live sans unsafe-inline. Resume à froid + STEP 4 (learn) toujours vierges

2026-07-05 — impeccable install chain (feature/impeccable-install)

Décision (user a délégué) : COMPLÉMENTAIRES → les deux. frontend-design garde la direction esthétique au build ; impeccable (pbakaus, 43.6k⭐, Apache-2.0, actif) apporte l'UNIQUE manquant : 45 règles déterministes anti-slop (CLI impeccable detect, exit 0/2, --json — le semgrep du design, doctrine backstop-déterministe) + 23 verbes sous UN skill (/impeccable) + contexte design persistant (DESIGN.md/PRODUCT.md). Faits vérifiés : npm CLI 3.2.0 (skill dist = track séparé), skills install -y --providers=claude --scope=project --no-hooks, Node ≥ 24 requis (hôte = 22.22) → step fail-soft + décision bump Node à l'user. Classifier a bloqué npx (code tiers) → dogfood via make plugin côté user. Pattern : ctx7/machine-owned (skills-external/impeccable gitignoré, synced par installeur, symlinké par link.sh EXTERNAL_SKILLS, profils type external). PAS en GATE-BLOCK design.profile tant que Node<24 + pas dogfoodé.

• plugins.lock.json — entry impeccable pin 3.2.0
• install-plugins.sh — Step 8d staged npx install → skills-external
• update-all.sh — step miroir pin-honored (Node<24 → skip, dist gardée)
• link.sh — EXTERNAL_SKILLS += impeccable
• .gitignore — skills/impeccable + skills-external/impeccable/
• profils design/web/web-full/full — impeccable external (show design → « impeccable missing » = statut honnête pré-install)
• plugin-advisor.md + CLAUDE.md Design work + lib/design-gate.md
• README table + CHANGELOG Unreleased
• Verify — bash -n ×3 OK, shellcheck clean (SC1091 info only), lock JSON valide, profile parse OK. Dogfood DIFFÉRÉ : classifier bloque npx code tiers en auto-mode → user lance make plugin (une fois Node ≥ 24)
• Bump Node baseline 22→24 LTS (install-plugins Step 1, 24cce6a) — la dépendance dure est résolue à l'install, plus une décision différée
• Follow-up (hors scope) : doctor.sh check (fichier gardé) ; GATE-BLOCK promotion après dogfood ; dogfood réel = prochain make plugin

2026-07-04 — skill /tour (tir groupé multi-projets, feature/tour-skill)

Goal: 1 orchestrateur = clean-code + sécurité (security-auditor/semgrep [+cso si gstack ON]) + reconcile + doc, mode auto, sur 1..N projets. Boucle de convergence (fixes peuvent invalider l'audit précédent) BORNÉE 3× (LRN-083). Build via superpowers:writing-skills (TDD, pattern audit-delta/reconcile) + guidance skill-creator (structure, description trigger-pushy). Design verrouillé :

• auto = fixes committés sur chore/tour-<date> par repo (gitflow lib), JAMAIS finish/merge (signal humain only). Tree sale ou pas de develop → report-only.
• ordre par repo : sécurité → clean → re-verify (checks projet, fail=revert fail-closed) → reconcile (REPORT-ONLY, jamais d'auto-coche TODO) → doc (mode silencieux doc-syncer) → re-audit convergence.
• convergence = 1 passe complète à zéro finding nouveau + checks verts ; sinon re-boucle, max 3 itérations, résidus rapportés honnêtement.
• rapport .claude/audits/TOUR.md par repo + synthèse inline multi-repos.
• registres : offre capitalize gatée en fin, jamais silencieux.
• RED : fixture repo → baseline SANS skill. 6 gaps : TODO cible ré-écrit silencieusement ; registres écrits de façon autonome ; sécu = grep ad-hoc sans semgrep ; zéro rapport persistant ; scope creep (.gitignore + registres bootstrap) ; boucle sans borne déclarée. (Bien fait : branche gitflow via lib, pas de merge, commits atomiques, convergence passe 2.)
• GREEN : skills/tour/SKILL.md — run avec skill sur fixture-green, 6/6 gaps fermés VÉRIFIÉS sur disque (TODO zero-diff, 0 registre, semgrep chaque itération, TOUR.md committé 18 findings, 0 scope creep, 3 it. bornées convergées, chore branch non mergée)
• REFACTOR : 2 trous du GREEN patchés (scratch semgrep non trackés → auto-blocage du prochain run, STEP 3.2 cleanup ; fix sécu cassant non signalé → tag BREAKING structurel dans template). Additions template-structurelles NON re-testées par un 3e run complet (coût) — re-test au premier usage réel.
• Routage CLAUDE.md (ligne « Grouped all-axes sweep → tour »)
• Commit branche + capitalize (BDR-052, LRN-099/100, EVAL-014, journal)
• GO user 2026-07-05 : merge develop + release/1.0.0 ; settings.json restauré (Opus 4.8 1M défaut, backstop attribution conservé)

2026-07-03 — verify loops + semgrep gate + contract (chantier orchestrateurs)

Archi validée au gate (session 2026-07-03). Cible : contract sur DISQUE dès création (fichier de run, pattern DIAGNOSIS) + verifier frais (verdict structuré CONFORME/écarts, preuve-qu'il-a-regardé LRN-048, 2 échecs structurels = escalade humaine — verifier muet ≠ PASS) + gate sécu semgrep (rulesets ÉPINGLÉS p/security-audit + p/secrets — pas --config auto, classe LRN-077 ; BLOCK HIGH/CRITICAL only, LRN-047) + boucles bornées 3× décidées en boucle principale (LRN-083). cso = symlink submodule gstack → non modifiable → greffes locales (onboard cso-fallback, audit-delta, agent neuf ; complément semgrep même gstack ON). Verdicts user : dev inline conservé feat/bugfix/hotfix (verify+sécu = sous-agents frais) ; hotfix garde revert-escalade ; PIN version semgrep dans plugins.lock.json (gate bloquante — upgrade silencieux = nouveaux BLOCK sur code inchangé ; pattern gsd-pin, saut affiché par update-all).

LOT 1 — feature/semgrep-install (GO)

• plugins.lock.json — pin semgrep 1.168.0 (pattern gsd, note gate bloquante)
• install-plugins.sh STEP 7.5 — pipx pinned, command -v guard + version echo, login guide-only (jamais auto)
• update-all.sh step 6.2 — pin-honored, affichage saut cur→pin, pipx install --force
• Dogfood — install réel 1.168.0 via bloc extrait + idempotence (re-run = skip) + pin-match + saut affiché (1.168.0→9.9.9 fake, warn propre, install intacte)
• Verify — bash -n OK, shellcheck clean (SC1091 info pré-existants only), lock JSON valide ; smoke rulesets : fetch anonyme 52 règles SANS login, subprocess-shell-true ERROR détecté. Limite notée pour LOT 3 : community tier rate SQLi %-format hors contexte API + tokens fake (choix rulesets à re-évaluer à l'agent)
• Commit scoped (settings.json dirty pré-existant JAMAIS stagé) + GATE lot 1

LOT 2 — feature/contract-verifier : specs montrées AVANT écriture. lib/contract-interview.md + agents/verifier.md. LOT 3 — feature/security-auditor : agents/security-auditor.md + greffe audit-delta + onboard fallback + complément gstack-ON. LOT 4 — feature/loops-light : câblage feat/bugfix/hotfix. LOT 5 — feature/loops-heavy : câblage ship-feature + init-project + onboard. Rien poussé ; gate par lot ; suites après chaque lot.

2026-07-03 — design-toolchain trigger fix (bugfix/design-toolchain-trigger)

Root cause (NOT a kill-switch, per user): ed2408e (07-02) dropped ultra-generic tokens but left bare tokens common in non-UI talk → ~6× false-fire THIS session (design, dashboard via ecc_dashboard.py, component, frontend, theme, transition, palette). Fix = tighten the trigger only + a fire-log counter for measured re-fire decisions.

• hooks/design-toolchain-reminder.sh — drop bare design|component|composant|theme|thème|transition|frontend|front-end|palette; dashboard→\bdashboard\b; keep animation; add "front-?end design" bigram; + fire-log (time+token+excerpt)
• lib/tests/design-toolchain-reminder.test.sh — 8 dropped tokens quiet; button/navbar/landing/glassmorphism/redesign/"frontend design"/"admin dashboard"/animation fire; ecc_dashboard.py quiet; fire logged
• Verify — shellcheck + bash -n + test PASS + live dogfood (hook now quiet on session tokens)
• GATE before finish (user); sentinel one-shot to edit the now-guarded hook

2026-07-03 — config-protection hook (feature/config-protection-hook)

Goal: PreToolUse hook blocks Edit/Write to this config's quality-gate files (guardrails an agent must not weaken to make an error pass). Adaptation from ECC second-look (BDR-047 corrob, Opus 4.8 re-audit) — MY idiom (~15-line bash), NOT ECC's Node dispatcher. Extends config's own doctrine ("backstops déterministes car l'advisory s'oublie"). Guarded: settings.json (+ .claude/settings*.json), lib/gitflow.sh, .githooks/*, doctor.sh, lint configs (preemptive, absent today). Bypass: CONFIG_EDIT_OK="reason" (logged). Mid-session env caveat flagged at gate.

• hooks/config-protection.sh — case-match guarded path, exit 2 else 0; fail-open
• Guarded: settings.json(+.claude/settings*), lib/gitflow.sh, .githooks/, doctor.sh, hooks/.sh (self-guard), lib/tests/* (T6c/LRN-077), lint (preemptive)
• Bypass: one-shot sentinel .claude/.config-edit-ok (non-empty reason, logged+consumed) — NOT env-var (launch-time env = set-and-forget = garde mort)
• lib/tests/config-protection.test.sh — block/allow/self-guard/near-miss/fail-open/sentinel-one-shot/empty-refuse (17 checks)
• settings.json — register PreToolUse matcher Edit|Write|MultiEdit -> hook
• Verify — shellcheck clean + 17/17 PASS + bash -n + bootstrap-safe (hook fires on Edit/Write only, not shell cp/ln)
• GATE passed — guarded list +2 (hooks/, tests/), sentinel over env-var
• Capitalize (BDR-047 corrob + LRN-090 câblé>déclaratif) + finish this branch only

2026-06-23 — install self-sufficient + gstack on-demand par profil

Goal: make install/make plugin/make update installent TOUT sans étape manuelle. Plus le profil-driven gstack on-demand (option 1 user : gstack OFF par défaut, mais set <profil> qui a besoin de gstack l'active pour ce profil). Root causes trouvées (logs install-20260623-181416.log) :

• Bug A : install.sh lance link.sh (étape 5) AVANT install-plugins.sh (étape 6), qui n'a jamais re-lancé link.sh → symlinks npx/externes jamais créés au 1er run (LRN-022 documentait déjà le trou). update-all.sh re-link déjà (L364).

• Bug B : npx skills add + gstack ./setup résolvent leur cible relativement au CWD (repo) → darwin-skill atterrit dans $REPO/.agents/skills + $REPO/.claude/skills au lieu de $HOME/.agents/skills. Auto-entretenu une fois $REPO/.agents créé.

• Bug C : profile.sh "missing — try: bash link.sh" trompeur (link.sh ne crée pas les skills gstack) ; full.profile liste 35 skills gstack jamais posés dans skills/.

• Edit 1 — install-plugins.sh Step 8.5 : npx skills add depuis $HOME (subshell cd)

• Edit 2 — install-plugins.sh : cleanup parasites $REPO/.agents/skills + $REPO/.claude/skills (gitignorés)

• Edit 3 — install-plugins.sh : Step 10 final re-lance bash "$REPO/link.sh" (idempotent)

• Edit 4 — update-all.sh Step 7.5 : npx skills add depuis $HOME (même Bug B)

• Edit 5 — lib/profile.sh : GSTACK_SRC var + enable_skill gstack branche on-demand (symlink skills/ → skills-external/gstack/) + message honnête

• Verif — shellcheck/bash -n propres ; migré darwin → $HOME/.agents/skills + bash link.sh (skills/darwin-skill OK) ; profile.sh set full → 0 "missing", 35 gstack on-demand ; cycle minimal↔full OK ; git propre (symlinks gstack gitignorés) ; profil full restauré

• Cleanup machine courante : $REPO/.claude/skills/darwin-skill + .agents/skills VIDE restent (rm bloqué par garde permission .claude/) → auto-nettoyés au prochain make plugin [reconcile 2026-06-29 : TOUJOURS présents (fs-vérifié, darwin-skill 116K daté 23/06) — make plugin pas rejoué depuis. Reste différé, déclencheur = prochain install.] [done 2026-06-30 : make plugin rejoué EXIT=0 (npm réparé via corepack, BLK-013) → Step 8.5 a retiré les deux ; fs-vérifié ABSENTS, vrai skills/ intact (36 entrées). Boucle fermée.]

• Capitalize — LRN-042 (Bug B CWD-relatif) + BDR-030 (gstack on-demand par profil) + journal 2026-06-23

• Commit (via /commit-change) — DONE (reconcile 2026-06-29 : working tree clean, travaux shippés)

profile.sh — verbe gstack on|off

• Extraire helper enable_all_gstack() (boucle de cmd_reset) — anti-duplication
• Extraire helper disable_gstack_not_in(prof) (boucle gstack de cmd_set) — anti-duplication
• Extraire helper parked_gstack_count() (réutilise pattern cmd_current)
• Refactor cmd_reset + cmd_set pour utiliser les helpers (comportement préservé)
• cmd_gstack() : on = enable tout gstack (garde label active-profile), off = disable gstack hors profil actif
• Wire main() dispatch gstack) + usage() + bloc header
• Doc : SKILL.md argument-hint + exemples + output-policy (Makefile générique suffit)
• shellcheck propre + tests (help/bad-action/none-error/on/off cycle) — état live restauré exact
• Investigué "fix" full.profile : PAS un bug — curation par design (BDR-017 caveat). Aucun fix code.
• FOLLOW-UP (BLK-007 résolu) : linké spec (symlink chirurgical) + ajouté à full/web-full ; iOS NON linké (Linux, besoin Mac+Tailscale) ; .gitignore allowlist gstack complété (12 ajouts + checkpoint stale retiré) → gstack on git-clean ; LRN-025 capitalisé
• Capitalize : BDR-018, LRN-024, BLK-007, EVAL-002, journal 2026-06-02 + backfill index (BDR-017, BLK-005/006)

README.md overhaul

• Plan
• Corriger section install ctx7 (retirer MCP, clarifier CLI + API key)
• Marquer ruflo comme désactivé
• Supprimer section Troubleshooting/bugs courants
• Simplifier stacks tierces (gstack, ruflo, ctx7, GSD) — juste description + lien
• Ajouter section skills personnels (skills-perso)
• Ajouter section système d'autogestion (plugin-advisor, tokens, synergies)
• Nettoyer section Updating (retirer instructions manuelles par outil)
• Nettoyer section Maintenance (retirer doublon updating)
• Mettre à jour table Plugins reference (ctx7 row, ruflo OFF)
• Corriger lien USAGE.md dans l'intro (retirer mention cas/erreurs)

USAGE.md cleanup

• Supprimer tous les "Cas de figure — corrections vX.X.X validées"
• Supprimer table "Erreurs fréquentes"
• Corriger /readme → /doc dans bonnes pratiques
• Supprimer séparateurs orphelins

Skill /doc

• Mettre à jour doc-syncer.md pour gérer ajouts/suppressions de features
• Mettre à jour SKILL.md description pour mentionner feature delta

Auto-activation ui-ux-pro-max sur détection design

• Créer lib/design-gate.md — snippet réutilisable (detect design signals + ask to activate ui-ux-pro-max)
• Intégrer dans feater.md — STEP 0.5 entre scope check et mini-plan
• Intégrer dans hotfixer.md — STEP 1.5 (si CSS/style/animation)
• Intégrer dans bugfixer.md — STEP 1.5 (si bug UI/style)
• Mettre à jour plugin-advisor.md — PHASE 4 : cohérence avec le design gate
• Mettre à jour CLAUDE.md skill routing — documenter le comportement auto

Refonte agents/seo-analyzer.md

• Lire agent actuel + plugin-advisor + interviewer + feater + hotfixer + analyzer
• Réécrire l'agent complet v1 (11 étapes)
• Ajouter orchestration sub-agents (hotfixer/feater) + triage par batches
• Déplacer plugin-advisor après détection stack (STEP 3 au lieu de STEP 0)
• Ajouter 2 niveaux d'audit (LOCAL code-only / FULL live+externe)
• Adapter scoring, legal, GEO aux deux niveaux
• Renumeroter proprement (0-14) + corriger toutes les refs internes
• Commit — DONE (reconcile 2026-06-29 : working tree clean, agent seo-analyzer live)

/onboard — cso archetype-aware

Problème : prompt cso fallback est non-adaptatif — cherche XSS/SQLi/CORS même sur firmware. Objectif : charger ## Typical pain points + Surface sécurité de l'archétype et les injecter dans le prompt cso.

• STEP 4.5 → ajouter extraction de archetype-context.md (pain points + Surface sécurité + category) — validé sur firmware-embedded / nextjs-app-router / library
• STEP 6 dispatch cso fallback → re-écrire prompt : universal checks + sections conditionnelles par category (web / embedded / library / cli / infra / data / desktop)
• STEP 6 dispatch cso gstack ON → passer --archetype <name> --context-file .onboard-audit/archetype-context.md dans args
• OUT-OF-SCOPE ce fix : étendre le pattern à analyze/code-clean/doc (déjà reçoivent ARCHETYPE: <name>, juste pas le context-file). À faire dans un 2e passage si besoin.

/validate — nouveau skill W3C + WCAG (option A)

Scope : W3C HTML validity (validator.nu API) + W3C CSS validity (jigsaw API) + WCAG a11y (axe-core CLI / pa11y / WAVE API / fallback statique). Même pattern que /harden (audit par défaut, --fix avec confirmation A/B/C/D). Rapport = VALIDATE.md racine. Complémentaire à /onboard (qui audite a11y au setup initial — /validate est l'outil on-demand réutilisable).

Design décisions :

• Agent dédié : agents/validator-analyzer.md (nouveau). Pas de réutilisation de seo-analyzer — scope différent (validité syntaxique vs indexabilité).
• Depth : LOCAL (fichiers HTML/CSS statiques, tools npm locaux si dispo) | FULL (URL live + APIs distantes W3C/WAVE).
• External validators : validator.nu/?out=json (HTML), jigsaw.w3.org/css-validator (CSS), WAVE API optionnelle (quota gratuit ~100/mois), axe-cli local, pa11y-cli local.
• Tools fallback order : npm tools locaux → APIs distantes → agent général statique (cas onboard). Aucun install forcé.
• --fix conservateur : alt="" sur images décoratives évidentes, lang sur <html>, fermetures de tags manquantes, sauts de niveau heading renumérotés. PAS : labels forms, contraste couleurs, landmarks (demandent décision humaine).
• Out of scope : meta tags/SEO → /seo ; JSON-LD → /geo ; security headers → /harden ; code linting générique (ESLint/Prettier) → hors scope web standards.

Subtasks :

• Créer agents/validator-analyzer.md — spec 6 étapes (478 lignes)
• Créer skills/validate/SKILL.md — dispatcher (378 lignes)
• Ajouter routage /validate dans ~/.claude/CLAUDE.md section "Skill routing"
• Mettre à jour skills/harden/SKILL.md — W3C/a11y redirigé vers /validate
• Mettre à jour skills/seo/SKILL.md — cross-ref /validate pour W3C/WCAG
• Grep cohérence : refs /validate correctes, skill détecté par la harness

Animation lib (motion) — install + détection

Problème : motion (ex-framer-motion, rebrandé nov 2024) n'est ni installé par les scripts ni détecté par plugin-advisor / design-gate. Ajouter détection + install conditionnel.

Décisions :

• Package : motion (npm motion, import motion/react). motion-v pour Vue 3 (package séparé). Svelte/vanilla → motion.
• Éligibilité : tout projet qui peut consommer l'API. ✅ React/Next/Remix/Astro+React, Vue3/Nuxt, Svelte. ❌ Backend, CLI, embedded, Flutter, WordPress/Drupal/Strapi, RN (réservé react-native-reanimated).
• init-project STEP 5 : auto-install si éligible + absent (l'utilisateur a déjà validé scaffold).
• onboard STEP 2.5 : propose + attendre OK (projet existant, opt-in).
• plugin-advisor : read-only — détecte + reporte ("✅ motion installed" ou "ℹ️ eligible but absent — run /onboard").
• design-gate : ajouter motion/motion-v/framer-motion (legacy) dans filesystem signals.

Subtasks :

• Créer lib/animation-lib-check.sh — fonctions detect_anim_eligibility() + is_anim_lib_installed() + recommend_anim_install_cmd()
• Patcher agents/scaffolder.md PHASE 4 — note (le scaffolder n'installe PAS, l'orchestrateur init-project STEP 5e gère)
• Patcher skills/init-project/SKILL.md — STEP 5e ANIMATION LIB (auto-install si éligible)
• Patcher skills/onboard/SKILL.md — STEP 2.5 ANIMATION LIB (propose + attendre yes/skip)
• Patcher agents/plugin-advisor.md PHASE 1 (sourcing du helper) + PHASE 2 (signaux anim-lib-eligible/anim-lib-installed) + PHASE 3 (section ANIMATION LIB read-only)
• Patcher lib/design-gate.md — ajouter motion/motion-v/framer-motion + autres anim-libs dans filesystem signals
• Tester : shellcheck OK ; matrix React/Vue/RN/backend/with-motion/no-package/pnpm tous corrects

Helper --help / help sur tous les skills (option C) [WON'T-BUILD 2026-06-30 — mesuré non-rentable]

⛔ WON'T-BUILD (2026-06-30) : ABANDON tranché après mesure. RED comportemental (6 reps, /web-validate + /harden, SANS instruction) → 6/6 rendent déjà une aide riche ET s'arrêtent sans dispatcher (même /harden n'a pas lancé l'audit). Le comportement supposé absent est déjà spontané (convention universelle --help). Seule valeur résiduelle = cohérence de format (6 formats divergents) → ROI insuffisant pour ~5 lignes dans un CLAUDE.md compressé (BDR-031) sur repo mono-user. 3e état : NON "fait" (rien construit), NON "ouvert" (on ne le fera pas). L'option globale réalisait l'intention BDR-001 ; per-skill toujours rejeté. Voir BDR-001 (won't-build), LRN-080, LRN-075. Design + subtasks ci-dessous = historique, non actionnables. Problème : aucun skill ne gère --help aujourd'hui. argument-hint affiche juste la syntaxe en autocomplétion, pas de description/exemples. L'utilisateur doit lire le SKILL.md ou deviner.

Objectif : /<skill> --help (ou /<skill> help) affiche un bloc standardisé (description, args, exemples, cross-refs) et exit SANS dispatcher l'agent ni modifier quoi que ce soit.

Design :

• Lib partagée : créer skills/lib/help-handler.md — snippet réutilisable "if $ARGUMENTS contains --help|help|-h, extract frontmatter fields (description, argument-hint, cross-refs) + afficher bloc d'aide standardisé + STOP".
• Format d'aide standardisé :

  /<skill> — <titre court>
  
  DESCRIPTION
    <extrait de la frontmatter description, dépouillé des Triggers>
  
  USAGE
    /<skill> <argument-hint>
  
  ARGUMENTS
    <liste détaillée de chaque flag avec son effet — nouvelle section
     dans les SKILL.md, ou parsée depuis STEP 0 arg parsing>
  
  EXAMPLES
    <3-4 exemples concrets>
  
  SEE ALSO
    <extrait des "For X → use /Y" de la frontmatter>
  

• Intégration : ajouter STEP 0.5 ("Handle --help") dans chaque SKILL.md juste après STEP 0 parsing args. Ordre : parse args → check --help → si oui afficher + exit → sinon continuer.
• Skills à patcher : ~/Documents/claude/skills/ = ~20 skills persos + skills-perso list pour référence. Ne PAS toucher skills-external/gstack (ownership externe) ni example-skills.

Subtasks :

• [-] Créer skills/lib/help-handler.md — snippet réutilisable (détection + extraction + affichage)
• [-] Définir format d'aide standard + section "ARGUMENTS" vs reuse de argument-hint
• [-] Décider : sections ARGUMENTS/EXAMPLES doivent-elles être dans la frontmatter (nouveau champ YAML) ou dans le corps du SKILL.md (nouvelle section ## Help) ?
• [-] Patcher un skill pilote (/validate) — valider UX (désormais /web-validate — renommé e5e673a)
• [-] Patcher les skills perso restants : analyze, bugfix, code-clean, commit-change, doc, feat, geo, graphify, harden, hotfix, init-project, make-pdf, onboard, plan-tune, plugin-check, refactor, seo, ship-feature, skills-perso, status, benchmark-models, context-save, context-restore
• [-] Mettre à jour ~/.claude/CLAUDE.md — mentionner convention --help disponible sur tous les skills perso
• [-] Note : skills-external/gstack ont leur propre convention, ne pas toucher

Skill profiles (partition gstack par usage)

• Plan
• lib/profile.sh — list/show/current/apply/set/reset/diff via symlink toggle
• lib/profiles/{design,dev,qa,audit,minimal}.profile — 5 profils
• skills/profile/SKILL.md — slash command /profile
• Wire agents/plugin-advisor.md — DETECT call profile.sh current + OUTPUT line PROFILE + nouvelle section "Skill profiles" dans TOGGLING EXTERNAL TOOLS
• Wire lib/toggle-external.sh — header pointer vers profile.sh
• Makefile — targets profile/profile-list/profile-current/profile-reset
• Tests : list/show/current/diff/set/reset/apply tous OK, shellcheck propre, symlinks bien restaurés après reset

Profile system v2 — extension plugins/MCPs/CLIs

• Inventaire complet : 7 plugins (4 ON / 3 OFF), 0 MCP local, 4 CLIs installés
• Définir MANAGED_PLUGINS (ui-ux-pro-max, plugin-dev, pr-review-toolkit) + PROTECTED_PLUGINS (caveman, security-guidance, superpowers)
• profile.sh étendu : nouveau type plugin@<marketplace> (auto-toggle via claude plugin enable/disable), mcp (delegate à toggle-external.sh pour magic), cli (advisory only)
• cmd_set désactive aussi les MANAGED_PLUGINS hors profil
• cmd_reset ne touche PAS aux plugins (info line explicite — re-enable manuel ou via apply)
• cmd_current : compte enabled + installed, tiebreaker = total le plus grand
• cmd_show : colonne TYPE élargie à 30 chars pour plugin@ui-ux-pro-max-skill
• 4 nouveaux profils : web, seo, web-full, backend
• Profils existants raffinés (design, dev, qa, audit) avec plugin@<marketplace> + cli
• skills/profile/SKILL.md : table profils mise à jour + table mécanisme par type
• agents/plugin-advisor.md : table de recommandations étendue avec web/seo/web-full/backend
• Tests : set web enable ui-ux-pro-max+magic, set seo disable ui-ux-pro-max, set minimal épargne always-on, reset restaure 64 skills
• Memoire : BDR-008 (v2 décision) + journal entry 2026-05-04
• Shellcheck propre

/audit-delta — skill audit incrémental multi-axes (2026-06-11)

But : 1 skill, 4 axes cochables (conformité CLAUDE.md, erreurs/améliorations, code mort, sécurité), scope = diff depuis dernier run (marqueur SHA persistant, par axe), boucle par axe : audit → gate approbation → fix → re-vérification obligatoire avant axe suivant. Construit via superpowers:writing-skills (TDD).

• RED : baseline subagent sans skill (worktree isolé) — 7 gaps documentés (boundary par date de fichier, checkpoint en prose, pas de marqueur par axe, zéro gate, lint=verify, passe unique mélangée, registres auto-écrits)
• GREEN : skills/audit-delta/SKILL.md — pass sous pression (state file utilisé, gate tenu malgré "fix tout + meeting", marqueurs par axe OK)
• REFACTOR : trou trouvé (premier run + user injoignable, aucune règle) → patch : défaut full codebase report-only, jamais "from HEAD" ; re-test pass
• Vérif finale : skill découvrable (~/.claude/skills/audit-delta via symlink skills/), frontmatter valide, worktrees de test nettoyés
• Capitalize : BDR-020 + LRN-027 + journal 2026-06-11
• Commit (via /commit-change quand prêt) — DONE (reconcile 2026-06-29 : working tree clean, skill audit-delta live)

2026-06-11 — darwin eval: 4 confirmed bugs fix (branch auto-optimize/*-bugfixes)

• geo-analyzer.md: unreachable user → ALL file fixes report-only (STEP 12/13 triage gate)
• init-project SKILL.md: repoint readme-updater.md (absent) → doc-syncer.md x2
• analyzer.md: resolve "Update project memory" vs "Do not modify files" contradiction
• onboard SKILL.md: allowed-tools += Agent, Skill (workflow STEPs 5-7 need them)
• re-test geo fixture (unreachable) → expect zero source edits; 2 blind judges on geo-analyzer diff
• commit per fix, results.tsv rows, merge if green

2026-06-19 — cleanup/caveman-always-on (full plugin purge)

Goal: disable caveman plugin + delete every repo dep on it. Plugin.json self-declares always-on hooks → "enabled w/o always-on" impossible → full purge. Keep memory-registry terse-format rule (separate subsystem); only replace dead /caveman:compress cmd refs w/ "Legacy entries (pre-format-rule): compress manually or via claude.ai on demand." Version 3.4.0 → 3.5.0.

• RUNTIME (user, no TTY): plugin disable + uninstall caveman@caveman; mcp list check
• PHASE 2: settings.json (2 hook blocks + enabledPlugins + marketplace); hooks/ files delete; .gitignore block; session-start.sh L134
• PHASE 3: install-plugins.sh STEP 5.5; update-all.sh block; plugins.lock.json; doctor.sh; lib/detect-plugins.sh; lib/profile.sh; plugin-advisor.md; skills/profile/SKILL.md
• PHASE 4: README row; USAGE always-on line; CHANGELOG; CLAUDE.md cmd ref; skills/capitalize+prune-memory cmd refs; version.txt
• PHASE 5: shellcheck clean (SC1091 info only); full diff reviewed → committed + merged to master

2026-06-26 — coupled-capitalize invariant v1 (Frame 2)

Plan: .claude/tasks/2026-06-26-coupled-capitalize-invariant.md Goal: every dev flow commits its memory automatically (1 commit/flow) via shared include; ship-feature reordered (capitalize before FINISH = PR-bug fix). Hook v2, doc-sync twin chantier deferred. Safety in the pathspec, never git add -A.

• Task 1 — lib/memory-commit.sh + tests T1/T2/T2-bis/T3/T4/T5/T6/T7 (real exec, outputs reported) — 58cb91d + bbef41c
• Task 2 — lib/capitalize-commit.md include — b44791b
• Task 3 — wire feater/hotfixer/bugfixer/commit-changer — 2763678
• Task 4 — ship-feature reorder (capitalize before FINISH) — e8eff7e
• Task 5 — init-project founding-decisions capitalize (F5) — df60df6
• Task 6 — behavioral verify + shellcheck + CHANGELOG + BDR/LRN — this commit
• v2 — REJETÉ (pas différé) — BDR-037 (reconcile 2026-06-29) : aucun event CC ne supporte un nag de fin-de-session (Stop = par-tour, SessionEnd = debug-log only). Vrai manque = câblage, corrigé en wirant /capitalize+/close à l'include. Aucun code à écrire.
• twin chantier — doc-sync DONE (reconcile 2026-06-29) : chantier propre livré ci-dessous (2026-06-27, BDR-036). La note REFUTED était juste — doc-commit BÂTI, pas reorder-seul.

2026-06-27 — doc-sync coupled (twin of coupled-capitalize)

Plan: .claude/tasks/2026-06-27-doc-sync-coupled.md Goal: orchestrators commit the docs doc-sync patched, on the branch, BEFORE FINISH. Same PR-bug class as memory, NOT same fix: doc-syncer commits nothing (proven) → reorder + CREATE doc-commit.sh/.md (mirror memory-commit, 4 deltas). Surface-don't-block.

• Task 1 — lib/doc-commit.sh + lib/tests/run-doc-commit.sh — 24/24 real-exec pass, shellcheck clean. T1a/b/c (guard catches .claude/+CLAUDE.md, mixed→refuse-all-loud) + T2 dynamic pathspec + T3/T4/T5/T6. Exit taxonomy 0/2/3/4 (4=scope violation).
• Task 2 — lib/doc-commit.md include — 4a54a65. 4-exit report table (rc 4 = loud upstream anomaly), visible surface w/ agent-composed summary (attribution locked 3×), 2 conscious acks.
• Task 3 — agents/doc-syncer.md PATCHED_FILES: OUTPUT — fb1f359. Newline (one path/line), both STEP 9 + AUTO A4; NONE silent. Separator contract aligned producer↔consumer, argv space-safe, T7 proves it (28/28). Additive, callers unaffected.
• Task 4 — ship-feature reorder — 636b491. DOC SYNC 9→8 (+doc-commit), FINISH 8→9, HTML comment deleted. Ref-coherence: 159/189 STEP 8→9 FINISH + README:152-153 illustration completed (stale since e8eff7e). Historical records left (append-only).
• Task 5 — init-project reorder — e81f629. SYNC README 12→10c (+doc-commit), GSD 13→12, /13→/12. Order 10b→10c→11→12. Ref-coherence: USAGE ×5 (table, illustration, 3 GSD refs) each verified post-swap. Latent-bug check: none (10b was non-shifting). BLK-011 record left (append-only), TODO locator→12.
• Task 6 — ref-sweep — clean (no old headers; live refs fixed in Task 4/5; historicals left; USAGE:256 non-ordering). Caught inline-flow gap → Task 6b.
• Task 6b — wire doc-commit into feat/bugfix/hotfix DOC SYNC — 1b01b95. commit-change exempt (no DOC SYNC); hotfix wired (include no-ops on empty).
• Task 7 — close: run-doc-behavioral.md + shellcheck clean + 28/28 + CHANGELOG + BDR-036 / LRN-058-060 / EVAL-008. surface-replaces-gate + partial-init + scope-expansion engraved honestly.
• RESOLVED 2026-06-29 — BLK-010 closed by gitflow_init root commit (init-project STEP 5f): scaffold/README get a deterministic commit owner + HEAD born before the worktree step. Verified (mechanism + STEP 5f wiring + T2 test); blockers.md index+body updated.
• RESOLVED 2026-06-29 — BLK-011 closed by REMOVAL: init-project STEP 12 (speculative gsd auto-bootstrap) deleted → orphan never created. Negative diff, not commit-plumbing (LRN-072). See chantier below.
• DONE 2026-06-29 — doc-sync MINOR gate strengthened: ① shape-oracle BDR-040 + ② masked-commit fix LRN-071 (③ branch-guard deferred). See chantier below.

2026-06-29 — gitflow universal model + 6-repo migration (DONE)

Goal: universal gitflow across all bchanot/* Gitea repos. Lib built across prior sessions; migrated + hardened + dogfooded this session.

• Lib hardened at ROOT — gitflow_init socle-commit made FATAL + identity precheck + migrate_local identity guard (BLK-012 → LRN-068); 57/57 green, abort-zero-mutation proven on identity-less repo
• lib/gitflow-migrate.sh — probe (rights, not just identity) / local / remote, reversible→irreversible ordering, delete-master LAST
• Migrated 6 repos (faunosteo, config, bchanot-cv, zenquality, game, claude): master→main, develop, Option-1 protection, master deleted — each delete behind eyeball+GO, ZERO loss, no force/--no-verify, settings intact
• claude SELF-APPLIED — own committed lib migrated it; chantier landed C1 feat 167ea96 + C2 memory 1254643 + socle 620071b; hook now governs claude
• gstack submodule dirty (BLK-008 Playwright bump) excluded via submodule.ignore=dirty (LRN-070), NOT reset
• Deleted merged branches: feat/deploy-skill (local+remote) + cleanup/caveman-always-on (remote)
• Dogfood PROVEN: hook whitelists .claude/** on main + Option-1 lets owner push (commit 1620e5b)
• Capitalize: BDR-039 (Option-1 protection), LRN-068/069/070, BLK-010 closed + BLK-012, journal 2026-06-29 — committed + pushed on main
• follow-up (a) — submodule.gstack.ignore=dirty committé dans .gitmodules — DONE (reconcile 2026-06-29 : commit be1dcef sur main, mergé via hotfix/gstack-ignore-gitmodules)
• follow-up (b) — zenquality cleanup/post-smtp-fix rename <type>/<name> ou finish+delete (AUTRE repo, optionnel)

2026-06-29 — MINOR-gate strengthening (doc-syncer) [DONE — merged develop, branch deleted]

Read-first cartography refuted the literal premise: "strengthen MINOR gate" = 3 problems; the literal one (blocking gate on MINOR) contradicts engraved BDR-036. Scope: ①+②, not B, ③ deferred. Built test-first (Iron Law).

• ② fix masked commit failure — doc-commit.sh exit 5 fail-loud (LRN-071, 3rd occurrence of the swallowed-commit pattern). RED T8 proved masking, GREEN 32/32 + taxonomy (sh header/funcdoc + doc-commit.md rc-5 row)
• ① MINOR-shape oracle — lib/doc-shape.sh (BDR-040) + run-doc-shape.sh 19/19 (boundary + env-override). Wired doc-syncer STEP A4 (escalate whole set → existing SIGNIFICANT gate; no=revert all, select=keep subset) + doc-commit.md ACKNOWLEDGMENTS coherence + behavioral Scenario C/D
• shellcheck clean (doc-commit.sh, doc-shape.sh, both test harnesses); coherence ref-sweep clean
• Capitalize — BDR-040 + LRN-071 + CHANGELOG (Added/Fixed) + journal 2026-06-29 (cont.)
• FINISH — merged feature/minor-gate-strengthening → develop (0f0bd7f) on explicit signal
• [~] ③ branch-guard in doc-commit DEFERRED — duplicates protected-base predicate 3rd time (lib + hook + here); all migrated repos have the hook. Reconsider only for repos outside gitflow init

2026-06-29 — BLK-011 GSD ROADMAP post-FINISH [DONE — merged develop ce4391a, branch deleted]

User reframed: don't plumb a commit for the stranded ROADMAP — ask if gsd belongs at init at all. Read refuted both option-premises (gsd ≫ roadmap; TODO ≠ gsd ROADMAP) but conclusion A held for a stronger reason: speculative auto-bootstrap of an unused engine at creation is bad per se (LRN-072).

• Resolve by REMOVAL — deleted init-project STEP 12 (negative diff −26/+13), not a commit helper
• Ref-coherence sweep ("test" for a removal) — header 12→11-step, 10c note, 4 USAGE refs; zero dangling STEP-12 refs repo-wide
• Scope guardrails — deliberate gsd use KEPT (onboarder PHASE 6, plugin-advisor, status-reporter)
• Capitalize — BLK-011 resolved (true reason + premise trace) + LRN-072 + CHANGELOG Removed + journal 2026-06-29 (cont. 2)
• FINISH — merged bugfix/blk-011-gsd-roadmap → develop (ce4391a); develop pushed to origin (6 commits, SSH)

2026-06-29 — prune-memory hardening (RED-7/8 + index backfill) [DONE — merged develop 73e12be, branch deleted]

LAST of 3 chantiers. Read-first cartography confirmed RED-7/8 + measured 34-row index drift.

• RED-7 (example-priming) — fictionalized STEP-2 example to 9xx ids (live ids primed a wrong merge of complementary LRN-014/016); DETERMINISTIC test (run-deterministic.sh) per LRN-046. Caught its own ugrep false-green → /usr/bin/grep (LRN-074). LRN-073
• RED-8 (added-negation inversion) — consciously ACCEPTED as documented limit in BACKLOG (LRN-047); no fragile guard built
• Index backfill — 34 missing rows (decisions 11, learnings 21, blockers 2) composed + ID-sorted insert; drift 34→0, STEP-4 verify OK; moved pre-existing out-of-order LRN-021
• Capitalize — LRN-073 + LRN-074 + EVAL-010 + journal 2026-06-29 (cont. 3)
• FINISH — merged bugfix/prune-memory-hardening → develop — DONE (reconcile 2026-06-29 : merge 73e12be)
• PUSH — develop → origin — DONE (reconcile 2026-06-29 : develop == origin/develop, 0 commit en avance)

2026-06-29 — skill /reconcile (RÉCONCILIATEUR file-ouverte ↔ réel) [SHIPPED 2026-06-30 — develop aede7af, pushed]

Genèse : l'inventaire manuel du 2026-06-29 a prouvé que le TODO mentait (5 cases fait-mais-non-coché

• 1 "auto-nettoyé" qui ne l'était pas + 1 rejeté marqué "deferred"). Cet inventaire EST la spec du skill ET son cas de test de référence (résultat manuel connu-bon à reproduire).

PRINCIPE NON NÉGOCIABLE — ce n'est PAS un grep des [ ] du TODO (ça reproduirait le mensonge : dirait "ouvert" sur du fait-mais-non-coché). C'est un RÉCONCILIATEUR : confronte les sources DÉCLARATIVES à l'état RÉEL et signale les ÉCARTS. Un lister-de-todos ne vaut rien (grep le fait) ; un "le TODO prétend X, le réel est Y" vaut beaucoup.

• Sources DÉCLARATIVES : TODO.md ; BDR deferred/follow-ups/caveats ; BLK status=open|upstream ; LRN caveats "revisit if / re-run if".
• État RÉEL (oracles) : git (branche mergée/absente, commit existe, origin sync, working tree clean) ; fichier live = committé (skill/agent présent + linké = shippé) ; statut registre.

SORTIE = les 4 catégories de l'inventaire 2026-06-29 :

1. actionnable maintenant (non bloqué)
2. bloqué (condition externe — upstream)
3. différé (déclencheur conditionnel)
4. écart TODO↔réalité (fait-mais-non-coché / rejeté-marqué-deferred / "auto-fait" non vérifié)

• CONTRADICTIONS inter-registres (ex. BDR-001 accepted "pas de helper par SKILL.md" vs chantier --help qui copie dans chaque SKILL.md).
• réconciliation TODO GATED : montre les écarts, DEMANDE avant cocher/requalifier (modifie un fichier tracké → jamais silencieux).

Subtasks (à détailler au lancement) :

• Spec : table oracle-par-source (commit existe / branche absente / tree clean / skill linké / statut registre) — chaque "déclaré" a son test réel — DONE (lib/reconcile.sh : reconcile_oracle_*)
• Décider build : superpowers:writing-skills (TDD, RED = fixture TODO menteur reproduisant les 7 écarts) — DONE (RED a4872 miroir + RED-B Index-ignore à dents + GREEN comportemental a8404)
• skills/reconcile/SKILL.md — DONE (skill mince : orchestration + gate A/B/C + limites honnêtes)
• routage CLAUDE.md (triggers : "reconcile", "file vraiment vide ?", "qu'est-ce qui reste ouvert", "inventaire chantiers") — DONE (CLAUDE.md "Skill routing" + link.sh)
• Détecteur de contradictions inter-registres (BDR accepted vs chantier qui le contredit) — DONE (reconcile_contradiction_candidates ; surface, n'asserte pas)
• Gate de réconciliation (diff TODO proposé, A/B/C confirm avant edit) — DONE (SKILL.md "The gate" ; registres read-only)
• Test final = reproduire l'inventaire 2026-06-29 (cat. 1-4 + contradiction BDR-001) comme oracle — DONE (run-reconcile.sh 20/20, fixtures neutres, RED prouvé rouge avant le vert)
• SHIPPED 2026-06-30 : feat 82e6322 + mémoire 6b512be → merge aede7af (feature/reconcile-skill supprimée) → poussé origin/develop. main intact. BDR-041 + LRN-075/076/077 + EVAL-011 capitalisés.

[SHIPPED 2026-06-30 — develop 0c0b748, released v4.0.0 (tag v4.0.0)] skill /release-candidate — orchestrateur gitflow release

Pertinent maintenant : develop ahead de main, prochaine étape gitflow = release. VÉRIFIÉ dans lib/gitflow.sh (2026-06-30) — release CÂBLÉE, pas que hotfix :

• start base=develop (gitflow_base_for L49) ; gitflow start release <ver> positionne sur la branche (L71).
• finish fan-out (gitflow_finish L108-111) : merge main + merge-back develop + delete (locale, _gitflow_delete L96).
• GAP CONFIRMÉ (grep clean) : AUCUN git tag ni bump version dans tout gitflow.sh → la mécanique merge mais ne tague PAS.

Design (à la conception) : ORCHESTRATEUR au-dessus du gitflow existant — NE PAS réécrire la mécanique.

• gitflow start release <ver> (depuis develop) → positionne.
• prep sur la branche release : bump VERSION + CHANGELOG (Keep-a-Changelog) + RC fixes.
• gitflow finish (merge main + merge-back develop + delete — déjà câblé).
• FOURNIR le tag manquant : git tag sur main au merge-commit (le seul morceau absent de la lib).
• push gaté (ASK, LRN-069) : main + develop + tag.

Subtasks (à détailler au lancement) :

• Décider : tag fourni par le skill au-dessus de gitflow (mécanique non réécrite) — d3d6ced, BDR-042
• skills/release-candidate/SKILL.md — orchestration start→prep→finish→tag→push(gaté) + gate humain "WHEN to release" — présent (d3d6ced)
• routage CLAUDE.md — présent (~/.claude/CLAUDE.md "Cut a release → release-candidate")
• test — prouvé par la release réelle 4.0.0 : fan-out main (709facf) + develop (4a00a60) + tag v4.0.0

Auto-déclenchement des skills par intention [WON'T-BUILD 2026-06-30 — mesuré : Claude discrimine déjà (3 classes)]

⛔ WON'T-BUILD (2026-06-30) : 3e moot de la série (après BDR-001 --help + BDR-043/LRN-082 darwin re-baseline). Cartographie : routing = STACK L0(design-hook)→L1(superpowers « 1%→MUST invoke », dominant)→L2(prose CLAUDE.md)→L3(frontmatter)→L4(BDR-019). L1 SUR-détermine déjà l'invocation → « auto-call ? » = déjà oui. Reframe C : la vraie question = DISCERNEMENT, risque inversé under→OVER-routing. Mesure en VRAIES sessions fraîches (8 prompts / 3 classes) : CLEAR→route ✓, AMBIGUË→demande (refuse de deviner, investigue pour une question utile) ✓, TRIVIALE→s'abstient ✓. Le sur-routing soupçonné (L1 vs règles Workflow) NE se matérialise PAS — le modèle équilibre. Prose de bornage L2 = valeur fantôme + risque de DÉGRADER un discernement déjà bon. Voir BDR-044 (reframe + verdict), LRN-083 (RED sous-agent invalide), LRN-080 (mesure-first, corroboré 3-in-a-row). RED sous-agent initial (0/6) RETIRÉ comme non-discriminant (plancher artefact). Design + subtasks ci-dessous = historique, non actionnables. ⏭️ (historique) NEXT, mais CADRÉ : pas de design avant la mesure. Jumeau méthodologique de BDR-001 --help (won't-build après RED) — même piège architectural, même garde-fou LRN-080 (mesurer avant d'instruire) + LRN-049 (borner le bruit avant le marqueur). Les subtasks ci-dessous s'arrêtent à la mesure ; le design ne s'ouvre QUE si le RED valide la valeur.

Contrainte architecturale (établie pour --help, non négociable) : Aucun mécanisme n'intercepte le message utilisateur pour lancer un skill. La harness ne route pas avant que le modèle réponde — un skill n'est invoqué QUE par le modèle (outil Skill). Donc « auto-call déterministe » = IMPOSSIBLE. Le seul levier sur l'invocation elle-même = instruire le MODÈLE à reconnaître l'intention et appeler le bon skill → conformité-modèle, PAS déterminisme. C'est une instruction de routage CLAUDE.md, pas un mécanisme.

• Nuance (raffinement) : une couche déterministe existe en amont du call, pas sur le call — un hook UserPromptSubmit peut détecter un signal et INJECTER un rappel de routage (le design-toolchain hook fait déjà exactement ça pour l'UI ; le banner session-start aussi). Détection déterministe + injection advisory ; le modèle reste celui qui tire. MAIS sur des verbes d'intention (« corrige », « crée », « bug »), un hook keyword serait BRUYANT (ces mots sont partout) — le design-hook s'en sort car « design/UI » est un signal rare. Donc le levier hook est probablement non-viable pour le cas large → ce qui renforce le besoin de borner aux signaux rares/non-ambigus.

Substrat déjà en place : BDR-019 a retiré disable-model-invocation repo-wide → le modèle PEUT déjà self-router vers les skills (défaut = activé ; user l'avait vécu live : intention feature détectée, ship-feature voulu, jadis bloqué). Et la section « Skill routing » de CLAUDE.md existe déjà. Donc la baseline du RED = le routage CLAUDE.md ACTUEL tel quel ; le chantier n'a de valeur que si le RED prouve que cette prose SOUS-déclenche sur intention claire (exactement la logique --help : baseline = convention déjà là, question = est-ce qu'instruire en plus change quoi que ce soit).

Le chantier COMMENCE par (rien d'autre avant) :

• (a) Cartographier le routage CLAUDE.md actuel — quels signaux → quels skills sont déjà censés router (« Skill routing » + « Design work » + descriptions de skills). État des lieux factuel, pas de jugement.
• (b) RED comportemental (LRN-080) — prompts d'intention IMPLICITE, naturalistes, SANS instruction renforcée : « il y a un bug, debug », « on va créer X », « corrige ceci », « refactor ce module », « cut a release »… → le modèle invoque-t-il le bon skill, ou fait-il la tâche à la main en ignorant le skill ? N reps, plusieurs intents distincts.
  • Garde-fou RED : ne PAS amorcer. Sessions fraîches / sous-agents, prompts naturels, zéro mention de « skill » / « routage » / « test » dans le prompt mesuré (sinon le modèle route parce qu'il SAIT qu'on le teste — contamination). Le RED --help était mécanique donc peu sensible à l'amorçage ; l'intent-routing l'est beaucoup plus → rigueur supérieure requise.
• (c) Décider selon le RED :
  • déjà bon (comme --help) → chantier MINCE, voire won't-build ; capitaliser le constat (3e état : mesuré non-rentable, ni fait ni ouvert).
  • sous-déclenche → vraie valeur : renforcer la prose de routage (levier modèle) sur signaux CLAIRS uniquement — PAS un hook keyword (trop bruyant, cf. nuance ci-dessus).

Scope à border au cadrage — NE PAS faire « tout skill jugé pertinent » : Tension réelle proactif vs intrusif. Auto-déclencher feat/bugfix sur intention CLAIRE et non-ambiguë = sain. « Déclenche tout skill jugé pertinent » = RISQUÉ (faux déclenchements, skills non sollicités, flux interrompus). Réglage cible (LRN-049 borner le bruit) = déclencher sur signaux d'intention CLAIRS et non-ambigus ; ambigu → DEMANDER, pas auto-déclencher. À définir précisément SI (et seulement si) le RED valide : table signal → skill + la frontière exacte de l'ambiguïté.

2026-06-30 — session-close follow-ups (promoted from BLK-013 / BDR-043)

• (a) Harden install-plugins.sh Step 1 — guarantee npm on apt-nodejs hosts (detect missing npm + corepack enable npm), not just check node >=22. Fix-forward for BLK-013 — stops make plugin Error 127 recurring on any fresh apt machine. [done 2026-07-01 : unconditional npm guard after Node block (corepack enable npm → distro install npm fallback → fatal exit 1 w/ clear msg). Catches node>=22-present-but-npm-absent (NODE_OK short-circuit). shellcheck clean, bash -n OK. Fresh-apt live validation pending (no npm-less host to hand). branch bugfix/install-plugins-npm-guard.]
• (b) Re-baseline darwin on the 5 ex-broken gstack skills (benchmark-models, context-restore, context-save, make-pdf, plan-tune) — now repaired and back in scope (BDR-043, trigger cleared). Verify results.tsv still marks them status=error first. (Promoted from BDR-043's action-field — not an item the user authored.) [resolved-MOOT 2026-06-30 : won't-run. BDR-043 cleared only motif (a) of BDR-015's TWO exclusion grounds (symlinks repaired ✅); motif (b) external-ownership INTACT — the 5 resolve to skills-external/gstack/ (submodule), darwin optimizes by EDITING SKILL.md → would dirty the submodule (forbidden LRN-070). Re-baseline = unactionable score. + results.tsv gone (wiped by 23/06 make-plugin reinstall) → not even a re-baseline, a fresh-from-zero one. Geometric trigger lifted, value trigger intact — twin of --help LRN-080. See LRN-082. Not "done", not "open": MOOT.]

2026-07-03 — bugfix/gitflow-finish-args (contract fix + doctor false-warns)

Root: audit 2026-07-02 residuals. gitflow_finish ignores its args (merges CHECKED-OUT branch) → LOT3 mis-merge trap; + 3 doctor false-warns (LRN-047 class).

• (1) lib/gitflow.sh gitflow_finish — optional ; error rc2 if != current branch ("operates on current branch X, you asked Y — checkout Y first"). No-args unchanged. Commit d9fdd4c. BLK-015 LRN-089.
• (2) lib/gitflow-test.sh — T12 arg-guard: arg-mismatch → nonzero + message names both; arg-match → merges as before. +7 assertions (71/71). T12 (not T6c — reconcile collision).
• (3) doctor.sh cargo line — false "(RTK unavailable)" → optional info (RTK prebuilt).
• (4) doctor.sh check_symlink — PASS iff canonical path under $REPO (direct OR via symlinked ancestor dir); hooks/session-start.sh false-warn gone. Commit 6778b9f.
• (5) doctor.sh §2 gstack — counts 34 per-skill symlinks; mythical [ -L skills/gstack ] dropped.
• (6) doctor.sh token § — denominator 11000→CONTEXT_WINDOW=200000, thresholds 15/25, comment anchored to measured ~11.4k (LRN-088). False "92% CRITICAL" → ~5% comfortable.
• Verify — suites green (71/13/32/19/20/13 + RC 5/5); doctor 0 false-warn; shellcheck clean. +docs(changelog) Unreleased entry (706abff). Gate passed on GO 2026-07-03. Finish pending.

2026-08-24 — contract gates: plancher déterministe (feature/contract-gates)

Source: analyse du skill unlazy (Leonxlnx/unlazy, 2.1.0). Verdict: son architecture de vérification n'apprend rien (contrat+verifier frais+boucles bornées ⊂ déjà en place). Le trou réel: entre l'exécuteur et GATE 1 il n'y a aucun plancher déterministe — GATE 1 est un dispatch LLM, et PROOF: est une ligne que le verifier ÉCRIT (rien ne l'empêche structurellement de la produire sans rien exécuter). Palier 2 retenu (user, 2026-08-24).

PRIS d'unlazy: critère porteur d'oracle exécutable (CHECK/EXPECT/EVIDENCE), fail-closed (exit 0 ET marqueur), evidence pending = NOT-MET, ABANDON: <id> <raison> comme handoff visible non supprimable, les 4 règles d'écriture de gates falsifiables, la discipline 4 passes. REFUSÉ: Stop hook decision:"block" (contredit "STOP + escalade humaine" et "merge sur signal humain"), approval store ~/.unlazy/approved (résout l'exécution de ledgers hérités non fiables — pas notre menace), arbre .unlazy/<scope>/ (4e arbre de bookkeeping ⇒ mort de la config), tree N (désavoué par ses propres docs), le checker Node 28k (stack lib = 100% bash, Health Stack = shellcheck).

• W0 branche feature/contract-gates depuis develop (via lib/gitflow.sh)
• W1 lib/gates.sh — parse ACCEPTANCE CRITERIA, exécute fail-closed (exit 0 ET EXPECT), réécrit EVIDENCE dans le contrat. Sous-commandes run (exécute+écrit) / status (parse seul, jamais d'exécution, jamais d'écriture). rc 0=MET · 2=UNMET/malformé · 3=ABANDONED.
• W2 lib/contract-interview.md — STEP 3 gagne CHECK/EXPECT/EVIDENCE optionnels par critère + les 4 règles de falsifiabilité; template mis à jour; ABANDON dans Lifecycle; ligne de poids par flow.
• W3 agents/verifier.md — EVIDENCE fail-closed (coché+pending = NOT-MET), bucket ABANDONED, verdict CONFORME impossible si abandon présent.
• W4 lib/verify-secure-loop.md — GATE 0 déterministe avant GATE 1 (rouge ⇒ re-dispatch exécuteur sans brûler un verifier).
• W5 agents/feater.md + agents/bugfixer.md — discipline 4 passes.
• W6 lib/tests/gates.test.sh — comportemental sur gates.sh (fail-closed, exit≠0 avec marqueur = FAIL, pending, ABANDON, malformé, status n'exécute pas) + locks de structure sur W2/W3/W4/W5.
• W7 shellcheck + bash -n + make test complet.
• W8 CHANGELOG + registres (BDR + LRN + journal).
• W10 restatements skills : bullet GATE 0 dans feat/bugfix/ship-feature/ init-project (+4 locks, flip-testé) ; ligne hotfix du tableau de poids corrigée (aucun floor à ce poids). 2026-08-24.
• W11 RED comportemental : 16/16 runs frais non-amorcés conformes (verifier ×9, feater ×2, orchestrateur ×5) → EVAL-027. 2026-08-24.
• W9 merge sur signal humain explicite (2026-08-24, "merge dans develop").

Won't-build-now — Palier 3 unlazy (OWNS/leases), trigger documenté : Différé volontairement (BDR-083) : tous les dispatches parallèles actuels sont read-only — le problème (2 exécuteurs ÉCRIVAINS concurrents) n'existe pas. Pattern LRN-080 : ne pas construire sans menace mesurée. TRIGGER = le jour où un flow dispatche ≥2 exécuteurs écrivains en parallèle : (1) FILE SCOPE du contrat = déclaration OWNS (champ existant, zéro format neuf) ; (2) ~40 l dans gates.sh ou lib/owns.sh — intersection CONSERVATRICE des FILE SCOPE des contrats actifs avant fan-out, conflit possible → refus + dispatch séquentiel (pas de locks disque tant que l'orchestrateur est unique) ; (3) locks + tests.

2026-08-24 — tour multi-projets en parallèle (feature/tour-parallel)

User (gate 2026-08-24): "tout paralléliser (option 2) mais bien garder la sélection des modèles — orchestrateur garde le modèle orchestrateur, les skills/agents suivent leurs orchestrateurs définis". Preuve mécanique préalable: probe imbriquée 3 sous-agents, fenêtres chevauchantes, 9.1s vs ~18s séquentiel. Dérogation LRN-083 (boucle de fix par projet déplacée dans un runner dispatché) → à consigner BDR-084. Repos indépendants, branches chore par repo, report-as-approval-gate ⇒ rien de partagé n'est décidé dans un runner; capitalize reste main-loop.

• T1 skills/tour/SKILL.md — STEP 0 routé (1 projet = inline inchangé; ≥2 = fan-out) + STEP 0b: un runner general-purpose par projet, TOUS dans UN message, SANS pin modèle (hérite session, model-gate déjà passé); agents internes gardent leurs tiers définis; runner mort = ligne RUNNER FAILED, jamais absent silencieux; capitalize main-loop.
• T2 locks census §12 dans lib/tests/model-routing.test.sh (fan-out présent, runner non-pinné, single message, capitalize main-loop).
• T3 BDR-084 + CHANGELOG + journal.
• T4 make test rc 0 + shellcheck clean (SC2016 silencé, littéral voulu). Merge NON fait — gate humain.