chore(memory): prune 2026-10-06 — BLK-028 merge, bounded caveman pass on 37 entries

2026-10-06 15:40:26 +02:00
parent 6bc7c12bf3
commit a84aaaabbd
5 changed files with 104 additions and 94 deletions
@@ -38,8 +38,8 @@ rules:
 | BLK-016 | 2026-07-04 | rtk compression PATH-dead 30 days — 6/5070 Bash commands compressed (~460K tokens missed); installer sources cargo env so its own check passes, Claude tool shell never gets ~/.cargo/bin | resolved |
 | BLK-017 | 2026-07-17 | Bing Webmaster API unusable for a multi-client agency: OAuth swamp (localhost redirect refused, rotated single-use refresh tokens race our parallel dispatch), API key = wrong model (client-owned sites) | open/deferred |
 | BLK-018 | 2026-07-20 | release-executor finish span blocked by permission classifier (human signal invisible to subagent) — 2026-07-… | open |
-| BLK-019 | 2026-09-01 | notify-attention bell silent, toast OK (VS Code client default) — 2026-09-01 | resolved |
+| BLK-019 | 2026-09-01 | notify-attention bell silent, toast OK (VS Code client default) — 2026-09-01 | superseded by BLK-028 |
-| BLK-020 | 2026-09-02 | notify-attention: both channels dead on one VS Code client — 2026-09-02 | resolved |
+| BLK-020 | 2026-09-02 | notify-attention: both channels dead on one VS Code client — 2026-09-02 | superseded by BLK-028 |
 | BLK-021 | 2026-09-22 | Bash tool dead mid-session ("every command exits 1"): /tmp usrquota blown by a dead session's probe HOMEs — 2… | open |
 | BLK-022 | 2026-09-22 | `hooks/guard-bash.sh` withheld by the safety classifier; executable spec shipped instead — 2026-09-22 | open |
 | BLK-023 | 2026-09-28 | floor-guard SKIP pattern `xit(` (Jasmine) matches any `exit(` in python/JS test helpers → false ECARTS; workaround: no `exit(` in inline python, bash derives rc from output — 2026-09-28 | resolved |
@@ -47,6 +47,7 @@ rules:
 | BLK-025 | 2026-09-30 | deny rule `Bash(npm install -g *)` bypassed unknowingly by the alias `npm i -g` (pasted user instruction ran as typed); deny patterns are literal prefixes — 2026-09-30 | resolved (partial) |
 | BLK-026 | 2026-10-06 | `make test` red on macOS: 13 suites, GNU-only idioms in suite + 7 libs (SIGPIPE under pipefail, `sed -i`, `wc` padding, `stat -c`, `realpath -m`, bare `timeout`, `grep -oP`) | resolved |
 | BLK-027 | 2026-10-06 | this machine never ran `make link`/`make plugin`: no global `core.hooksPath` → post-commit push never fired, branches landed ahead of upstream; 11 vendored skills + `~/.claude/.env` missing | resolved (link) / open (plugin) |
 | BLK-028 | 2026-10-06 | notify-attention on a VS Code client: bell + toast silent-degradation faults (merge of BLK-019 + BLK-020): terminalBell sound default off, ext hooks only terminals born after activation, Code muted in Windows mixer | resolved |
 ---
@@ -296,3 +297,11 @@ rules:
 - **Real cause**: `make link` never run on this Mac → `core.hooksPath` unset (local + global), `~/.claude/githooks` absent. `gitflow start` pushes explicitly so branch creation looked fine; commits rely on the post-commit hook. `make link` also reports `make plugin` never ran (11 vendored skills absent) and `~/.claude/.env` missing.
 - **Solution**: pushed both branches by hand; `make link` run (user go) → `core.hooksPath=~/.claude/githooks`, 4 hooks installed. `make doctor` "Git hooks" section flags this; run it first on a new machine.
 - **Status**: resolved for hooks; open: `make plugin` + `.env` on this machine (user action).
 ## BLK-028 — notify-attention on VS Code client: three client-side faults, one probe order (merge BLK-019 + BLK-020) — 2026-10-06
 - **Friction**: hook fires, server side clean, yet bell and/or toast silent on a VS Code client over SSH. Looks like half-broken hook. Two machines, three distinct faults.
 - **Real cause (3 faults, all client-side)**: (1) VS Code `accessibility.signals.terminalBell` defaults `"auto"` = sound OFF unless screen reader active (BLK-019). (2) ext `wenbopan.vscode-terminal-osc-notifier` parses only terminals created AFTER its activation: claude terminal born before install never hooked, toast dead (BLK-020 fault A). (3) Windows per-app volume mixer, Code entry at 0: toast still audible because Windows shell emits that sound, not Code → masked plain app mute (BLK-020 fault B). Not a hook bug; not dtach (dtach broadcasts to every attached client, zero session loss).
 - **Solution**: client settings.json `"accessibility.signals.terminalBell": { "sound": "on" }`; install ext THEN start or re-attach claude (`dtach -a ~/.dtach/<sess>` from a fresh terminal); raise Code volume in Windows mixer (mixer lists app only after it tried playback → hit preview first). Per-client-machine, not repo-portable.
 - **Probe order (do FIRST, before server archaeology)**: fresh VS Code terminal, `printf '\a\a\033]777;notify;Test;hello\033\\'` → splits terminal path from client renderer; palette `Help: List Signal Sounds` → Terminal Bell preview bypasses terminal/BEL/hook/dtach/ext, isolates renderer audio in one step.
 - **Status**: resolved (BLK-019 2026-09-01, BLK-020 A+B 2026-09-02/03). Sources superseded by this entry; bodies kept for history.
 - **Reference**: `~/.claude/hooks/notify-attention.sh` header documents the setting; [[LRN-145]] terminalSequence-not-/dev/tty; silent-degradation class [[LRN-047]]; sources [[BLK-019]], [[BLK-020]].
@@ -982,9 +982,9 @@ rules:
 ## BDR-062 — supersede BDR-031's 275-line CLAUDE.md target: 305 is the assumed reality
 - **Date**: 2026-07-08
 - **Status**: accepted (supersedes the 275-line density TARGET of [[BDR-031]] only; BDR-031's core principle — lightening = compression, not path-scope/externalization — stands unchanged)
- **Decision**: global CLAUDE.md sits at 305 lines, stays there. job1's density pass took it 319→305 and no later job re-inflated it; the extraction BDR-031 called for is done. Old 275 target (or the 280 guard) now costs clarity more than it saves tokens. The `hooks/session-start.sh` guard threshold is realigned 280→320: still catches genuine regression (real bloat past 320) but stops firing a permanent "density pass requis" warning on an assumed-final 305.
+- **Decision**: global CLAUDE.md sits at 305 lines, stays there. job1's density pass took it 319→305 and no later job re-inflated it; the extraction BDR-031 called for is done. Old 275 target (or 280 guard) now costs clarity more than tokens saved. `hooks/session-start.sh` guard threshold realigned 280→320: still catches genuine regression (bloat past 320), stops firing permanent "density pass requis" warning on assumed-final 305.
 - **Why**: the review (`.audit/review-release-1.0.0.md` A6) found the guard had warned every session since job1 without the target ever being met — a self-inflicted permanent warning, not an actionable signal. A gate that never goes green trains you to ignore it. Realign to reality; 15-line margin keeps real regressions visible.
- **Alternatives rejected**: (a) finish the compression 305→≤275 — the remaining lines are load-bearing constraints, not filler; further squeeze loses clarity for a marginal token gain on a solo repo. (b) leave the guard at 280 and accept the permanent warning — a permanently-red non-blocking gate is noise. (c) rewrite BDR-031 — registries append-only; supersede the target, keep the principle.
+- **Alternatives rejected**: (a) finish the compression 305→≤275 — the remaining lines are load-bearing constraints, not filler; further squeeze loses clarity for a marginal token gain on a solo repo. (b) leave guard at 280, accept permanent warning — permanently-red non-blocking gate is noise. (c) rewrite BDR-031 — registries append-only; supersede target, keep principle.
 - **Reference**: `hooks/session-start.sh:202-211`; supersedes the 275 target in [[BDR-031]] (principle kept). Review remediation A6, 2026-07-08.
 ## BDR-063 — GSC multi-account: OAuth2 installed-app flow + label-keyed token store
@@ -235,9 +235,9 @@ rules:
 ## EVAL-021 — adversarial review of the 9-job series (release/1.0.0..develop) + remediation
 - **Date**: 2026-07-08
 - **output**: read-only adversarial review — 11 analyzers (1/job + validator-analyzer contract) + fresh-context verifier on 6 top findings + make test. Report `.audit/review-release-1.0.0.md`: 1 BLOQUANT (A1 trailer), 5 à corriger (A2 gitleaks hook inert, A3 back-merge gap, A4 YAML, A5 geo attribution, A8 smoke-A), 5 mineurs, 10 verified false-positives; jobs 4/5/6/8 CLEAN, validator-analyzer contract SOUND. Remediation (chore/review-remediation): A1/A2/A4/A5 fixed, A8 PROVEN (both /seo+/geo AUTO items land on disk via L1 — no silent no-op), fil-rouge guard added, A3 backfilled + rtk fix ported, A6 threshold realigned.
- **method**: analyzers write findings to scratch; main loop does the inter-jobs cross-pass + memory-sequence + trailer sweep + cost check; verifier re-derives 6 findings from scratch. Sandbox gotcha logged: `git log | grep` truncates silently → used `git rev-list`.
+- **method**: analyzers write findings to scratch; main loop does inter-jobs cross-pass + memory-sequence + trailer sweep + cost check; verifier re-derives 6 findings from scratch. Sandbox gotcha logged: `git log | grep` truncates silently → used `git rev-list`.
 - **anomalies**: (1) 2 sub-agent verdicts overturned — job7 CLEAN was wrong (gitleaks hook not wired, [[LRN-114]]) and the contract-agent's tool-grant "defect" was a false-positive ([[LRN-115]]). (2) A8 smoke-A root cause was undocumented in 212f9aa; reconstructed live — dispatcher classifies by batch-id (seo A/B/C, geo G1-G7), tolerant of header wording so items aren't dropped; path-b proven to land AUTO fixes on disk. (3) A7: job1/3f639b3 broke the design-hook oracle ~10h until job2/860b803 — historical; lesson = run make test before merging a branch, not only at finish.
- **action**: keep. Remediation branch unmerged (human gate). Fil-rouge guard now prevents the partial-fix class ([[LRN-113]]).
+- **action**: keep. Remediation branch unmerged (human gate). Fil-rouge guard now prevents partial-fix class ([[LRN-113]]).
 ## EVAL-022 — job9 model pins (BDR-060) were smoke-tested but never recorded as an EVAL (M5 trace)
 - **Date**: 2026-07-08
@@ -293,10 +293,10 @@ Dogfood: 3 blind lenses attacked the v1 plan for the plan-challenge feature itse
 ## EVAL-029 — 4-agent plan challenge: 6 BLOCKERs, and the fix round produced 3 of them
 - **Date**: 2026-09-15
- **Method**: 3 blind lenses (correctness / robustness / simplicity) on plan rev 1, then 1 confirmation lens on rev 2. Subject = the gstack Playwright lib plan ([[BDR-088]]).
+- **Method**: 3 blind lenses (correctness / robustness / simplicity) on plan rev 1, then 1 confirmation lens on rev 2. Subject = gstack Playwright lib plan ([[BDR-088]]).
- **Result**: rev 1 → 3 BLOCKER + 12 MAJOR. Rev 2, written specifically to close them → 3 NEW BLOCKERs, and 2 of the 3 were INTRODUCED BY the fixes: the new "every public function returns 0" rule contradicted the new "return rc", and the printer-name clause came verbatim from my own contract criterion 9. Rev 3 dropped the recovery branch entirely at the human gate — 6 findings closed by deletion instead of code.
+- **Result**: rev 1 → 3 BLOCKER + 12 MAJOR. Rev 2, written to close them → 3 NEW BLOCKERs, 2 of 3 INTRODUCED BY the fixes: new "every public function returns 0" rule contradicted new "return rc"; printer-name clause came verbatim from my own contract criterion 9. Rev 3 dropped recovery branch entirely at human gate — 6 findings closed by deletion instead of code.
- **Anomaly**: my first user-facing answer asserted ~654 MB of orphan Playwright revisions. FALSE — `.links` showed every dir referenced, 0 reclaimable. Caught only while designing the guard, not while asserting the number. Worse, the guard I proposed would itself have deleted gsd-pi's rev 1243.
+- **Anomaly**: first user-facing answer asserted ~654 MB orphan Playwright revisions. FALSE — `.links` showed every dir referenced, 0 reclaimable. Caught only while designing the guard, not while asserting the number. Worse, proposed guard would itself have deleted gsd-pi's rev 1243.
- **Action**: (1) never state a disk-reclaimable figure before reading the registry that owns it ([[LRN-151]]). (2) A fix round deserves the same challenge as the original plan — 3/3 confirmation BLOCKERs came from fixes, not from the original. (3) The confirmation pass earned its cost: without it the printer override would have shipped and silently disconnected doctor's counters ([[LRN-150]]).
+- **Action**: (1) never state a disk-reclaimable figure before reading the registry that owns it ([[LRN-151]]). (2) A fix round deserves the same challenge as the original plan — 3/3 confirmation BLOCKERs came from fixes, not from the original. (3) Confirmation pass earned its cost: without it printer override would have shipped, silently disconnected doctor's counters ([[LRN-150]]).
 - **Status**: keep.
 - **Reference**: `.claude/tasks/plans/2026-09-13-gstack-playwright-lib-2220.md` (rev 3). Links [[BDR-088]], [[LRN-150]].
@@ -565,3 +565,4 @@ rules:
 ## 2026-10-06
 - /release-candidate 2.0.0 (user: MAJOR): prep DONE on release/2.0.0 (9d421e4), suite RED → user hold. Root cause = GNU-only idioms on new macOS machine ([[BLK-026]]). /bugfix on bugfix/macos-portability: 4 challenge passes → r3, bugfixer, GATE 0 MET, verifier CONFORME 9/9, security PASS, hardening (sed_profile keeps tmp on failed write), commit 0efdff0 + CHANGELOG docs commit; [[BDR-110]] [[LRN-189]] [[LRN-190]]. Found [[BLK-027]]: no global hooksPath here, `make link` run (user go), `make plugin` + `.env` still missing. Next: reconcile, prune-memory, doc-sync, resume release at STEP 4 after merging develop into release/2.0.0.
 - Reconcile 2026-10-06: TODO:15 + TODO:10 closed (npm soft_deny covers), TODO:892 re-verified open; 6 BLK external/open unchanged; BLK-018 due at the running release.
 - /prune-memory 2026-10-06: A none, D none; B BLK-019+020 → BLK-028 (merge); C bounded 37 entries ≥9% filler → 37 edited, 1 untouched (LRN-075 all-negation), cuts 1-11% only (negation guard protects "X not Y" lessons); fidelity + index OK. 110 bloated entries left for a later run.
@@ -681,20 +681,20 @@ rules:
 ## LRN-037 — Verify the load-bearing scenario on the REAL subject in REAL context, not a stub or a logic argument
 - **Date**: 2026-06-21
- **Context**: design-gate chantier. 4 successive plausible claims each REFUTED only by running the real thing: (1) .env read path was `$REPO/.env`, not `~/.claude/.env` (read the actual script); (2) fail-open — unknown folded into silent READY (saw it in live output); (3) "alias dies in subshell = cause" (refuted: real binary on inherited PATH → `command -v` succeeds); (4) real cause = PATH carrying nvm bin (proven by `PATH=/usr/bin:/bin` run). Logic/stub never caught any. The DISCRIMINATING magic-OFF-under-stripped-PATH → exit 10 is what proved the gate truly runs `claude mcp list` vs. defaulting to READY.
+- **Context**: design-gate chantier. 4 successive plausible claims each REFUTED only by running the real thing: (1) .env read path was `$REPO/.env`, not `~/.claude/.env` (read the actual script); (2) fail-open — unknown folded into silent READY (saw it in live output); (3) "alias dies in subshell = cause" (refuted: real binary on inherited PATH → `command -v` succeeds); (4) real cause = PATH carrying nvm bin (proven by `PATH=/usr/bin:/bin` run). Logic/stub never caught any. DISCRIMINATING magic-OFF-under-stripped-PATH → exit 10 proved gate truly runs `claude mcp list` vs. defaulting to READY.
- **Pattern**: for the load-bearing scenario, run it on the REAL subject in the REAL invocation context (prod path `$HOME/.claude/lib/...`, prod-like PATH), not a stub or a "the code path is correct" argument. A stub proves branch coverage; only the real subject proves the integration. Always add a DISCRIMINATING case — force the failure state; the check must REPORT it, not pass by default (a check that only ever passes proves nothing).
+- **Pattern**: for the load-bearing scenario, run it on the REAL subject in the REAL invocation context (prod path `$HOME/.claude/lib/...`, prod-like PATH), not a stub or a "the code path is correct" argument. Stub proves branch coverage; only real subject proves integration. Always add a DISCRIMINATING case — force the failure state; the check must REPORT it, not pass by default (a check that only ever passes proves nothing).
 - **Future application**: any "fixed/works" claim on a critical path → produce the real run output (command + lines + exit code) before capitalizing or shipping; don't summarize ("condition met") in place of the output. Stub/logic = necessary for branch coverage, never sufficient for the integration claim. Most rentable discipline of the whole segment: every refutation came from execution, none from reasoning.
- **Reference**: design-gate chantier, the `PATH=/usr/bin:/bin` matrix (magic-on → READY/0, magic-off → INCOMPLETE/10), commits 4d19135 / f963318. Linked to [[LRN-036]] (the concrete instance: the PATH cause surfaced only by the real run), [[LRN-034]] (its twin — 034 = don't trust a narrated *claim*; 037 = don't trust a *stub/logic argument* as proof; both demand execution against ground truth).
+- **Reference**: design-gate chantier, `PATH=/usr/bin:/bin` matrix (magic-on → READY/0, magic-off → INCOMPLETE/10), commits 4d19135 / f963318. Linked to [[LRN-036]] (the concrete instance: the PATH cause surfaced only by the real run), [[LRN-034]] (its twin — 034 = don't trust a narrated *claim*; 037 = don't trust a *stub/logic argument* as proof; both demand execution against ground truth).
 ---
 ## LRN-038 — Playwright host-platform override for distros newer than its hardcoded support list
 - **Date**: 2026-06-23
 - **Context**: fresh Ubuntu 26.04. gstack `./setup` aborted: "Playwright does not support chromium on ubuntu26.04-x64". Playwright 1.58.2's registry hardcodes `ubuntu20.04/22.04/24.04` only; a newer release → no matching build → hard error. gstack is a pinned submodule (must not edit).
- **Pattern**: `PLAYWRIGHT_HOST_PLATFORM_OVERRIDE=ubuntuXX.04-<arch>` forces a fallback build. MUST include arch (`x64`/`arm64`) — bare `ubuntu24.04` fails ("does not support … ubuntu24.04"). Set from the WRAPPER: `export` before the submodule's setup (install-time download) AND persist to the shell profile (runtime launch) — both paths call `getHostPlatform`. No submodule edit. Gate on real OS version (`sort -V`) → supported distros untouched. Test with the LOCAL `./node_modules/.bin/playwright` — `bunx playwright` pulls the LATEST playwright (different browser revision than the local import), masks the result.
+- **Pattern**: `PLAYWRIGHT_HOST_PLATFORM_OVERRIDE=ubuntuXX.04-<arch>` forces fallback build. MUST include arch (`x64`/`arm64`) — bare `ubuntu24.04` fails ("does not support … ubuntu24.04"). Set from WRAPPER: `export` before submodule's setup (install-time download) AND persist to shell profile (runtime launch) — both paths call `getHostPlatform`. No submodule edit. Gate on real OS version (`sort -V`) → supported distros untouched. Test with LOCAL `./node_modules/.bin/playwright` — `bunx playwright` pulls LATEST playwright (different browser revision than local import), masks result.
- **Future application**: pinned tool hardcoding an OS allowlist breaks on a fresh OS upgrade. Look for a host-platform override env before bumping/forking the dep. Prove the fallback binary actually runs (`ldd` = no missing libs + a real headless render), not just that the download resolves.
+- **Future application**: pinned tool hardcoding OS allowlist breaks on fresh OS upgrade. Look for host-platform override env before bumping/forking dep. Prove the fallback binary actually runs (`ldd` = no missing libs + a real headless render), not just that the download resolves.
 - **Reference**: `install-plugins.sh` `playwright_platform_override()`, commit 211c7d4. Linked to [[BLK-008]].
- **2026-06-23 CORRECTION (override REVERTED, commit b9c3937)**: the override is NOT a usable fix on Ubuntu 26.04. It makes `playwright install` switch to the ubuntu24.04 fallback build, which downloads to 100% then HANGS at extraction (chrome binary never materializes; real machine + sandbox). 0.5s fast-fail → install-blocking hang. Isolated proof (`ldd` + headless render) PASSED on an already-extracted sibling build (rev 1228) — masked the install-path hang in the real flow (rev 1208). **Sharpened lesson**: proving the binary launches in isolation is NOT proving the install path works — run the ACTUAL install command end-to-end (it must COMPLETE, not just "download resolves" nor "a binary launches"). Override technique stays valid in general; the EXTRACTION/COMPLETE step is part of "does it work".
+- **2026-06-23 CORRECTION (override REVERTED, commit b9c3937)**: the override is NOT a usable fix on Ubuntu 26.04. It makes `playwright install` switch to the ubuntu24.04 fallback build, which downloads to 100% then HANGS at extraction (chrome binary never materializes; real machine + sandbox). 0.5s fast-fail → install-blocking hang. Isolated proof (`ldd` + headless render) PASSED on already-extracted sibling build (rev 1228) — masked install-path hang in real flow (rev 1208). **Sharpened lesson**: proving the binary launches in isolation is NOT proving the install path works — run the ACTUAL install command end-to-end (it must COMPLETE, not just "download resolves" nor "a binary launches"). Override technique stays valid in general; EXTRACTION/COMPLETE step is part of "does it work".
 ---
@@ -711,8 +711,8 @@ rules:
 ## LRN-040 — OS newer than a pinned tool supports = TWO distinct layers (version build + security policy)
 - **Date**: 2026-06-23
 - **Context**: gstack browser on fresh Ubuntu 26.04. Layer 1 = Playwright 1.58.2 ships no browser build for 26.04 → install errors (the host-platform override "fixes" the error but its fallback build HANGS at extraction — dead end, [[BLK-008]]). Layer 2 = even with Playwright 1.61 (native 26.04 build that launches fine in isolation), the real browse path aborts "No usable sandbox" because Ubuntu 24.04+ restricts unprivileged user namespaces via AppArmor.
- **Pattern**: (a) bump the tool PAST the OS-support threshold — don't force the OS to look older (overrides/fallbacks are fragile; prove the install COMPLETES, not just that a binary launches). Pinned submodule dep: `bun add X@latest` in the submodule, automatable in the installer, idempotent via grep of the dep's support list for the running OS tag before bumping. (b) SEPARATELY handle OS security hardening: Chromium needs `--no-sandbox` where `sysctl kernel.apparmor_restrict_unprivileged_userns=1`; gstack exposes `GSTACK_CHROMIUM_NO_SANDBOX=1` (#1562). Gate persistence on the sysctl, not an OS-version guess.
+- **Pattern**: (a) bump the tool PAST the OS-support threshold — don't force the OS to look older (overrides/fallbacks are fragile; prove the install COMPLETES, not just that a binary launches). Pinned submodule dep: `bun add X@latest` in submodule, automatable in installer, idempotent via grep of dep's support list for running OS tag before bumping. (b) SEPARATELY handle OS security hardening: Chromium needs `--no-sandbox` where `sysctl kernel.apparmor_restrict_unprivileged_userns=1`; gstack exposes `GSTACK_CHROMIUM_NO_SANDBOX=1` (#1562). Gate persistence on the sysctl, not an OS-version guess.
- **Future application**: "tool X broke after an OS upgrade" → check BOTH (1) does X ship a build / support entry for the new OS (bump if not), and (2) does the new OS's hardening (userns/AppArmor/SELinux) block X at runtime (needs an opt-out flag). Fix one without the other → still fails. Verify the FULL runtime path (drive a real page) — isolated `chromium.launch()` PASSED while the real `browse` path failed on the sandbox.
+- **Future application**: "tool X broke after an OS upgrade" → check BOTH (1) does X ship a build / support entry for the new OS (bump if not), and (2) does the new OS's hardening (userns/AppArmor/SELinux) block X at runtime (needs an opt-out flag). Fix one without the other → still fails. Verify FULL runtime path (drive real page) — isolated `chromium.launch()` PASSED while real `browse` path failed on sandbox.
 - **Reference**: `install-plugins.sh`, `.bashrc` `GSTACK_CHROMIUM_NO_SANDBOX=1`, gstack `browse/src/browser-manager.ts` `shouldEnableChromiumSandbox()`, commit 3b8ffb1. Linked to [[BDR-029]], [[BLK-008]], [[LRN-038]].
 ---
@@ -720,8 +720,8 @@ rules:
 ## LRN-041 — A check reading a symlink an EARLIER install step makes → false negative if that step's precondition wasn't met
 - **Date**: 2026-06-23
- **Context**: install warned "MAGIC_API_KEY not found in ~/.claude/.env" though the key WAS set there. Root: the check grep'd `$REPO/.env` — a symlink → `~/.claude/.env` ([[BDR-026]]) created by `link.sh`'s `link_env`. On a fresh machine `~/.claude/.env` is created AFTER `link.sh` runs (install first warns "create it"), so the symlink was never made and the key was unreachable via `$REPO/.env`. `make plugin` also never runs `link.sh`. The warning misleadingly blamed `~/.claude/.env`.
+- **Context**: install warned "MAGIC_API_KEY not found in ~/.claude/.env" though the key WAS set there. Root: check grep'd `$REPO/.env` — symlink → `~/.claude/.env` ([[BDR-026]]) created by `link.sh`'s `link_env`. On a fresh machine `~/.claude/.env` is created AFTER `link.sh` runs (install first warns "create it"), so the symlink was never made and the key was unreachable via `$REPO/.env`. `make plugin` also never runs `link.sh`. Warning misleadingly blamed `~/.claude/.env`.
- **Pattern**: a check that reads a path PRODUCED by an earlier setup step silently fails when that step's precondition wasn't met yet (target absent → symlink skipped). Fix: read the CANONICAL source and/or self-heal (create the missing symlink when the canonical exists). Env-key greps must tolerate `export `/leading whitespace and require a non-empty value: `^[[:space:]]*(export[[:space:]]+)?KEY=.` — and the message must name the real gap (symlink missing vs key absent), with an actionable hint (`run make link`).
+- **Pattern**: a check that reads a path PRODUCED by an earlier setup step silently fails when that step's precondition wasn't met yet (target absent → symlink skipped). Fix: read CANONICAL source and/or self-heal (create missing symlink when canonical exists). Env-key greps must tolerate `export `/leading whitespace and require non-empty value: `^[[:space:]]*(export[[:space:]]+)?KEY=.` — and message must name real gap (symlink missing vs key absent), with actionable hint (`run make link`).
 - **Future application**: any "X not found in FILE" where FILE is a symlink/derived path → verify the producing step ran with its precondition, prefer the canonical source, self-heal or give an actionable message. Sandbox note: `.env*` reads were blocked — diagnosed via directory listing + regex tests on SYNTHETIC lines, never reading the secret.
 - **Reference**: `install-plugins.sh` magic check (self-heal symlink + tolerant regex), `link.sh` `link_env`, commit 1b028cb. Linked to [[BDR-026]].
@@ -760,9 +760,9 @@ rules:
 ## LRN-045 — Renaming a command: audit exact-name leak-guard / forbidden-token regexes
 - **Date**: 2026-06-25
- **Context**: rename `/validate` → `/web-validate`. A client-deliverable leak-guard in `agents/client-handover-writer.md:1462` greps generated docs for internal tool names via `grep -niE '/(seo|harden|validate|cso|...)\b'`. The `web-` prefix means `/web-validate` no longer matches the `/validate` branch (the `/` must sit immediately before `validate`; post-rename a `-` sits there) → renamed command leaks SILENTLY into client-facing output. No error — the gate just stops catching it.
+- **Context**: rename `/validate` → `/web-validate`. Client-deliverable leak-guard in `agents/client-handover-writer.md:1462` greps generated docs for internal tool names via `grep -niE '/(seo|harden|validate|cso|...)\b'`. The `web-` prefix means `/web-validate` no longer matches the `/validate` branch (the `/` must sit immediately before `validate`; post-rename a `-` sits there) → renamed command leaks SILENTLY into client-facing output. No error — the gate just stops catching it.
- **Pattern**: any rename of a command/skill/identifier must sweep regexes/allowlists/denylists that match the OLD name by exact token — leak guards, forbidden-token gates, routing dispatchers, CI greps. A prefix/suffix rename breaks anchored matches (`/oldname\b`) with zero error. Fix = alternation covering BOTH names (`web-validate|validate`), NOT replacement — old artifacts (already-shipped client docs, logs) still carry the legacy name and must stay caught.
+- **Pattern**: any rename of command/skill/identifier must sweep regexes/allowlists/denylists matching OLD name by exact token — leak guards, forbidden-token gates, routing dispatchers, CI greps. Prefix/suffix rename breaks anchored matches (`/oldname\b`) with zero error. Fix = alternation covering BOTH names (`web-validate|validate`), NOT replacement — old artifacts (already-shipped client docs, logs) still carry the legacy name and must stay caught.
- **Future application**: when renaming, grep the BARE old token inside regex/test/gate files, not just `/oldname` command refs. A blind `replace_all '/old' '/new'` MISSES these because the guard stores the name inside an alternation (`|old|`), not as `/old`. For each guard found, extend to `new|old`; verify the gate line shows both names.
+- **Future application**: when renaming, grep the BARE old token inside regex/test/gate files, not just `/oldname` command refs. A blind `replace_all '/old' '/new'` MISSES these because the guard stores the name inside an alternation (`|old|`), not as `/old`. For each guard found, extend to `new|old`; verify gate line shows both names.
 - **Reference**: `agents/client-handover-writer.md:1462`, rename commit `e5e673a`. Linked to [[BDR-032]].
 ## LRN-046 — Destructive skill: deterministic oracle > semantic judge
@@ -840,8 +840,8 @@ rules:
 ## LRN-055 — Body `## ID —` headings are a drift-immune index; the maintained `## Index` table is not
 - **Date**: 2026-06-26
 - **Pattern**: When a registry keeps both per-entry `## ID — title` headings AND a hand-maintained `## Index` table, the Index DRIFTS (entries land in the body, the manual update lapses) while headings cannot (an entry IS its heading — 100% coverage by construction). Measured: decisions 11/34 (32%), learnings 21/52 (40%), blockers 2/9 (22%) missing from the Index — scattered in large blocks (e.g. decisions BDR-024–033 unindexed while the newer BDR-034 is), not an old/new split. Manual Index-update step unreliable. Key any selector/scan off `grep '^## <PREFIX>-'`, never the convenience Index. Backfill (prune-memory passe D) = human-TOC hygiene, NOT a selector dependency.
- **Context**: analyze-before-plan ([[BDR-035]]) two-pass. First instinct "reuse the Index capitalize maintains"; measuring the drift killed it — convenient artifact unreliable, guaranteed one (headings) free.
+- **Context**: analyze-before-plan ([[BDR-035]]) two-pass. First instinct "reuse the Index capitalize maintains"; measuring drift killed it — convenient artifact unreliable, guaranteed one (headings) free.
- **Future application**: choosing a substrate to index/select over: prefer what the STRUCTURE guarantees over what a step PROMISES to maintain. Verify maintained-artifact completeness before depending on it.
+- **Future application**: choosing substrate to index/select over: prefer what STRUCTURE guarantees over what a step PROMISES to maintain. Verify maintained-artifact completeness before depending on it.
 - **Reference**: `lib/analyze-before-plan.md` (PASS 1). `skills/prune-memory` passe D. See [[BDR-035]].
 ## LRN-056 — `grep PAT dir/*.md` on an absent dir ERRORS (exit 2), it does not no-op → guard with `[ -d ]`
@@ -855,8 +855,8 @@ rules:
 ## LRN-057 — Match the consumption mechanism to the consumer (mechanical / external-cognitive / inline-cognitive)
 - **Date**: 2026-06-26
 - **Pattern**: When a produced artifact must be CONSUMED downstream, the mechanism depends on the consumer: (a) MECHANICAL (git merge integrating a branch) — production on the shared substrate = consumption, automatic ([[BDR-034]]'s "commit before FINISH"); (b) EXTERNAL-COGNITIVE (an unmodifiable skill like `superpowers:brainstorming`) — "produced before" ≠ "consumed"; INJECT the artifact into the consumer's INPUT at the invocation boundary (orchestrator = adapter) + a RECONCILIATION gate that EXPOSES the disposition for review (not auto-detect); (c) INLINE-COGNITIVE (same agent reads then plans) — reader=planner, same context → natural consumption, just force the trace ([[LRN-053]]). Don't import (b)'s machinery where (c) suffices, nor assume (a)'s automatism when the consumer is cognitive.
- **Context**: analyze-before-plan ([[BDR-035]]). ship-feature brainstorm = external-cognitive → STEP 0d injection + STEP 3 expose-for-review gate; feat/bugfix = inline-cognitive → natural + trace, no injection. Asymmetry vs [[BDR-034]] (mechanical merge) = the chantier's hardest point.
+- **Context**: analyze-before-plan ([[BDR-035]]). ship-feature brainstorm = external-cognitive → STEP 0d injection + STEP 3 expose-for-review gate; feat/bugfix = inline-cognitive → natural + trace, no injection. Asymmetry vs [[BDR-034]] (mechanical merge) = chantier's hardest point.
- **Future application**: wiring ANY produce→consume invariant: classify the consumer first (mechanical / external-cognitive / inline-cognitive), pick the lightest sufficient mechanism. Stops reflexive import of orchestrator-grade injection+gate where an inline trace would do.
+- **Future application**: wiring ANY produce→consume invariant: classify consumer first (mechanical / external-cognitive / inline-cognitive), pick lightest sufficient mechanism. Stops reflexive import of orchestrator-grade injection+gate where inline trace would do.
 - **Reference**: `skills/ship-feature/SKILL.md` STEP 0d/1/2/3, `agents/bugfixer.md`+`feater.md`. Contrast [[BDR-034]] (mechanical). See [[BDR-035]], [[LRN-053]].
 ## LRN-058 — Same bug-class ≠ same fix: verify the twin shares the fix's PRECONDITION before replicating
@@ -878,15 +878,15 @@ rules:
 ## LRN-060 — A fail-closed guard is proven by what it REFUSES (loudly); pass dynamic lists as argv, not a separator-string
 - **Date**: 2026-06-27
- **Pattern**: Two robustness lessons from doc-commit. (a) The inverse-`.claude/` exclusion is a SECURITY guard (BDR-022) → test it by what it must REFUSE (forbidden path ALONE, and MIXED with legit), not only what it accepts; and refuse LOUDLY (dedicated exit 4, names the offender, refuse-ALL on mixed) — silent-filtering would MASK an upstream violation (doc-syncer surfaced a `.claude/` it must never patch). The refusal IS the alarm. (b) Pass a dynamic file list as ARGV, never a separator-joined string: argv has no in-band delimiter → a path with spaces survives as one element (proven, T7); newline is only the producer's text format the agent maps to argv. Space-join-then-resplit would mis-split + the `[ -e ]` filter then silently drops it.
+- **Pattern**: Two robustness lessons from doc-commit. (a) The inverse-`.claude/` exclusion is a SECURITY guard (BDR-022) → test it by what it must REFUSE (forbidden path ALONE, and MIXED with legit), not only what it accepts; and refuse LOUDLY (dedicated exit 4, names the offender, refuse-ALL on mixed) — silent-filtering would MASK an upstream violation (doc-syncer surfaced a `.claude/` it must never patch). Refusal IS the alarm. (b) Pass a dynamic file list as ARGV, never a separator-joined string: argv has no in-band delimiter → a path with spaces survives as one element (proven, T7); newline is only the producer's text format the agent maps to argv. Space-join-then-resplit would mis-split + `[ -e ]` filter then silently drops it.
 - **Context**: doc-commit.sh ([[BDR-036]]), T1a/b/c (refuse paths) + T7 (argv space-safe), all real-exec.
- **Future application**: any automated scoped-commit / destructive guard — test the REFUSAL path + refuse loud; pass lists as argv. Same family as [[LRN-046]] (deterministic oracle for a destructive guard).
+- **Future application**: any automated scoped-commit / destructive guard — test REFUSAL path + refuse loud; pass lists as argv. Same family as [[LRN-046]] (deterministic oracle for destructive guard).
 - **Reference**: [[BDR-036]], [[LRN-051]] (changed-paths filter), [[LRN-046]].
 ## LRN-061 — Runtime net proposed for an unwired skill → check the wiring first
 - **Date**: 2026-06-27
- **Pattern**: Tempted to build a runtime guard/hook/monitor that watches for a bad OUTCOME (memory written but uncommitted)? First ask if the outcome is a MISSING WIRING, not a behavioral lapse. A per-turn Stop-hook was proposed to catch "dirty memory" — but the cause was `/capitalize`+`/close` not calling the commit include (they predate it). Fix for an unwired skill = WIRE it (deterministic, zero-noise, at source); a monitor over a wiring hole pays RECURRING cost for a ONE-TIME omission; a frequent ignored nag is itself a risk ([[LRN-047]]). **NOT "runtime nets are bad"** — the split is by DETERMINISM: a MISSING WIRING is deterministic → repair structurally; a genuinely NON-DETERMINISTIC aléa → a runtime net IS the right tool. Good counter-example: [[BDR-033]] anim-lib nudge — "will the user want motion?" is unknowable statically → a stateless 1-line suggestion is correct. Same determinism test as [[LRN-046]]/[[LRN-049]], applied to the build-or-not question.
+- **Pattern**: Tempted to build runtime guard/hook/monitor watching for bad OUTCOME (memory written but uncommitted)? First ask if the outcome is a MISSING WIRING, not a behavioral lapse. A per-turn Stop-hook was proposed to catch "dirty memory" — but the cause was `/capitalize`+`/close` not calling the commit include (they predate it). Fix for unwired skill = WIRE it (deterministic, zero-noise, at source); monitor over a wiring hole pays RECURRING cost for ONE-TIME omission; frequent ignored nag is itself a risk ([[LRN-047]]). **NOT "runtime nets are bad"** — the split is by DETERMINISM: a MISSING WIRING is deterministic → repair structurally; a genuinely NON-DETERMINISTIC aléa → a runtime net IS the right tool. Good counter-example: [[BDR-033]] anim-lib nudge — "will the user want motion?" is unknowable statically → stateless 1-line suggestion is correct. Same determinism test as [[LRN-046]]/[[LRN-049]], applied to the build-or-not question.
- **Context**: deferred "v2 capitalize hook" ([[BDR-037]]). Read-phase killed it before code: git proved skills predate the include (oubli), memory committed by hand 35×, orphans self-heal via `commit_memory`. Hook would've been disabled within an hour (frequent ignored nag).
+- **Context**: deferred "v2 capitalize hook" ([[BDR-037]]). Read-phase killed it before code: git proved skills predate include (oubli), memory committed by hand 35×, orphans self-heal via `commit_memory`. Hook would've been disabled within an hour (frequent ignored nag).
 - **Future application**: any "build a hook/watcher/lint to catch when X isn't done" — first grep whether X is even WIRED at its source. Deterministic/structural gap (missing include/call) → fix structurally; reserve runtime nets for non-deterministic lapses, never to complete a rollout. Classify by determinism BEFORE building.
 - **Reference**: [[BDR-037]], [[BDR-034]] (rollout this completes), [[BDR-033]] (the GOOD net — contrast). Conditions [[LRN-047]], [[LRN-049]], [[LRN-054]].
@@ -914,14 +914,14 @@ rules:
 - **future application**: any helper relying on `git status --porcelain` to detect changes — add a `git check-ignore` guard; a path that must persist but is ignored has to fail loud, not no-op.
 ## LRN-067 — a pipeline that looks 2-level can finish at the SAME level; a human-mediated step masks the collision until automated
- **pattern**: an orchestrator delegating to a sub-skill can LOOK two-level (sub assembles, orchestrator integrates) yet the sub's TERMINAL node operates at the SAME level as the orchestrator's finish → double-integration. `subagent-driven-development` assembles tasks on ONE branch (no per-task sub-branches — true) BUT its last flowchart node IS `finishing-a-development-branch` = feature→base merge, the SAME act as the orchestrator's FINISH. init-project (STEP 8 SDD + STEP 11 finish) AND ship-feature (STEP 4 SDD + STEP 9 finish) BOTH invoked finish TWICE. Latent, not visibly broken: SDD's terminal finish is INTERACTIVE (menu → human picks "keep as-is"), so the human SILENTLY de-duplicated. Collision SURFACES when the orchestrator's finish becomes DETERMINISTIC (gitflow finish) → real double-merge. Fix = scope the sub-skill by instruction to stop before its terminal step (NO fork — the finish is a flowchart node the controller follows, not a script; verified by reading SDD's scripts). Pressure-test: RED agent chained the finish ("literal next node in the flowchart"); GREEN with the scope instruction stopped + returned.
+- **pattern**: orchestrator delegating to a sub-skill can LOOK two-level (sub assembles, orchestrator integrates) yet sub's TERMINAL node operates at SAME level as orchestrator's finish → double-integration. `subagent-driven-development` assembles tasks on ONE branch (no per-task sub-branches — true) BUT its last flowchart node IS `finishing-a-development-branch` = feature→base merge, the SAME act as the orchestrator's FINISH. init-project (STEP 8 SDD + STEP 11 finish) AND ship-feature (STEP 4 SDD + STEP 9 finish) BOTH invoked finish TWICE. Latent, not visibly broken: SDD's terminal finish is INTERACTIVE (menu → human picks "keep as-is"), so the human SILENTLY de-duplicated. Collision SURFACES when orchestrator's finish becomes DETERMINISTIC (gitflow finish) → real double-merge. Fix = scope the sub-skill by instruction to stop before its terminal step (NO fork — the finish is a flowchart node the controller follows, not a script; verified by reading SDD's scripts). Pressure-test: RED agent chained finish ("literal next node in the flowchart"); GREEN with scope instruction stopped + returned.
 - **context**: gitflow chantier, wiring orchestrators onto `gitflow finish`. Mapping (premise #6) caught it by READING the real (SDD `SKILL.md` + `scripts/`) BEFORE coding — seam-bug class `deploy` hit, caught earlier this time. Two human-gate backstops survive a missed instruction: SDD's interactive menu + the `gitflow finish` human gate ([[LRN-054]] — no oracle; deterministic layer carries the dangerous case).
- **future application**: before replacing an interactive/human-mediated step with a deterministic one, check whether a delegated sub-skill's TERMINAL step operates at the same level — the human gate may have silently de-duplicated a double-action. Read the sub-skill's real flow (nodes + scripts), don't assume "distinct levels".
+- **future application**: before replacing interactive/human-mediated step with deterministic one, check whether delegated sub-skill's TERMINAL step operates at same level — human gate may have silently de-duplicated a double-action. Read the sub-skill's real flow (nodes + scripts), don't assume "distinct levels".
 ## LRN-068 — enforcement-bootstrap must be transactional: activate the guard LAST and gate it on the bootstrap commit succeeding
- **pattern**: a routine that BOTH installs an enforcement guard (pre-commit hook, branch protection, lock) AND makes a bootstrap commit must be transactional, else a partial run strands it. Two teeth: (a) precheck preconditions (git identity, clean tree) and fail LOUD before ANY mutation; (b) the guard-activation step must NOT run if the guarded bootstrap commit failed — order activation LAST and gate it on commit success. A `cmd_a || cmd_b` form SWALLOWS cmd_b's failure when a later stmt returns 0 → the failure never propagates; use explicit `if ! …; then … || return 1; fi`.
+- **pattern**: routine that BOTH installs enforcement guard (pre-commit hook, branch protection, lock) AND makes bootstrap commit must be transactional, else partial run strands it. Two teeth: (a) precheck preconditions (git identity, clean tree) and fail LOUD before ANY mutation; (b) the guard-activation step must NOT run if the guarded bootstrap commit failed — order activation LAST and gate it on commit success. A `cmd_a || cmd_b` form SWALLOWS cmd_b's failure when a later stmt returns 0 → the failure never propagates; use explicit `if ! …; then … || return 1; fi`.
- **context**: `gitflow_init` ([[BLK-012]]). Existing-repo path swallowed the socle-commit failure (`git diff --cached --quiet || git commit`, then `git branch develop` returned 0 masking it) → init CONTINUED and ran `gitflow_activate_hook` though the socle was never committed → every re-run self-blocked (commit on main blocked by the hook just installed). Fresh-repo path already propagated → the asymmetry was the bug. Fix: fatal socle commit + identity precheck; verified on an identity-less repo → aborts rc1 with ZERO mutation, 57/57 tests green.
+- **context**: `gitflow_init` ([[BLK-012]]). Existing-repo path swallowed the socle-commit failure (`git diff --cached --quiet || git commit`, then `git branch develop` returned 0 masking it) → init CONTINUED and ran `gitflow_activate_hook` though the socle was never committed → every re-run self-blocked (commit on main blocked by the hook just installed). Fresh-repo path already propagated → asymmetry was the bug. Fix: fatal socle commit + identity precheck; verified on identity-less repo → aborts rc1 with ZERO mutation, 57/57 tests green.
- **future application**: any init/bootstrap installing enforcement (hooks, protection, immutability) + committing — activate LAST, gate on the commit, precheck identity/clean-tree up front, make every link propagate (no `||` swallow). TEST the partial-failure path (identity-less / commit-blocked repo) → must abort with zero mutation and stay re-runnable.
+- **future application**: any init/bootstrap installing enforcement (hooks, protection, immutability) + committing — activate LAST, gate on the commit, precheck identity/clean-tree up front, make every link propagate (no `||` swallow). TEST partial-failure path (identity-less / commit-blocked repo) → must abort with zero mutation and stay re-runnable.
 ## LRN-069 — token-authed remote writes under CC perms: inline-env (never `export`), token in the header, keep `git push` on ASK as the real gate
 - **pattern**: a secrets-guard `Bash(export *)` in `permissions.deny` auto-denies ANY command whose FIRST token is `export …` — a false positive (`export GIT_CONFIG_VALUE_0="Authorization: token $TOK" …` reads as blocked when only the `export` prefix tripped it, not the git/curl op). Correct model for token-authed remote writes from tool calls: (a) INLINE env assignment `GIT_CONFIG_COUNT=1 GIT_CONFIG_KEY_0=http.extraHeader GIT_CONFIG_VALUE_0="Authorization: token $TOK" git push …` (no `export` keyword → passes; token rides the http header via git env-config, NEVER in argv nor written to the clone's `.git/config`); (b) keep `Bash(git push *)` on ASK (not deny) — that prompt IS the per-write human gate; don't suppress it, don't allow-list pushes in settings.
@@ -929,8 +929,8 @@ rules:
 - **future application**: scripting token-authed git/curl writes under CC perms → inline env (never `export`), token in `Authorization` header (curl `-H`, git `GIT_CONFIG_*` extraHeader), keep `git push` on ASK as the approval. Tool-call denied unexpectedly → read `permissions.deny` for an over-broad prefix rule (`export *`, `env`, `printenv`) catching a false positive BEFORE concluding the op itself is blocked.
 ## LRN-070 — clean-tree-gated migration + a dirty submodule: diagnose pointer-vs-content, ignore=dirty not blind reset
- **pattern**: an op gated on a clean tree (`git status --porcelain`) is blocked by a submodule showing ` M`. FIRST distinguish: (a) **pointer move** — gitlink (HEAD) ≠ submodule HEAD → resettable via `git submodule update`/`checkout`; (b) **dirty content** — gitlink UNCHANGED, files modified INSIDE the submodule → a local edit. For an intentional local edit, `checkout --`/`submodule update` correctly REFUSE to discard it, and a blind "reset" would DESTROY it. Exclude it non-destructively: `git config submodule.<name>.ignore dirty` (local `.git/config`) → status stops reporting the submodule's dirty content, gate passes, edit preserved. Commit it to `.gitmodules` to share the ignore across clones.
+- **pattern**: op gated on clean tree (`git status --porcelain`) blocked by submodule showing ` M`. FIRST distinguish: (a) **pointer move** — gitlink (HEAD) ≠ submodule HEAD → resettable via `git submodule update`/`checkout`; (b) **dirty content** — gitlink UNCHANGED, files modified INSIDE submodule → local edit. For intentional local edit, `checkout --`/`submodule update` correctly REFUSE to discard it, and blind "reset" would DESTROY it. Exclude it non-destructively: `git config submodule.<name>.ignore dirty` (local `.git/config`) → status stops reporting submodule's dirty content, gate passes, edit preserved. Commit to `.gitmodules` to share ignore across clones.
- **context**: claude gitflow self-migration. `skills-external/gstack` showed ` M`; gitlink `070722a` == submodule HEAD `070722a` (NOT a pointer move), 2 tracked-modified files (`bun.lock`+`package.json`) = the [[BLK-008]] Playwright 1.61 bump (Ubuntu 26.04 browser). The planned "reset" (D2) would have discarded the browser fix; `submodule.skills-external/gstack.ignore=dirty` cleared the tree for `migrate_local`, bump intact.
+- **context**: claude gitflow self-migration. `skills-external/gstack` showed ` M`; gitlink `070722a` == submodule HEAD `070722a` (NOT a pointer move), 2 tracked-modified files (`bun.lock`+`package.json`) = the [[BLK-008]] Playwright 1.61 bump (Ubuntu 26.04 browser). Planned "reset" (D2) would have discarded browser fix; `submodule.skills-external/gstack.ignore=dirty` cleared tree for `migrate_local`, bump intact.
 - **future application**: any clean-tree-gated op (migrate/release/bisect) on a superproject with a submodule carrying intentional local edits → diagnose pointer-vs-content FIRST (compare gitlink to submodule HEAD); for content, `submodule.<name>.ignore=dirty`, never a blind reset. Cross-ref [[BLK-008]] (gstack -dirty by design).
 ## LRN-071 — fail-loud must cover the helper's OWN commit, not just its inputs — 3rd occurrence of the swallowed-commit pattern
@@ -940,9 +940,9 @@ rules:
 - **future application**: any helper whose RETURN VALUE gates a downstream "success" — audit that EVERY fallible internal op propagates its failure, ESPECIALLY the load-bearing commit. `set -uo pipefail` without `-e` does NOT abort mid-function; an unchecked failing command followed by a returning-0 line exits 0 and lies. Check `cmd || other` forms, no-`-e` blocks, every "report success after the op" line. Test the partial-failure path (commit-blocked repo) → must fail loud, empty, non-zero.
 ## LRN-072 — a stranded-artifact bug can be fixed by NOT creating the artifact (negative diff), not by plumbing its commit
- **pattern**: 3rd member of the post-FINISH-artifact class (memory, docs, GSD ROADMAP) — but UNLIKE the first two (real artifacts ALWAYS produced → couple a commit), the GSD artifact came from a SPECULATIVE, opt-in, rarely-used producer (init-project auto-bootstrapping a multi-session engine at project creation). Reflex fix (reorder + build `gsd-commit.sh` + tests) = machinery to faithfully commit an artifact nobody uses. The right fix was a NEGATIVE diff: delete the producer → orphan never created → bug dissolves, zero new code (BLK-011).
+- **pattern**: 3rd member of post-FINISH-artifact class (memory, docs, GSD ROADMAP) — but UNLIKE first two (real artifacts ALWAYS produced → couple a commit), GSD artifact came from SPECULATIVE, opt-in, rarely-used producer (init-project auto-bootstrapping multi-session engine at project creation). Reflex fix (reorder + build `gsd-commit.sh` + tests) = machinery to faithfully commit artifact nobody uses. The right fix was a NEGATIVE diff: delete the producer → orphan never created → bug dissolves, zero new code (BLK-011).
- **the refutation that got there**: framing "ROADMAP redundant with TODO" WRONG (gsd ≫ roadmap = state machine/crash-recovery/cost/parallel/worktree; TODO ≠ gsd ROADMAP = different altitude + consumer). Reading REFUTED both premises, yet the CONCLUSION (remove the step) held for a STRONGER reason: speculatively scaffolding a heavy engine the sole user doesn't use, at creation, is bad per se. Right answer, reason corrected before engraving — change the QUESTION before changing the code.
+- **the refutation that got there**: framing "ROADMAP redundant with TODO" WRONG (gsd ≫ roadmap = state machine/crash-recovery/cost/parallel/worktree; TODO ≠ gsd ROADMAP = different altitude + consumer). Reading REFUTED both premises, yet the CONCLUSION (remove the step) held for a STRONGER reason: speculatively scaffolding a heavy engine the sole user doesn't use, at creation, is bad per se. Right answer, reason corrected before engraving — change QUESTION before changing code.
- **future application**: stranded / duplicated / uncommitted-artifact bug → BEFORE building machinery for the artifact, ask whether the step that PRODUCES it is used / wanted / non-speculative. Speculative or unused (esp. personal/single-user repo) → DELETE the producer; cleanest fix = the absent one. Distinguish speculative-at-creation (REMOVE) from deliberate-on-demand (KEEP). Family: [[BLK-010]], [[BLK-011]], [[BDR-036]].
+- **future application**: stranded / duplicated / uncommitted-artifact bug → BEFORE building machinery for artifact, ask whether step that PRODUCES it is used / wanted / non-speculative. Speculative or unused (esp. personal/single-user repo) → DELETE producer; cleanest fix = absent one. Distinguish speculative-at-creation (REMOVE) from deliberate-on-demand (KEEP). Family: [[BLK-010]], [[BLK-011]], [[BDR-036]].
 ## LRN-073 — a skill's worked-example must use FICTIONAL ids, never live registry ids (they prime real-data behavior)
 - **pattern**: prune-memory's STEP-2 plan example named real LRN-014 + LRN-016 ("merge these"). A real-data run merged exactly that pair — though they're COMPLEMENTARY (header-ids vs checkbox-CSS), a merge its own rule forbids. Example ids that match live entries, in context at audit time, PRIME the action: you can't tell "judged correctly" from "pattern-matched its own example".
@@ -968,15 +968,15 @@ rules:
 ## LRN-077 — test fixtures must carry NEUTRAL names (pass for the right reason)
 - **Date**: 2026-06-30
 - **pattern**: a baseline agent on a worktree named `wt-pre-reconcile` read "pre-reconcile" FROM THE DIR NAME and inferred staleness — reasoning for the WRONG reason (the name), not the right one (verify git). Fixtures + the GREEN test were re-frozen under NEUTRAL names so the engine reaches truth by querying git, never by reading a path hint.
- **meta — same symptom, distinct cause as [[LRN-074]]**: 074 = COMMAND-ASSUMPTION (ugrep parsed `-9..` → false green); 077 = LEAKY FIXTURE (name telegraphs the answer). Different mechanisms, SAME symptom: test passes/fails for the wrong reason. Cross-cutting lesson = verify a test passes for the RIGHT reason, not merely that it passes — whether the false signal comes from an assumed command (074) or a leaky fixture (077).
+- **meta — same symptom, distinct cause as [[LRN-074]]**: 074 = COMMAND-ASSUMPTION (ugrep parsed `-9..` → false green); 077 = LEAKY FIXTURE (name telegraphs answer). Different mechanisms, SAME symptom: test passes/fails for wrong reason. Cross-cutting lesson = verify a test passes for the RIGHT reason, not merely that it passes — whether the false signal comes from an assumed command (074) or a leaky fixture (077).
 - **future application**: name fixtures/paths neutrally; for any green, ask "did it pass because the subject did the work, or because something leaked the answer?"
 - **corroboration 2026-07-02 (T6c)**: 3rd family member — test truth borrowed from TRANSIENT env state. run-reconcile T6c asserted `$MEM/../skills/darwin-skill` = `.claude/skills/` (the [[LRN-042]] parasite dir), not canonical `skills/`; born green because the parasite still existed, red since the same-day cleanup, unnoticed until the 2026-07-02 audit re-ran the suite ([[EVAL-011]]'s "20/20" silently 19/1 for 2 days). Oracles target CANONICAL paths (never derived `X/../Y`); re-run suites after ANY env cleanup tests may have silently depended on; "green at build" ≠ "green now".
 ## LRN-078 — semver number DERIVES from the change nature; "breaking" = requires a migration
 - **Date**: 2026-06-30
- **pattern**: framing a release as "it's 4.0.0 → find the breaking changes to justify it" is backwards; the number FOLLOWS the nature of the changes. The real question = "is there a breaking change?", not "how do I justify the target". Solo / mono-user repo, no public API ⇒ "breaking" = casse mon propre usage / EXIGE une migration de ma part.
+- **pattern**: framing release as "it's 4.0.0 → find the breaking changes to justify it" is backwards; number FOLLOWS nature of changes. The real question = "is there a breaking change?", not "how do I justify the target". Solo / mono-user repo, no public API ⇒ "breaking" = casse mon propre usage / EXIGE une migration de ma part.
 - **applied (v4.0.0)**: gitflow universal = TRUE breaking workflow change (master→main, mandatory branches, hook, 6-repo migration) → MAJOR on its own. caveman removal = VERIFIED nothing invoked it (grep: only the kept memory format-rule + frozen fixtures, settings/hooks clean) → a clean `### Removed` (capability gone, nothing breaks, no migration), NOT breaking. The MAJOR rests on gitflow alone; don't mislabel a removal as breaking.
- **future application**: pick MAJOR/MINOR/PATCH from the changes; the lineage gives the digits. Verify "does X actually break / require migration?" from the refs (grep), not from the size of the change or the desire for a round number.
+- **future application**: pick MAJOR/MINOR/PATCH from changes; lineage gives digits. Verify "does X actually break / require migration?" from the refs (grep), not from the size of the change or the desire for a round number.
 ## LRN-079 — orchestrator-skill TDD: replay the flow on a throwaway repo, RED = flow minus the new step
 - **Date**: 2026-06-30
@@ -985,10 +985,10 @@ rules:
 ## LRN-080 — measure whether the model already does X before adding an instruction to make it do X
 - **Date**: 2026-06-30
- **pattern**: the --help chantier (implement [[BDR-001]] as a global CLAUDE.md instruction "on --help → render help + stop") was KILLED by its behavioral RED. Before writing a line, measured the control (6 reps, `/web-validate` + `/harden`, no instruction): **6/6 already rendered rich help AND stopped without dispatching** — the supposedly-absent behavior was fully present. Residual value = format consistency across 6 divergent shapes → not worth ~5 lines in a compressed CLAUDE.md on a solo repo. A phantom-value addition avoided.
+- **pattern**: --help chantier (implement [[BDR-001]] as global CLAUDE.md instruction "on --help → render help + stop") KILLED by its behavioral RED. Before writing a line, measured the control (6 reps, `/web-validate` + `/harden`, no instruction): **6/6 already rendered rich help AND stopped without dispatching** — the supposedly-absent behavior was fully present. Residual value = format consistency across 6 divergent shapes → not worth ~5 lines in a compressed CLAUDE.md on a solo repo. Phantom-value addition avoided.
- **why it matters**: [[LRN-075]] (test the UNGUIDED control) paying off one chantier later — measuring the RED before building is what caught it. For UNIVERSAL conventions the model already honors (--help, common flags, standard shapes), a "teach it to do X" instruction buys nothing but tokens; the only thing left to buy is consistency, which must clear its own ROI bar.
+- **why it matters**: [[LRN-075]] (test the UNGUIDED control) paying off one chantier later — measuring RED before building caught it. For UNIVERSAL conventions the model already honors (--help, common flags, standard shapes), a "teach it to do X" instruction buys nothing but tokens; the only thing left to buy is consistency, which must clear its own ROI bar.
- **future application**: before adding any global instruction to ELICIT a behavior, run the behavioral control first — does the model already do it unaided? If yes, the only remaining value is standardization; price it honestly vs the cost (esp. a compressed CLAUDE.md). Often: don't add it.
+- **future application**: before adding any global instruction to ELICIT a behavior, run behavioral control first — does model already do it unaided? If yes, only remaining value is standardization; price it honestly vs cost (esp. compressed CLAUDE.md). Often: don't add it.
- **corroboration 2026-06-30**: 3 consecutive "make the model do X" chantiers — --help ([[BDR-001]]), darwin re-baseline ([[BDR-043]]/[[LRN-082]]), auto-skill-dispatch ([[BDR-044]]) — ALL measured won't-build/moot. A backlog of "add instruction to elicit behavior Y" has a high phantom-value rate (universal conventions + aggressive existing mandates like superpowers L1 already elicit Y) → sweep such backlogs measure-first, expect kills.
+- **corroboration 2026-06-30**: 3 consecutive "make the model do X" chantiers — --help ([[BDR-001]]), darwin re-baseline ([[BDR-043]]/[[LRN-082]]), auto-skill-dispatch ([[BDR-044]]) — ALL measured won't-build/moot. Backlog of "add instruction to elicit behavior Y" has high phantom-value rate (universal conventions + aggressive existing mandates like superpowers L1 already elicit Y) → sweep such backlogs measure-first, expect kills.
 ## LRN-081 — Commit trailers: Claude-COMPOSED content only, never on staging of user-authored text
 - **Date**: 2026-06-30
@@ -1007,16 +1007,16 @@ rules:
 ## LRN-083 — Subagents are an INVALID instrument for measuring MAIN-LOOP spontaneous routing
 - **Date**: 2026-06-30
- **pattern**: measuring whether the MAIN loop self-invokes a skill on implicit intent: dispatched subagents are non-discriminating — SUBAGENT-STOP tells them to SKIP the L1 routing mandate, delegated-execute framing suppresses meta-routing → they hand-do the task regardless of main-loop prose strength. Result pins to the no-route FLOOR (artifact, not signal). Complement of [[LRN-028]] (there subagents OVER-saw installed skills, invalidating a no-skill baseline; here they UNDER-route, invalidating a routing-measurement) — both = subagent ≠ main-loop condition.
+- **pattern**: measuring whether MAIN loop self-invokes a skill on implicit intent: dispatched subagents are non-discriminating — SUBAGENT-STOP tells them to SKIP L1 routing mandate, delegated-execute framing suppresses meta-routing → they hand-do the task regardless of main-loop prose strength. Result pins to the no-route FLOOR (artifact, not signal). Complement of [[LRN-028]] (there subagents OVER-saw installed skills, invalidating a no-skill baseline; here they UNDER-route, invalidating a routing-measurement) — both = subagent ≠ main-loop condition.
 - **why it matters**: a 0/N subagent RED reads as "under-triggers → build the chantier" but is the [[LRN-028]] trap — the instrument can't tell strong prose from weak. Concluding from it = pass/fail for the WRONG reason ([[LRN-074]]/[[LRN-077]]).
 - **context**: 2026-06-30 auto-skill-dispatch RED. 6 subagents on toy implicit-intent tasks → 0/6 routed → RETIRED as non-discriminating, NOT reported as a number. Reframed; measured in REAL fresh main-loop sessions.
 - **future application**: measure main-loop spontaneous routing/discernment in FRESH main-loop sessions (full L0–L4, no SUBAGENT-STOP, real user-turn). Observable instrument = the HUMAN typing the prompts + watching live — cron/schedule-spawned fresh sessions are the right CONDITION but UNOBSERVABLE to the orchestrator (they notify the owner, not the dispatcher), so they can't be the measurement vehicle. Never substitute a subagent for a fresh session in a routing RED. See [[LRN-028]], [[LRN-075]], [[LRN-080]].
 ## LRN-084 — A protection hook enforces PROD safety, not the full branch-flow — the exemption masked the rule-vs-guard divergence
 - **Date**: 2026-07-01
- **pattern**: the gitflow pre-commit hook is a PROTECTION guard (block code on main/develop), NOT a flow enforcer. It exempts `.claude/**` and can only test "on a protected base" — it can NEVER verify "branched FROM develop" (no base knowledge). "Every change via a branch from develop" is only HALF-encoded by the hook; the base half lives upstream in `gitflow_start`. The exemption is scoped to the SIDE-CAR ([[BDR-034]]); it has no branch to follow when memory IS the work → standalone memory fell back to `main`.
+- **pattern**: the gitflow pre-commit hook is a PROTECTION guard (block code on main/develop), NOT a flow enforcer. It exempts `.claude/**` and can only test "on a protected base" — it can NEVER verify "branched FROM develop" (no base knowledge). "Every change via a branch from develop" is only HALF-encoded by hook; base half lives upstream in `gitflow_start`. The exemption is scoped to the SIDE-CAR ([[BDR-034]]); it has no branch to follow when memory IS the work → standalone memory fell back to `main`.
- **why it matters**: multi-repo raccord committed 5 `chore(memory)` direct on `main`, NOTHING flagged it — nothing violated, exemption worked as designed. Divergence = guard (declares PROD protection) vs intended rule (all via branch); exemption MASKED it, raccord revealed it by violating the unencoded half. A guard encoding only PART of the intent reads as full enforcement — a false-green.
+- **why it matters**: multi-repo raccord committed 5 `chore(memory)` direct on `main`, NOTHING flagged it — nothing violated, exemption worked as designed. Divergence = guard (declares PROD protection) vs intended rule (all via branch); exemption MASKED it, raccord revealed it by violating unencoded half. Guard encoding only PART of intent reads as full enforcement — false-green.
- **future application**: when a guard exempts a class or checks one predicate, ask what it does NOT encode and whether a human leans on it for MORE than it enforces. Enforce the unencoded half where it actually lives (the aiguillage at skill start, [[BDR-045]]), do not push it into a guard that structurally can't hold it. Verify the guard's real scope against the rule's full scope before trusting "it would have caught it." See [[BDR-034]], [[BDR-045]], [[LRN-034]].
+- **future application**: when a guard exempts a class or checks one predicate, ask what it does NOT encode and whether a human leans on it for MORE than it enforces. Enforce the unencoded half where it actually lives (the aiguillage at skill start, [[BDR-045]]), do not push it into a guard that structurally can't hold it. Verify guard's real scope against rule's full scope before trusting "it would have caught it." See [[BDR-034]], [[BDR-045]], [[LRN-034]].
 ---
@@ -1057,9 +1057,9 @@ rules:
 ## LRN-089 — a pass-through wrapper whose callee reads ambient state silently ignores its args
 - **Date**: 2026-07-03
- **pattern**: a CLI/dispatcher that forwards `"$@"` to a function which derives its TARGET from ambient state (HEAD, cwd, env, "current X") rather than from those args → the args are silently dropped. The call SITE looks parameterized (`finish bugfix audit-bugs`) but the callee acts on whatever state it's standing in → wrong-target action, NO error. `gitflow_finish` read `HEAD`, never `$1/$2`; `finish bugfix X` from another branch merged that other branch.
+- **pattern**: CLI/dispatcher forwarding `"$@"` to a function deriving its TARGET from ambient state (HEAD, cwd, env, "current X") rather than from those args → args silently dropped. The call SITE looks parameterized (`finish bugfix audit-bugs`) but the callee acts on whatever state it's standing in → wrong-target action, NO error. `gitflow_finish` read `HEAD`, never `$1/$2`; `finish bugfix X` from another branch merged that other branch.
- **context**: audit 2026-07-02, `lib/gitflow.sh:257` `finish) gitflow_finish "$@"` passed args the function never consulted. Surfaced when a finish "for" one branch merged another (LOT3). [[BLK-015]].
+- **context**: audit 2026-07-02, `lib/gitflow.sh:257` `finish) gitflow_finish "$@"` passed args the function never consulted. Surfaced when finish "for" one branch merged another (LOT3). [[BLK-015]].
- **future application**: any wrapper/dispatcher forwarding args to a callee that resolves its target from ambient state — either (a) make the callee USE the args as the target, or (b) if the ambient-state contract is deliberate, treat passed args as an ASSERTION and refuse loudly when they disagree with the state. Never let forwarded args be silently dropped: silent-drop = the caller believes they steered, the callee ignored them. Sibling of "presence-flag ≠ capability" [[LRN-087]] — both = a visible signal lying about the real behavior.
+- **future application**: any wrapper/dispatcher forwarding args to a callee resolving its target from ambient state — either (a) make callee USE args as target, or (b) if ambient-state contract is deliberate, treat passed args as ASSERTION and refuse loudly when they disagree with state. Never let forwarded args be silently dropped: silent-drop = the caller believes they steered, the callee ignored them. Sibling of "presence-flag ≠ capability" [[LRN-087]] — both = visible signal lying about real behavior.
 - **Reference**: `lib/gitflow.sh` gitflow_finish arg-guard, `lib/gitflow-test.sh` T12. [[BLK-015]].
 ## LRN-090 — external-repo audit: open WIRED subsystems before declarative
@@ -1099,10 +1099,10 @@ rules:
 - **cousin**: [[BDR-050]] the pipeline; [[BDR-049]] fresh verifier; conditions [[LRN-083]].
 ## LRN-096 — A backstop is code: prove it can FAIL (flip-test) before trusting its green
- **pattern**: deterministic guard replacing a forgettable advisory is itself code; UNPROVEN guard = vacuous guard — [[LRN-048]] (a pass must prove it looked) applied to guards. LRN-093 backstop (refuse `\n` in grep/tf patterns) shipped with a regex requiring whitespace before `tf` → silently MISSED `tf` at line start (where the real locks sit). Flip-test (feed the guard a KNOWN offender, assert it bites) caught the hole; without it the guard would have green-lit the very class it was built to kill. So: a flip-test is MANDATORY at guard creation, part of the guard, not optional QA.
+- **pattern**: deterministic guard replacing forgettable advisory is itself code; UNPROVEN guard = vacuous guard — [[LRN-048]] (a pass must prove it looked) applied to guards. LRN-093 backstop (refuse `\n` in grep/tf patterns) shipped with regex requiring whitespace before `tf` → silently MISSED `tf` at line start (where real locks sit). Flip-test (feed guard a KNOWN offender, assert it bites) caught the hole; without it guard would have green-lit the very class it was built to kill. So: a flip-test is MANDATORY at guard creation, part of the guard, not optional QA.
- **why it matters**: the whole point of a backstop is that it fires on the bad case; a guard that can't fail proves nothing and is WORSE than the advisory it replaced (false confidence). Advisory→backstop move ([[LRN-047]] [[LRN-091]]) is sound only if the backstop is verified against a real miss.
+- **why it matters**: the whole point of a backstop is that it fires on the bad case; a guard that can't fail proves nothing and is WORSE than the advisory it replaced (false confidence). Advisory→backstop move ([[LRN-047]] [[LRN-091]]) sound only if backstop verified against a real miss.
- **context**: lot 5 `lib/tests/no-vacuous-locks.test.sh` 2026-07-04. Built the guard, flip-test RED'd (regex too weak, missed line-start `tf`), fixed the regex, flip-test green. Guard ships WITH the flip-test inline, self-proves on every run.
+- **context**: lot 5 `lib/tests/no-vacuous-locks.test.sh` 2026-07-04. Built guard, flip-test RED'd (regex too weak, missed line-start `tf`), fixed regex, flip-test green. Guard ships WITH flip-test inline, self-proves on every run.
- **future application**: building any guard/lint/census/backstop — bundle a flip-test (a synthetic offender the guard must catch) in the same file; a guard whose failure path was never exercised is untrusted. Corroborates [[LRN-047]]/[[LRN-091]] (advisory→deterministic): the *quality bar* on the deterministic replacement.
+- **future application**: building any guard/lint/census/backstop — bundle a flip-test (a synthetic offender the guard must catch) in the same file; a guard whose failure path was never exercised is untrusted. Corroborates [[LRN-047]]/[[LRN-091]] (advisory→deterministic): the *quality bar* on deterministic replacement.
 - **cousin**: [[LRN-048]] prove it looked; [[LRN-093]] the class this guards; [[LRN-046]] deterministic-oracle discipline.
 ## LRN-097 — Community blog pattern ≠ official feature: verify against docs before building infra
@@ -1146,8 +1146,8 @@ rules:
 - **backmerge**: from release/1.0.0 (74d3804) — 2026-07-08 review remediation A3.
 ## LRN-102 — Deliverable text before a tool call may never render: the turn's FINAL text is the only guaranteed display
- **pattern**: /deploy hand-back printed the full checklist, then called AskUserQuestion. The user saw ONLY the question UI — the checklist never reached them ("là on a rien, je dois ouvrir le fichier"). Harness reliably renders only the LAST text of a turn; text before a tool call can be swallowed by the tool UI.
+- **pattern**: /deploy hand-back printed full checklist, then called AskUserQuestion. The user saw ONLY the question UI — the checklist never reached them ("là on a rien, je dois ouvrir le fichier"). Harness reliably renders only LAST text of a turn; text before a tool call can be swallowed by tool UI.
- **why**: conversational deliverable (commands to copy-paste, a report) fails silently if any tool call follows the print — user sees "nothing displayed" while the transcript contains it. Structural fix: the deliverable IS the turn's final text; collect answers BEFORE printing, or let the reply arrive as the next user message.
+- **why**: conversational deliverable (commands to copy-paste, a report) fails silently if any tool call follows the print — user sees "nothing displayed" while the transcript contains it. Structural fix: deliverable IS the turn's final text; collect answers BEFORE printing, or let reply arrive as next user message.
 - **context**: 2026-07-05 /deploy run 2 (bchanot-cv). Skill patched same turn: checklist display-only (no NEXT.sh file at all — user: throwaway once deployed) + hand-back ends the turn, no tool call after.
 - **future application**: designing any skill/flow output meant to be read+used from the conversation — put it LAST; never sandwich a deliverable between tool calls; prefer plain-text report requests over blocking question tools after a deliverable.
 - **cousin**: [[LRN-100]] same skill lineage; CLAUDE.md communication doctrine (final message carries everything).
@@ -1156,8 +1156,8 @@ rules:
 - **pattern**: job3 docs-drift audit dispatched an exploration subagent (Bash + Read/Grep, "audit BODIES — do NOT modify any file") to check graphify skill docs. It ran `graphify .` to check CLI behavior — a real build, not a read — leaving an empty `graphify-out/` dir at repo root. The prompt said "read-only" and "verify via Read/Grep/Bash (read-only)" but never named the specific command class to avoid; the agent treated "run the CLI to see what it does" as within a Bash read-only mandate.
 - **why**: "read-only" is a framing about FILES, not an instruction the model maps onto every tool call by default — a subagent with Bash access will happily execute a program to observe its behavior, which is investigative but not read-only if the program writes to disk. The fix only landed after a main-session correction mid-run ("do NOT run graphify... verify by reading the installed source instead"), not from the original prompt.
- **context**: 2026-07-06, job3 audit exploration phase (`.audit/job3-report.md` A1/A2 findings, incident noted in the report header). No tracked file was touched; the stray dir was harmless but wasted a round-trip and could have mutated git-visible state on a less-guarded command.
+- **context**: 2026-07-06, job3 audit exploration phase (`.audit/job3-report.md` A1/A2 findings, incident noted in report header). No tracked file was touched; the stray dir was harmless but wasted a round-trip and could have mutated git-visible state on a less-guarded command.
- **future application**: any subagent dispatch framed as "read-only" / "audit" / "verify" that grants Bash — explicitly ban execution of the subject-under-test's own CLI/build/generator commands, and name the safe alternative (read installed source, grep docs) in the same sentence. Don't rely on the word "read-only" alone to scope tool use.
+- **future application**: any subagent dispatch framed "read-only" / "audit" / "verify" that grants Bash — explicitly ban execution of subject-under-test's own CLI/build/generator commands, and name safe alternative (read installed source, grep docs) in same sentence. Don't rely on the word "read-only" alone to scope tool use.
 - **cousin**: [[LRN-100]] (tool must clean its own scratch) — same class of "prose framing ≠ enforced constraint", different failure mode.
 ## LRN-103 — BLK-009 was stale: re-probe confirms `paths:` frontmatter works at BOTH levels now
@@ -1209,7 +1209,7 @@ rules:
 - **cousin**: [[BDR-058]] (this job's fix), darwin-skill's OVERSCOPED git-commit finding (job8 report — 3rd-party code, not patched, accepted risk under human-checkpoint gating, twin of [[LRN-105]]'s no-execute mandate for OUR read-only audits).
 ## LRN-110 — magic MCP `component_builder`'s local callback server = unauthenticated prompt-injection channel
- **context**: job8 audit read `dist/utils/callback-server.js:36` (+ `create-ui.js:35-38`) in the installed `@21st-dev/magic` package. `21st_magic_component_builder` opens a plain HTTP server on `127.0.0.1:9221+`, `Access-Control-Allow-Origin: *`, no token/origin check, staying open up to 10 minutes per call. Any POST body to `/data` is injected VERBATIM into the tool result the model consumes — any local process or open browser tab on the machine can win the race against the legitimate browser hand-back.
+- **context**: job8 audit read `dist/utils/callback-server.js:36` (+ `create-ui.js:35-38`) in installed `@21st-dev/magic` package. `21st_magic_component_builder` opens a plain HTTP server on `127.0.0.1:9221+`, `Access-Control-Allow-Origin: *`, no token/origin check, staying open up to 10 minutes per call. Any POST body to `/data` injected VERBATIM into tool result the model consumes — any local process or open browser tab on the machine can win the race against legitimate browser hand-back.
 - **future application**: this is in the third-party package's code, not our config — don't try to patch a vendored/npx-installed dependency. The only real lever is on OUR side of the boundary: never allowlist a tool with this shape, keep it `ask`-gated so a human sees every invocation (see [[BDR-059]]). Applies to any MCP tool whose implementation opens a listener to receive async results, not just this one — check the listener's auth/origin scoping when auditing MCP server code, the tool's *description* text tells you nothing about it.
 - **cousin**: [[BDR-059]] (the settings fix), [[LRN-111]] (why the allowlist stays empty), job8 report §2 surface 1 finding A#0. Magic MCP retired 2026-09-22 ([[BDR-093]]).
@@ -1226,16 +1226,16 @@ rules:
 - **cousin**: [[BDR-060]] (version floor), [[BDR-061]] (path-b bundle pattern), [[LRN-057]] (subagent invocation idioms).
 ## LRN-113 — Partial-pattern-fix is the job1-9 series' recurring defect: grep the whole surface + guard it
- **pattern**: fix one cited instance of a banned pattern, leave the twins. Review found 4: trailer stripped from commit-changer only (A1, twins in bugfixer/feater/hotfixer); YAML quoted elsewhere but seo/security-auditor left broken (A4); attribution scrubbed on 3 skills but geo-analyzer missed (A5); gitleaks added to the hook generator but the installed hook not regenerated (A2).
+- **pattern**: fix one cited instance of banned pattern, leave twins. Review found 4: trailer stripped from commit-changer only (A1, twins in bugfixer/feater/hotfixer); YAML quoted elsewhere but seo/security-auditor left broken (A4); attribution scrubbed on 3 skills but geo-analyzer missed (A5); gitleaks added to the hook generator but the installed hook not regenerated (A2).
 - **why it recurs**: the fixer greps for the reported line, fixes it, stops — never enumerates the pattern across the full surface. An adversarial review catches the twins later; nothing catches them at commit time.
- **fix**: every pattern-fix ends with (1) a whole-surface grep proving zero residue, (2) a deterministic make-test guard that REDs if any occurrence returns. Shipped `lib/tests/run-review-guards.sh` — G1 trailer, G2 false attribution, G3 strict-YAML, G4 reconcile hermeticity, G5 hook-drift; teeth-verified (planted violation REDs). This is the check that would have caught A1/A4/A5/A2 at make-test time instead of a review.
+- **fix**: every pattern-fix ends with (1) whole-surface grep proving zero residue, (2) deterministic make-test guard that REDs if any occurrence returns. Shipped `lib/tests/run-review-guards.sh` — G1 trailer, G2 false attribution, G3 strict-YAML, G4 reconcile hermeticity, G5 hook-drift; teeth-verified (planted violation REDs). Check that would have caught A1/A4/A5/A2 at make-test time instead of review.
- **future application**: any "fix pattern X" task → grep agents/ lib/ hooks/ templates/ skills/, add/extend a review-guard with teeth.
+- **future application**: any "fix pattern X" task → grep agents/ lib/ hooks/ templates/ skills/, add/extend review-guard with teeth.
 - **cousin**: [[LRN-114]] (hook-drift class), [[LRN-047]] (silent degradation → measure/guard).
 ## LRN-114 — Editing a hook generator does not touch the installed hook: reinstall + drift-guard
- **pattern**: job7 added the gitleaks scan to `_gitflow_emit_pre_commit` (the GENERATOR), but the installed `.githooks/pre-commit` is only (re)written by `gitflow init`/`install-hook`. job7 never re-installed → the repo's active hook stayed the pre-job7 version (620071b) for 8 days; `git commit` ran no secret scan while the team believed it did.
+- **pattern**: job7 added gitleaks scan to `_gitflow_emit_pre_commit` (the GENERATOR), but installed `.githooks/pre-commit` is only (re)written by `gitflow init`/`install-hook`. job7 never re-installed → the repo's active hook stayed the pre-job7 version (620071b) for 8 days; `git commit` ran no secret scan while the team believed it did.
- **why undetected**: T10 (drift test) compares only the hook's allow/block VERDICT, not content; T16 emits a FRESH hook in a throwaway repo, validating the generator, never the installed file. Both green while the installed hook was stale.
+- **why undetected**: T10 (drift test) compares only the hook's allow/block VERDICT, not content; T16 emits a FRESH hook in a throwaway repo, validating the generator, never the installed file. Both green while installed hook was stale.
- **fix**: after editing any template-generated artifact, regenerate the installed copy (`gitflow.sh install-hook`) AND add a content-drift gate — `run-review-guards.sh` G5 diffs installed `.githooks/pre-commit` against `emit-hook`.
+- **fix**: after editing any template-generated artifact, regenerate installed copy (`gitflow.sh install-hook`) AND add content-drift gate — `run-review-guards.sh` G5 diffs installed `.githooks/pre-commit` against `emit-hook`.
 - **future application**: any generator/template emitting an on-disk artifact needs an "installed == freshly-emitted" test, not just a behavioral one.
 - **cousin**: [[LRN-113]] (partial-fix + guard), [[LRN-039]] (installers drift hand-curated config).
@@ -1280,9 +1280,9 @@ rules:
 - **cousin**: [[LRN-119]] (same GSC+CrUX build); SDD skill's own "never HEAD~1" warning (same base-selection bug class).
 ## LRN-121 — Shell allowlist validation: `grep -Eq` is fragile; use a whole-string POSIX `case`
- **pattern**: guarding a user-supplied label to shell-safe ASCII with `printf '%s' "$v" | grep -Eq '^[A-Za-z0-9._-]+$'` failed 3 adversarial gate passes: (1) command-injection framing (label interpolated into an agent-composed Bash line); (2) parser differential — the guard pre-scanned argv for the literal `--label` while the downstream `argparse` ALSO accepts `--label=v` and abbreviations (`--labe`, `allow_abbrev=True`), those forms reached the parser unchecked; (3) `grep -q` matches PER LINE, a label with an embedded newline (`ok\nrm -rf`) passes on its FIRST line. Fix = replace the whole mechanism, don't patch again: `_label_safe() ( LC_ALL=C; case "$1" in ''|[!A-Za-z0-9]*|*[!A-Za-z0-9._-]*) exit 1;; esac )` — POSIX `case`, whole-string, C-locale subshell. No grep (no per-line), no regex, no second grammar to differ from; a newline is just a non-allowed byte caught by `*[!...]*`; `LC_ALL=C` stops UTF-8 collation widening `[A-Za-z0-9]` to homoglyphs (U+FF11, Kelvin U+212A).
+- **pattern**: guarding user-supplied label to shell-safe ASCII with `printf '%s' "$v" | grep -Eq '^[A-Za-z0-9._-]+$'` failed 3 adversarial gate passes: (1) command-injection framing (label interpolated into agent-composed Bash line); (2) parser differential — guard pre-scanned argv for literal `--label` while downstream `argparse` ALSO accepts `--label=v` and abbreviations (`--labe`, `allow_abbrev=True`), those forms reached parser unchecked; (3) `grep -q` matches PER LINE, label with embedded newline (`ok\nrm -rf`) passes on its FIRST line. Fix = replace the whole mechanism, don't patch again: `_label_safe() ( LC_ALL=C; case "$1" in ''|[!A-Za-z0-9]*|*[!A-Za-z0-9._-]*) exit 1;; esac )` — POSIX `case`, whole-string, C-locale subshell. No grep (no per-line), no regex, no second grammar to differ from; a newline is just a non-allowed byte caught by `*[!...]*`; `LC_ALL=C` stops UTF-8 collation widening `[A-Za-z0-9]` to homoglyphs (U+FF11, Kelvin U+212A).
 - **why it matters**: three distinct bypasses of the SAME guard = the approach was wrong, not each patch. `grep`'s line-orientation + locale-sensitive ranges, plus argv-prescan-vs-real-parser grammar drift, are the three classic ways an allowlist "passes" a string it shouldn't. Whole-string `case` in C locale closes all three at once. These were defense-in-depth (downstream used `"$2"`/`"$@"`/JSON-key, never `sh -c`/`eval` → not exploitable in the real exec chain) — but the backstop still took a categorical rewrite, and 3 security-gate BLOCKs to get there.
- **future application**: validate shell input WHOLE-STRING (`case` or bash `[[ =~ ]]`), never `grep -q` (per-line). Set `LC_ALL=C` for byte-wise ranges. Argv pre-scan guard must be STRICTER than the downstream parser (reject `=`-joined/abbrev) or validate post-parse against the value the parser settled on. When a fix is bypassed twice → STOP patching, replace the mechanism (re-plan, not whack-a-mole).
+- **future application**: validate shell input WHOLE-STRING (`case` or bash `[[ =~ ]]`), never `grep -q` (per-line). Set `LC_ALL=C` for byte-wise ranges. Argv pre-scan guard must be STRICTER than downstream parser (reject `=`-joined/abbrev) or validate post-parse against the value parser settled on. When a fix is bypassed twice → STOP patching, replace the mechanism (re-plan, not whack-a-mole).
 - **cousin**: [[LRN-119]] (fail-open engine this hardens), [[BDR-063]] (token store whose labels these guard), [[LRN-045]] (renaming-command leak-guard regexes — same charset-guard family).
 ---
@@ -1320,9 +1320,9 @@ rules:
 - **cousin**: [[BDR-066]] (model routing: reflection/audit big, execution sonnet), [[LRN-113]] (consumer-staleness sweep on a pattern fix).
 ## LRN-126 — splitting a monolith agent severs every IMPLICIT data path; forward each consumed field through the handoff contract
- **pattern**: wave-4 split (client-handover-writer monolith → reflection parent + sonnet doc-writer child) silently dropped 2 inputs the extracted STEPs consumed. `DEPLOY_HINTS` (detected in parent STEP 2, consumed by child STEP 14) + `--skip-seo` flag (parsed from `$ARGUMENTS`, gated child STEP 13) worked in the monolith by shared scope; after the split they were dead — never added to the PACKAGE. Child rendered a §8 without platform tailoring; `--skip-seo` became a silent no-op. Caught only by the opus whole-branch review, not the census.
+- **pattern**: wave-4 split (client-handover-writer monolith → reflection parent + sonnet doc-writer child) silently dropped 2 inputs extracted STEPs consumed. `DEPLOY_HINTS` (detected in parent STEP 2, consumed by child STEP 14) + `--skip-seo` flag (parsed from `$ARGUMENTS`, gated child STEP 13) worked in the monolith by shared scope; after the split they were dead — never added to the PACKAGE. Child rendered a §8 without platform tailoring; `--skip-seo` became a silent no-op. Caught only by the opus whole-branch review, not the census.
- **why**: monolith: `$ARGUMENTS`, detected vars, STEP-N side-outputs share one scope, later STEPs read them free. Split turns each free read into a data path that MUST cross the parent→child contract explicitly; every implicit read is a severed wire unless forwarded.
+- **why**: monolith: `$ARGUMENTS`, detected vars, STEP-N side-outputs share one scope, later STEPs read them free. Split turns each free read into data path that MUST cross parent→child contract explicitly; every implicit read is a severed wire unless forwarded.
- **future application**: splitting an agent: enumerate EVERY field the child reads (grep child for `PACKAGE.`, bare var names, `$ARGUMENTS` flags), diff against what the parent SETS before dispatch. Any child-consumed field the parent never populates = severed path = renders a hole or a silent no-op. A census that checks shape (model pin, gate-free) will NOT catch this — needs a data-flow read.
+- **future application**: splitting an agent: enumerate EVERY field child reads (grep child for `PACKAGE.`, bare var names, `$ARGUMENTS` flags), diff against what parent SETS before dispatch. Any child-consumed field the parent never populates = severed path = renders a hole or a silent no-op. A census that checks shape (model pin, gate-free) will NOT catch this — needs a data-flow read.
 - **cousin**: [[LRN-125]] (route consumer to right tier on a split), [[BDR-066]] (reflection/execution split), [[LRN-113]] (sweep ALL consumers). Distinct: 113/125 = WHICH agent/tier a consumer routes to; this = WHICH fields must cross the contract.
 ## LRN-127 — SDD implementers must not run destructive git ops on files outside their task scope
@@ -1333,9 +1333,9 @@ rules:
 ## LRN-128 — a version RESET (backward bump) is editorial reflection, not the forward-only release-executor
- **pattern**: first public release cut as v1.0.0 from an internal 4.x lineage = backward version.txt (4.0.0→1.0.0) + CHANGELOG restructure (new public `[1.0.0]` on top, old 1.0-4.0 lineage under a `## Pre-release (internal history)` banner) + tag swap (delete v4.0.0, tag v1.0.0). The sonnet `release-executor` (release-candidate skill's mechanical prep span) assumes a FORWARD semver bump — its prep = `[Unreleased]`→`[X.Y.Z]` move + version increment. Cannot derive a backward reset, the CHANGELOG restructure, or the existing-`[1.0.0]`-collision handling.
+- **pattern**: first public release cut as v1.0.0 from internal 4.x lineage = backward version.txt (4.0.0→1.0.0) + CHANGELOG restructure (new public `[1.0.0]` on top, old 1.0-4.0 lineage under `## Pre-release (internal history)` banner) + tag swap (delete v4.0.0, tag v1.0.0). Sonnet `release-executor` (release-candidate skill's mechanical prep span) assumes FORWARD semver bump — its prep = `[Unreleased]`→`[X.Y.Z]` move + version increment. Cannot derive a backward reset, the CHANGELOG restructure, or the existing-`[1.0.0]`-collision handling.
 - **why**: a reset is a JUDGMENT act (what's public vs pre-release, how to frame the launch, what to do with the old lineage) = reflection tier, not the executor's mechanical forward move.
- **future application**: version RESET or any non-standard release → do PREP MANUALLY inline (big model), use `gitflow.sh` only for branch mechanics (start/finish), KEEP the skill's human gates (when-to-release, push). Don't dispatch the forward-only executor for it. [[BDR-067]] [[BDR-066]]
+- **future application**: version RESET or any non-standard release → do PREP MANUALLY inline (big model), use `gitflow.sh` only for branch mechanics (start/finish), KEEP skill's human gates (when-to-release, push). Don't dispatch the forward-only executor for it. [[BDR-067]] [[BDR-066]]
 ## LRN-129 — `git cherry` (patch-id) proves a stale/divergent branch has nothing orphaned before you delete it
@@ -1354,9 +1354,9 @@ rules:
 - **Applied**: [[BDR-069]].
 ## LRN-131 — WebSearch is not verification for a number; require a primary source — 2026-07-17
- **pattern**: a statistic reaches a client only with `<claim> — <source, year, venue|vendor> — measured: <what the source ACTUALLY measured> — <link>`. The `measured:` field is what catches the error.
+- **pattern**: statistic reaches a client only with `<claim> — <source, year, venue|vendor> — measured: <what the source ACTUALLY measured> — <link>`. `measured:` field catches the error.
- **context**: "VSI (Visual Stability Index) — new 2026 Core Web Vital" lived in seo-analyzer as a threshold, stated as fact. It does NOT exist — absent from the CrUX API metric list AND web.dev; 10 SEO blogs cross-cited it into apparent consensus, several falsely claiming CrUX already collected it. And EVERY stat in agents/resources/ was real but grafted onto the wrong subject: Aggarwal 40% = ALL methods (pinned on "add stats"); AccuraCast 58.9% = Person-schema PREVALENCE (pinned on QAPage lift, meaning inverted — FAQPage was 1.8%); LLMrefs 3x = brand-mentions-vs-backlinks (pinned on freshness decay).
+- **context**: "VSI (Visual Stability Index) — new 2026 Core Web Vital" lived in seo-analyzer as threshold, stated as fact. It does NOT exist — absent from the CrUX API metric list AND web.dev; 10 SEO blogs cross-cited it into apparent consensus, several falsely claiming CrUX already collected it. EVERY stat in agents/resources/ was real but grafted onto wrong subject: Aggarwal 40% = ALL methods (pinned on "add stats"); AccuraCast 58.9% = Person-schema PREVALENCE (pinned on QAPage lift, meaning inverted — FAQPage was 1.8%); LLMrefs 3x = brand-mentions-vs-backlinks (pinned on freshness decay).
- **future**: the failure mode is plausible RECOMBINATION — what a model half-remembering a search produces. The old rule "cross-check via WebSearch" LAUNDERS the blog consensus instead of catching it. An API's metric list (e.g. developer.chrome.com/docs/crux) is decisive: a metric the API can't return is one you can't score. See [[LRN-132]] (same family, subagent summaries).
+- **future**: failure mode is plausible RECOMBINATION — what a model half-remembering a search produces. Old rule "cross-check via WebSearch" LAUNDERS blog consensus instead of catching it. An API's metric list (e.g. developer.chrome.com/docs/crux) is decisive: a metric the API can't return is one you can't score. See [[LRN-132]] (same family, subagent summaries).
 ## LRN-132 — a subagent summary is a claim, not a fact — verify before planning on it — 2026-07-17
 - **pattern**: relaying a subagent's characterisation without checking it propagates plausible-but-false. Treat every relayed finding as a claim to verify against a primary source or a live test.
@@ -1463,9 +1463,9 @@ Rule: when editing a doctrine file under structure locks, grep the test's lock s
 ## LRN-150 — Sourced shell lib is not a subprocess: prefix printers, honor inherited errexit
 - **Date**: 2026-09-15
- **Pattern**: `source lib.sh` shares the caller's shell. Two bites. (a) bare `ok()`/`warn()`/`info()` in the lib OVERRIDE the caller's same-named funcs. `doctor.sh` counts ERRORS/WARNS inside its own `warn()` → a lib `warn` disconnects the counter and doctor prints "No errors" while warnings scroll. Prefix every lib printer (`_gspw_ok`, `_gspw_warn`, `_gspw_info`). (b) caller's `set -euo pipefail` applies INSIDE the lib's functions: a failing command-substitution assignment (`x="$(. /etc/os-release; [ "$ID" = ubuntu ] && printf ...)"`) aborts the CALLER when the func is called as a bare statement. Reproduced — exit 1 on every non-Ubuntu host, latent in `install-plugins.sh` since [[BDR-029]].
+- **Pattern**: `source lib.sh` shares caller's shell. Two bites. (a) bare `ok()`/`warn()`/`info()` in lib OVERRIDE caller's same-named funcs. `doctor.sh` counts ERRORS/WARNS inside its own `warn()` → a lib `warn` disconnects the counter and doctor prints "No errors" while warnings scroll. Prefix every lib printer (`_gspw_ok`, `_gspw_warn`, `_gspw_info`). (b) caller's `set -euo pipefail` applies INSIDE lib's functions: failing command-substitution assignment (`x="$(. /etc/os-release; [ "$ID" = ubuntu ] && printf ...)"`) aborts CALLER when func is called as bare statement. Reproduced — exit 1 on every non-Ubuntu host, latent in `install-plugins.sh` since [[BDR-029]].
- **Rule**: public func called bare → `return 0` on every path + `|| true` on every capture. Func allowed to return non-zero → call it ONLY as an `if` condition.
+- **Rule**: public func called bare → `return 0` on every path + `|| true` on every capture. Func allowed to return non-zero → call ONLY as `if` condition.
- **Future application**: any new `lib/*.sh` sourced by a script that owns printers or sets `-e`. Check BOTH facets before wiring; the printer one is silent (no error, just a lying summary).
+- **Future application**: any new `lib/*.sh` sourced by script owning printers or setting `-e`. Check BOTH facets before wiring; the printer one is silent (no error, just a lying summary).
 - **Reference**: `lib/gstack-playwright.sh`, `doctor.sh:12-15`. Links [[BDR-088]].
 ---
@@ -1496,9 +1496,9 @@ Rule: when editing a doctrine file under structure locks, grep the test's lock s
 ## LRN-154 — Untracking a generated file then merging deletes it from disk
 - **Date**: 2026-09-15
- **Pattern**: `git rm --cached` removes from the index and KEEPS the working file, which is the whole point when untracking a tool-generated artifact. But `gitflow finish` checks out the target branch first, where the file is still tracked, so git restores it; the merge then applies the deletion to a tracked file and removes it from disk. `.gitignore` does not protect it — it only stops a re-add. Net effect: the file survives the commit and dies at the merge, several minutes later, which reads as unrelated.
+- **Pattern**: `git rm --cached` removes from index and KEEPS working file, the whole point when untracking a tool-generated artifact. But `gitflow finish` checks out target branch first, where file is still tracked, so git restores it; merge then applies deletion to a tracked file and removes it from disk. `.gitignore` does not protect it — it only stops a re-add. Net effect: file survives commit, dies at merge several minutes later, reads as unrelated.
- **Detection**: the working tree is clean and the file is simply absent. Nothing errors. Only a post-merge `ls` catches it.
+- **Detection**: working tree clean, file simply absent. Nothing errors. Only post-merge `ls` catches it.
- **Future application**: untracking any generated file — know the regeneration command BEFORE merging, and `ls` the path right after `finish`. If nothing regenerates it, keep it tracked.
+- **Future application**: untracking any generated file — know regeneration command BEFORE merging, `ls` the path right after `finish`. If nothing regenerates it, keep it tracked.
 - **graphify specifics**: `graphify install --platform claude` copies the skill and touches nothing else. `graphify claude install` is a different command — it writes the CLAUDE.md section and the `.claude/settings.json` hooks, rewrites both guarded configs, and does NOT copy the skill. Confusing the two wastes a recovery attempt.
 - **Reference**: `CLAUDE.md` machine-owned section, commit 80ccdaf. Links [[BDR-090]].
@@ -1516,16 +1516,16 @@ Rule: when editing a doctrine file under structure locks, grep the test's lock s
 ## LRN-157 — Taste is invisible to a gap-only trigger; ask at plan time
 - **Date**: 2026-09-16
- **Pattern**: a trigger that fires only on missing outcome / scope / constraints lets every taste choice through — "add a share icon" is complete by those criteria and the icon's side is decided downstream. More budget changes nothing; the fix is a new trigger class (VISIBLE / PUBLIC NAME / SCOPE). Cost geometry: a fresh re-dispatch keeps the working tree and loses the executor's reasoning → the same question costs about one executor run more mid-run than at PLAN. So: sweep once at the plan step, keep the mid-run channel for leftovers. Executor tags the class; orchestrator re-reads it (tag = hint, a mis-tag would offload class 4 onto the human). Relayed questions obey [[LRN-102]]: context inside `AskUserQuestion`, nothing the user needs printed before it.
+- **Pattern**: trigger firing only on missing outcome / scope / constraints lets every taste choice through — "add a share icon" is complete by those criteria, icon's side decided downstream. More budget changes nothing; the fix is a new trigger class (VISIBLE / PUBLIC NAME / SCOPE). Cost geometry: fresh re-dispatch keeps working tree, loses executor's reasoning → same question costs about one executor run more mid-run than at PLAN. So: sweep once at plan step, keep mid-run channel for leftovers. Executor tags class; orchestrator re-reads it (tag = hint, mis-tag would offload class 4 onto the human). Relayed questions obey [[LRN-102]]: context inside `AskUserQuestion`, nothing the user needs printed before it.
- **Future application**: any "ask more" request → check WHICH trigger is blind before touching a quota. Any orchestrator with a "decide it yourself" fallback on an executor halt → route by class first.
+- **Future application**: any "ask more" request → check WHICH trigger is blind before touching quota. Any orchestrator with "decide it yourself" fallback on executor halt → route by class first.
 - **Reference**: [[BDR-091]], `lib/contract-interview.md` STEP 2 + MID-RUN CLARIFICATION.
 ## LRN-158 — A hardened installer + a symlinked config dir = documented command fails; stage under a throwaway HOME
 - **Date**: 2026-09-22
- **Context**: `21st install-skill` (= `21st skills install --global`) is upstream's documented one-liner. Here it dies: `Refusing to access symbolic link /home/…/.claude/skills`. The installer walks every segment of `<HOME>/.claude/skills/<n>/SKILL.md` with an `assertNoSymlinkComponents` guard (anti symlink-escape); this repo's whole model is `~/.claude/skills -> repo/skills`. Two correct designs, mutually exclusive on the same path.
+- **Context**: `21st install-skill` (= `21st skills install --global`) is upstream's documented one-liner. Here it dies: `Refusing to access symbolic link /home/…/.claude/skills`. Installer walks every segment of `<HOME>/.claude/skills/<n>/SKILL.md` with `assertNoSymlinkComponents` guard (anti symlink-escape); this repo's whole model is `~/.claude/skills -> repo/skills`. Two correct designs, mutually exclusive on same path.
- **Pattern**: don't fight the guard and don't unlink the config dir. Run the installer with `HOME=$(mktemp -d)` so it writes into a pristine real tree, then move the output to the vendored dir the repo controls and symlink from there. Same shape as the impeccable/ctx7 staging (`mktemp -d`, install, `mv` into `skills-external/`), with HOME as the extra lever. Two conditions make it safe: the command must need nothing else from HOME (checked: manifest + content fetch are unauthenticated, hash-verified), and the moved payload must be self-contained.
+- **Pattern**: don't fight the guard and don't unlink the config dir. Run installer with `HOME=$(mktemp -d)` so it writes into pristine real tree, then move output to the vendored dir the repo controls and symlink from there. Same shape as impeccable/ctx7 staging (`mktemp -d`, install, `mv` into `skills-external/`), HOME as extra lever. Two conditions make it safe: the command must need nothing else from HOME (checked: manifest + content fetch are unauthenticated, hash-verified), and the moved payload must be self-contained.
- **Also**: read the npm tarball, not the vendor's web page. 21st.dev's `/mcp` and `/llms.txt` still document the MCP `init --client` flow with an API key; the package README states the CLI supersedes it. `curl registry.npmjs.org/<pkg>` + untar + read `README.md`/`dist` answered every question (commands, exit codes, where files land) that the site got wrong.
+- **Also**: read the npm tarball, not the vendor's web page. 21st.dev's `/mcp` and `/llms.txt` still document MCP `init --client` flow with API key; package README states CLI supersedes it. `curl registry.npmjs.org/<pkg>` + untar + read `README.md`/`dist` answered every question (commands, exit codes, where files land) the site got wrong.
- **Future application**: any vendor installer that writes into `~/.claude`, `~/.config` or `~/.agents` on this machine. Probe first with a fake HOME containing the symlink, before wiring it into `install-plugins.sh` — the failure is instant and unambiguous.
+- **Future application**: any vendor installer writing into `~/.claude`, `~/.config` or `~/.agents` on this machine. Probe first with fake HOME containing the symlink, before wiring into `install-plugins.sh` — failure is instant and unambiguous.
 - **Reference**: [[BDR-093]], `install-plugins.sh` Step 8.7, `update-all.sh` 7.4. Links [[LRN-034]] (run the real thing), [[BLK-014]]-class symlink/self-heal issues.
 ## LRN-159 — A pin whose payload is fetched at install time rots: pin + fallback, and read the installer's output, not its exit code
@@ -1537,8 +1537,8 @@ Rule: when editing a doctrine file under structure locks, grep the test's lock s
 ## LRN-160 — Prose guardrails are judgment, not boundary: a well-argued brief walks a sub-agent through them
 - **Date**: 2026-09-22
- **Context**: 2026-09-21 00:21, old server. Reviewer sub-agent (opus, atlast SDD task 26) briefed by the orchestrator: "Tracing lftp semantics against a scratch tree of your own making, outside the repository, is allowed". It ran `mirror --reverse --delete` against a local `file://` tree; target resolved to a real path; `mirror --delete` = `rm -r` on target dirs absent from source, `--exclude` ignored. 90 s: home, `~/.claude`, `/tmp` outputs, NAS (`uid=1000`), 15 Gitea repos (Gitea ran as bchanot = uid 1000, no Docker bridge needed). Reviewer's next Bash rc 1 with its output file gone, then API "Not logged in" (credentials wiped). Config of the day already had hard_deny "deploy to provider" + soft_deny `rsync --delete`: neither names lftp nor a local trace. 4 days of faunosteo never pushed; Gitea on the same disk.
+- **Context**: 2026-09-21 00:21, old server. Reviewer sub-agent (opus, atlast SDD task 26) briefed by orchestrator: "Tracing lftp semantics against a scratch tree of your own making, outside the repository, is allowed". Ran `mirror --reverse --delete` against local `file://` tree; target resolved to a real path; `mirror --delete` = `rm -r` on target dirs absent from source, `--exclude` ignored. 90 s: home, `~/.claude`, `/tmp` outputs, NAS (`uid=1000`), 15 Gitea repos (Gitea ran as bchanot = uid 1000, no Docker bridge needed). Reviewer's next Bash rc 1 with its output file gone, then API "Not logged in" (credentials wiped). Config of the day already had hard_deny "deploy to provider" + soft_deny `rsync --delete`: neither names lftp nor a local trace. 4 days of faunosteo never pushed; Gitea on the same disk.
- **Pattern**: (a) an LLM classifier reads intent; the orchestrator's brief IS the sub-agent's user voice, so a reasoned authorization passes. Only static deny rules (resolve first, inherited by sub-agents, per-segment on `&&`) and OS rights are boundaries. (b) "Trace what it would do" is execution; a scratch target from a variable is one unset var away from `/`. (c) The event deletes its own evidence when the agent's uid owns the logs, the config and the transcripts. (d) A remote backs up only what it holds: push at branch creation and at every commit, from a hook, not from discipline. (e) `git merge` fires post-merge, not post-commit.
+- **Pattern**: (a) LLM classifier reads intent; orchestrator's brief IS sub-agent's user voice, so reasoned authorization passes. Only static deny rules (resolve first, inherited by sub-agents, per-segment on `&&`) and OS rights are boundaries. (b) "Trace what it would do" is execution; scratch target from a variable is one unset var away from `/`. (c) Event deletes its own evidence when agent's uid owns logs, config and transcripts. (d) A remote backs up only what it holds: push at branch creation and at every commit, from a hook, not from discipline. (e) `git merge` fires post-merge, not post-commit.
 - **Future application**: any new destructive capability → static deny first, prose second, doctrine third. Any orchestrator brief → never "X is allowed outside the repo". Sub-agent tools: report-only agents trace by reading. Probe a guard with the real sub-agent path (auto mode inherited), not the main session.
 - **Reference**: [[BDR-095]], `/mnt/cloudpex/RECOVERY/00-incident/`, atlast transcript `26e76a0b…` + stub `agent-a7d9119…`. Links [[BDR-090]], [[BDR-092]], [[LRN-155]], [[LRN-114]].