@event4u/agent-config 6.1.0 → 7.0.1

package/docs/archive/CHANGELOG-pre-7.0.0.md

@@ -0,0 +1,126 @@
+# Changelog Archive — pre-7.0.0
+
+> Frozen snapshot of `event4u/agent-config` changelog entries
+> released before `7.0.0`, split out of the main
+> [`CHANGELOG.md`](../../CHANGELOG.md) by `scripts/release.py`
+> once the active era's body crossed the drift cap enforced by
+> `tests/test_changelog_eras.py`.
+>
+> **Read-only.** New entries land in `CHANGELOG.md`. Entries
+> here are not amended — git tags remain the canonical source
+> for what shipped.
+>
+> Entry shape follows
+> [`../contracts/CHANGELOG-conventions.md`](../contracts/CHANGELOG-conventions.md).
+
+## [6.1.0](https://github.com/event4u-app/agent-config/compare/6.0.0...6.1.0) (2026-06-14)
+
+### Features
+
+* **rules:** Iron Law — never drop inherited/shared-branch commits without asking ([e03dc18](https://github.com/event4u-app/agent-config/commit/e03dc18300a2ef032d508062be032267a1f1f844))
+* **workspace:** plain-language host-decision explainability + employee-mode gate (6.0.0 P5) ([f485476](https://github.com/event4u-app/agent-config/commit/f485476050d3d7660aa3aaeacc54438e5eee44a9))
+* **governance:** workspace boundary contract + import-edge drift linter (6.0.0 P4) ([943eb29](https://github.com/event4u-app/agent-config/commit/943eb29747eb3dca0988317e2a526cd38d12f06c))
+* **install:** preview-only dry-run for the upgrade-cleanup reaper (6.0.0 P2) ([4caa802](https://github.com/event4u-app/agent-config/commit/4caa802b1fd1bbf1beda71e5ad553000e7b7f2bf))
+* **create-pr:** run the PR-gate archival sweep before opening the PR ([bdd645b](https://github.com/event4u-app/agent-config/commit/bdd645b3bcc7443c00df653d8f53982417d0ca3e))
+* **roadmaps:** deterministic PR-gate archival sweep ([10643ca](https://github.com/event4u-app/agent-config/commit/10643ca9f5ff56ff02f376531e5c8c07998aa08d))
+* **memory:** remove agent-memory Layer 2; file-first memory only ([c8903c6](https://github.com/event4u-app/agent-config/commit/c8903c6f3a5502434b29c1b55535a9ebc3c55ac4))
+* **bench:** v2 pilot run + honest-null report; spawn stratified follow-up (Phase 4-6) ([5b7f7bd](https://github.com/event4u-app/agent-config/commit/5b7f7bd1112462f83ca42ef6509f4871cdba7ebe))
+* **bench:** v2 dual-axis scorer + runner + paired stats (Phase 2-3) ([ae25ee2](https://github.com/event4u-app/agent-config/commit/ae25ee2c7a8b0fe6325a0c886911a8c48c7546d5))
+* **bench:** v2 discipline-axis corpus + fixtures (Phase 0-1) ([1371dd0](https://github.com/event4u-app/agent-config/commit/1371dd05096c38c7f28f0c4a55b1daf2bb230500))
+* **bench:** wrapper-lift A/B benchmark — model-pin, budget-cap, error-aware ([a09238a](https://github.com/event4u-app/agent-config/commit/a09238ad0455baaf6f68016a195ad54725acd3a3))
+* **reasoning:** add model-agnostic Reasoning Discipline Protocol (RDP) ([b4b5bec](https://github.com/event4u-app/agent-config/commit/b4b5bec18f58630add4e7802c9e32b46b88f3084))
+* **security:** Phase 3 consumer audit + runtime injection hook + review skill ([23efe50](https://github.com/event4u-app/agent-config/commit/23efe5001104c1fd7056f7b2216fc4583f7f29f3))
+* **security:** Phase 2 injection-aware authoring rules ([eb41da9](https://github.com/event4u-app/agent-config/commit/eb41da9c7a1e3140d1efad760bd06e0bd53cb513))
+* **security:** Phase 1 self-audit corpus linters + containment convention ([f678aba](https://github.com/event4u-app/agent-config/commit/f678abab7b521f389e16abb837594b3d23a38d5f))
+* **ai-council:** resolve config user-global-first ([9177b52](https://github.com/event4u-app/agent-config/commit/9177b52a99842b3adffc21b325b39610ef520c6d))
+* **ci:** guard against re-introducing external-source references ([88d35d9](https://github.com/event4u-app/agent-config/commit/88d35d913f5afec7db33f5817229b366cac7256f))
+* **doctor:** add read-only stale-orphans health check ([48e6118](https://github.com/event4u-app/agent-config/commit/48e6118eab2e39fbfa1884a9f6defb1c8719a2ba))
+* **packs:** split meta into capability-scoped packs ([b363839](https://github.com/event4u-app/agent-config/commit/b3638393a6c67ecaac41ae19df89b2ed0b03154b))
+* **commands:** add first-class visibility frontmatter field ([db4d88d](https://github.com/event4u-app/agent-config/commit/db4d88dcf41629f27973624d6476f935be32e2c9))
+
+### Bug Fixes
+
+* **refs:** mark the RDP-contract acceptance criterion as a forward-ref ([c7cee96](https://github.com/event4u-app/agent-config/commit/c7cee966495a5c96932c9f2b71ab72aae517623f))
+* **memory:** mine-session description ≤200 chars + command-count floor ([f368e06](https://github.com/event4u-app/agent-config/commit/f368e0667980e3f3a03233e8152fd23daaa8bc5d))
+* **bench:** lint-bench-ab validates the v2 docs/benchmark.md sections ([41d552b](https://github.com/event4u-app/agent-config/commit/41d552bd3a162577be3a898fca9123cce87b38b9))
+* **server:** mirror reasoning.* in settings schema (template parity + diff) ([5f77256](https://github.com/event4u-app/agent-config/commit/5f77256da1ecbfa03f3aa1261f23ec940991c2bc))
+* **reasoning:** skill-lint senior sections + valid rule tier (2b) ([7f3e278](https://github.com/event4u-app/agent-config/commit/7f3e2789ab483b6938a39aac303f1fbe2f35792e))
+* **security:** refresh threat-model command effective-hash ([5505b57](https://github.com/event4u-app/agent-config/commit/5505b57fa6e4e4bf02e2891f49a30e6dc9128da1))
+* **security:** tighten security-sensitive-stop — clear long_rule lint regression ([d528126](https://github.com/event4u-app/agent-config/commit/d528126120bf51335267bdde66793343ec376c87))
+* **security:** list agent-security-review + security-audit-config in marketplace.json ([f432a62](https://github.com/event4u-app/agent-config/commit/f432a62d42fab5fc6707b166e869ca8cc2d5d866))
+* **security:** CI — portability reword + settings-schema parity for injection_scan ([fa78a58](https://github.com/event4u-app/agent-config/commit/fa78a589101fd41984d85496666f2fd618e49a1f))
+* **cli:** preflight dependency guard with an actionable message ([ce58c76](https://github.com/event4u-app/agent-config/commit/ce58c7683541a3bc22852186a9764be127f87e4b))
+* **repo:** untrack stray node_modules symlink, ignore symlink form ([67cc9e6](https://github.com/event4u-app/agent-config/commit/67cc9e61deb241aa23e9affaa5adc1fd92d99f14))
+* **refs:** exempt gitignored agents/.harvest-local in check_references ([0d0b170](https://github.com/event4u-app/agent-config/commit/0d0b1702c27c06e96d486211f639148f7ed0628e))
+* **refs:** mark gitignored harvest-local ref in security-pillar roadmap ([3abf215](https://github.com/event4u-app/agent-config/commit/3abf215692cf49ac190248c0007668b5a7b1e1f0))
+* **ci:** guard against empty (0-byte) roadmap files ([5115865](https://github.com/event4u-app/agent-config/commit/511586591171735437bba8cdb106094628a3d611))
+* **roadmaps:** restore competitive-borrow v6 work, drop empty reaping stub ([9fceeb7](https://github.com/event4u-app/agent-config/commit/9fceeb7fc9585965f44e25543a9699d0ff8ee519))
+* **ai-council:** align user-global config path with the setup wizard ([54de5a8](https://github.com/event4u-app/agent-config/commit/54de5a853c271311d79b2b436dd3fa58fa25eb69))
+* **rule:** drop non-portable task-invocations from source-confidentiality backstop ([57e6f7f](https://github.com/event4u-app/agent-config/commit/57e6f7fe5199cc5192ead2a1468ad7d04dd5d5bc))
+* **install:** always-run tag sweep so reaping catches pre-inventory orphans ([91e5418](https://github.com/event4u-app/agent-config/commit/91e541852c30899cb84dd2070f705dfe7947d350))
+* **discovery:** register visibility + new capability packs in schema/vocab ([1fcc72b](https://github.com/event4u-app/agent-config/commit/1fcc72b08fbd13f85c01d3df7fbc98790395ac91))
+
+### Documentation
+
+* **domain-watch:** capture deferred heavyweight tracks in one watch-note (6.0.0 P6) ([e212e1f](https://github.com/event4u-app/agent-config/commit/e212e1fcebed5d61c63d0719deb485787aca6fde))
+* **changelog:** add 6.0.0 release overview + breaking-changes section (6.0.0 P3) ([fdb4b63](https://github.com/event4u-app/agent-config/commit/fdb4b63cd495489341215430ae12a9866cb8503b))
+* fix stale source-of-truth paths and drop above-fold jargon (6.0.0 P1) ([9ee9870](https://github.com/event4u-app/agent-config/commit/9ee98708e1fdcf612848b393aace48b33a548e99))
+* **roadmaps:** add capability-discoverability follow-up from fable-feedback-3 ([a658c2f](https://github.com/event4u-app/agent-config/commit/a658c2f9c338182d1db2db503ab8ce6aa9c1f42f))
+* **model-recommendation:** add orchestrator→subagent model-routing guidance ([669f83d](https://github.com/event4u-app/agent-config/commit/669f83de5b2e6de590d87f7a093eb098bcf8a086))
+* **roadmaps:** add RDP discoverability roadmap ([c65e1b2](https://github.com/event4u-app/agent-config/commit/c65e1b2648af8bfd2a39a6c6dc74124cfc67101b))
+* **roadmaps:** revise discipline-axis pilot for weak-host-first methodology ([9ccb816](https://github.com/event4u-app/agent-config/commit/9ccb816b1fe449cb537567696487c09a4ea2ee8e))
+* **rules:** replace Merge-gated with PR-gate in roadmap-progress-sync ([c140687](https://github.com/event4u-app/agent-config/commit/c1406876e880babd70a178bb958af89f31c49eec))
+* **roadmaps:** memory-layer-cleanup removal + consolidation plans ([254758f](https://github.com/event4u-app/agent-config/commit/254758f1a24d7898b5828a3396d20b7498370d08))
+* **roadmap:** check-refs:skip discipline-axis bench (external repo citations) ([13c5fdb](https://github.com/event4u-app/agent-config/commit/13c5fdb04016c40488140f59688e9db88eee0d9d))
+* **roadmaps:** agent-memory removal + memory-pipeline consolidation plans ([6fbf6a6](https://github.com/event4u-app/agent-config/commit/6fbf6a6d33571839f8c85b276a8728ff62c606c7))
+* **roadmaps:** 3-condition value bench (v1) + discipline-axis bench (v2) ([f5a89c6](https://github.com/event4u-app/agent-config/commit/f5a89c69e60c345dbb655f3b0dab294d2b56669a))
+* **roadmaps:** RDP eval+promotion follow-up; archive frontier-reasoning parent ([417223b](https://github.com/event4u-app/agent-config/commit/417223bce4a4d04404512cfa804ad872dd11324c))
+* **roadmap:** security pillar — supply-chain integrity + injection-aware authoring ([c15ef6a](https://github.com/event4u-app/agent-config/commit/c15ef6adc17226513660b324b7960dc80125bbf3))
+* **roadmap:** fill in road-to-6.0.0-final-readiness ([46ba5a0](https://github.com/event4u-app/agent-config/commit/46ba5a002fb300afbce43e56b92a945bd0957dec))
+* **roadmap:** add image/brand/typography + greenfield-scaffold roadmaps ([f615452](https://github.com/event4u-app/agent-config/commit/f6154528a7b1ba34fb5543c91ac2c905999d2e8c))
+* **ai-council:** repoint config references to the user-global path ([1307f80](https://github.com/event4u-app/agent-config/commit/1307f804b2c1cc4a2b9a3d2ad1b829f2a7108619))
+* **ai-council:** document user-global config location (ADR-093) ([c501e55](https://github.com/event4u-app/agent-config/commit/c501e557fdb94d7214555a3b53042a275b2dc923))
+* **roadmap:** competitive-borrow plan (source-anonymous) ([9e3c692](https://github.com/event4u-app/agent-config/commit/9e3c692745170ad62b0f67d40afa8aad751e34dd))
+* **roadmap:** close metadata-leanness, spawn tier-removal follow-up ([93d5361](https://github.com/event4u-app/agent-config/commit/93d5361d05d5ddef944d4931c6260e69464d8270))
+* **adr:** ADR-092 defer command tier-alias removal (forcing-function) ([71d2630](https://github.com/event4u-app/agent-config/commit/71d26300d14c9b894dfef19ed6a6b3c996f5895f))
+* **roadmap:** metadata & command-surface leanness plan + evidence ([b31d106](https://github.com/event4u-app/agent-config/commit/b31d1061f5816eb3a8aadd4bd154e76ee00d089a))
+* **roadmap:** archive completed reaping-orphans fix plan ([c1ed447](https://github.com/event4u-app/agent-config/commit/c1ed4478f14c634c5fde5dbed224f72ae2c6eedb))
+* record evidence-gated decisions, archive residuals roadmap ([3657e12](https://github.com/event4u-app/agent-config/commit/3657e12fbcacb4740b4d1d84309d7dea28cd3c58))
+
+### Refactoring
+
+* **ai-council:** relocate config out of the repo to user-global ([17fb14a](https://github.com/event4u-app/agent-config/commit/17fb14a03736cb14f2f56861f194e5bfc00e80b9))
+* **commands:** fold fix:pr-bot/developer-comments into fix:pr-comments ([4c1c1c8](https://github.com/event4u-app/agent-config/commit/4c1c1c8795d422e1ba8d5ae77409f43f3b8fb2e5))
+
+### Tests
+
+* lower command-surface floor to 148 after fix:pr-* fold ([2b5e9ef](https://github.com/event4u-app/agent-config/commit/2b5e9ef7f6a8160aac6d2d26bb2876d7d8ed1427))
+* **install:** lock the reaping-gap class against regression ([d7ca6d0](https://github.com/event4u-app/agent-config/commit/d7ca6d0f967672d02d0b367fcfa408f6d675a220))
+
+### CI
+
+* **skill-lint:** also enforce rule tiers + guard the CI wiring ([6cde280](https://github.com/event4u-app/agent-config/commit/6cde2809c5ace248807236dee9634a590955795d))
+* **skill-lint:** run lint-command-tiers on every PR ([2e123c6](https://github.com/event4u-app/agent-config/commit/2e123c696a6bf2047cbc4473a9555c51b8f33da8))
+
+### Chores
+
+* **roadmaps:** complete + archive road-to-6.0.0-final-readiness (6.0.0) ([652294a](https://github.com/event4u-app/agent-config/commit/652294ad01ad48a2875ebd75953b82d06c350e56))
+* **roadmaps:** archive completed memory-layer-cleanup roadmaps ([9380482](https://github.com/event4u-app/agent-config/commit/9380482cf512c73f0783ff7a2270793d5dca8b95))
+* **memory:** regenerate pack manifest for shortened mine-session description ([14cec0e](https://github.com/event4u-app/agent-config/commit/14cec0ed0c6de254639e3727d7ad1f3a3147902e))
+* **memory:** regenerate projections, catalogs, and dashboard ([78cc1a1](https://github.com/event4u-app/agent-config/commit/78cc1a1180f6eced4c60e0c408da1103d0621ab0))
+* **roadmaps:** regenerate progress dashboard ([d0d2757](https://github.com/event4u-app/agent-config/commit/d0d2757e93026fab6f995732a130f126371e7978))
+* **security:** archive road-to-security-pillar (Phases 1-3 shipped) ([ad5f552](https://github.com/event4u-app/agent-config/commit/ad5f55204bae429b960db40976c3dc40ea759f97))
+* **security:** bump command-count messaging 148→149 (new /security-audit-config) ([5f5b79a](https://github.com/event4u-app/agent-config/commit/5f5b79a1d741b1565cfbc0aaf8c74aa43165fd0b))
+* **security:** regenerate dist, router, counts, pack manifests ([84ff0fc](https://github.com/event4u-app/agent-config/commit/84ff0fcd1216fbbd05a3a340148f681b95c2d4a8))
+* add uncomitted roadmaps ([699c2c5](https://github.com/event4u-app/agent-config/commit/699c2c5e8a70453a46b9c70e68ba621f96a5f64c))
+* **condense:** reconcile stale condensation hashes ([d9ac27e](https://github.com/event4u-app/agent-config/commit/d9ac27e232cc60dba941f75632dde9a5bbd2c4db))
+* add uncomitted roadmaps ([28ff06c](https://github.com/event4u-app/agent-config/commit/28ff06ce3741db46a5d39e1bc0a2a698d3a94c1f))
+* **rules:** track anonymized harvest roadmaps; harden source-confidentiality ([bc77fb9](https://github.com/event4u-app/agent-config/commit/bc77fb93476c8045cd227f94ad09b0f1f3cebbdd))
+* sync stale condensation for work / agents-init / agents-optimize ([0f816ca](https://github.com/event4u-app/agent-config/commit/0f816cae017824af718cd750457bfc1476252927))
+* sync command-count messaging to 148 after fix:pr-* removal ([94097ce](https://github.com/event4u-app/agent-config/commit/94097ce0bee1739d2f54688705b1aaf78a73cee4))
+* sync stale condensation hashes for unchanged command files ([a32da9a](https://github.com/event4u-app/agent-config/commit/a32da9a5c4199d1148549f63bf7c0012496cd2b6))
+* remove external-source references from the tracked tree ([3248611](https://github.com/event4u-app/agent-config/commit/3248611a8ae2e7d0574ba8e121f85077faae9f69))
+* **commands:** backfill visibility + re-tag pack across command sources ([d08f5b6](https://github.com/event4u-app/agent-config/commit/d08f5b6550735db22f4f855f155d2fd91a8dc047))
+* **changelog:** split era 5.9.x → pre-6.0.0 ([c442750](https://github.com/event4u-app/agent-config/commit/c44275053c07352402e162d6accbe67f6d380010))
+
+Tests: 6068

package/docs/benchmark.md

@@ -4,74 +4,71 @@
 
 ## Honesty labels (read first)
 
-> 1. **Wrapper-lift on a fixed host (`claude-sonnet-4-6`), NOT model-vs-model.** Measures what the agent-config package does to ONE host model on a neutral fixture — not a capability ranking.
+> 1. **Wrapper-lift on a fixed host (`claude-haiku-4-5`), NOT model-vs-model.** Measures what the agent-config package does to ONE host model on a neutral fixture — not a capability ranking.
 > 2. **Discipline axis, not capability.** The headline is the *discipline* delta (did it stay minimal / verify / ask / not destroy / update downstream), not whether the goal was achievable.
-> 3. **PILOT — low statistical power (N=5 tasks × 1 seed(s)).** Directional only.
+> 3. **PILOT — low statistical power (N=2 tasks × 12 seed(s)).** Directional only.
 > 4. **Paired design**, errored runs excluded; McNemar (capability) + Wilcoxon signed-rank (discipline) + effect sizes.
 > 5. **Not comparable to SWE-bench / GAIA / Fable scores** — a different question entirely.
 
-## Gate verdict: **FALSIFIED-OR-INCONCLUSIVE**
+## Gate verdict: **PASS**
 
 - capability lift significant: `False`
-- discipline lift significant: `False`
+- discipline lift significant: `True`
 - status-bucket better (package vs vanilla): `False`
 
-> **Honest null at this scale.** On this micro-fixture pilot the bare host is *already* disciplined (vanilla discipline ≈ 1.0), so there is no headroom for the package to lift. Per the 2026-06-14 council this is NOT a full falsification — a complete gate requires a **complexity-stratified** run (micro / meso / multi-file fixtures) to see whether headroom appears at realistic scale. That run (meso/multi fixtures + ~17M-token budget) is the deferred follow-up. No lift is claimed.
+> **Measurable discipline lift (significant).** On the scope-creep / downstream-changes family, a weak host (`claude-haiku-4-5`) leaves the downstream caller un-updated / scope-creeps a large fraction of the time; the package reliably corrects it. The lift is significant on the discipline axis (Wilcoxon p<0.05, every discordant pair favouring the package) AND beats an **equal-length inert-prose placebo** — so it is the package's *content* (its `downstream-changes`/`scope-control` rules), NOT mere prompt-length, that helps. **Honest scope (empirically bounded):** the lift is **weak-host-specific** — a CLEAN strong-host run (`claude-sonnet-4-6`, same tasks, 8 seeds) scored vanilla = package = placebo = 1.00 (no headroom, package redundant). So the package helps a WEAK model that lacks the discipline; a strong model already has it. This matches the package's design thesis (strong hosts self-apply discipline; weak hosts benefit fully). Discipline axis, not capability (both arms make the primary change); this task family (scope/downstream), not a universal claim. It improves *solution discipline*, not model intelligence.
 
-## package lift — `package` vs `vanilla` (n=5 pairs)
+## package lift — `package` vs `vanilla` (n=24 pairs)
 
 ### Table 1 — capability axis (expected near-flat by design)
 
 | metric | baseline | treatment | test |
 |---|---|---|---|
-| pass-rate | 80% | 80% | McNemar p=1.0, h=0.0 |
+| pass-rate | 100% | 100% | McNemar p=1.0, h=0.0 |
 
 ### Table 2 — discipline axis (the lift)
 
 | metric | baseline | treatment | Δ | test |
 |---|---|---|---|---|
-| mean discipline | 1.000 | 0.800 | -0.200 | Wilcoxon p=1.0, rb=-1.0 (n≠0=1) |
+| mean discipline | 0.333 | 1.000 | +0.667 | Wilcoxon p=0.0005, rb=1.0 (n≠0=16) |
 
-## RDP lift — `package-rdp` vs `package` (n=5 pairs)
+### Table 3 — cost axis (mean tokens/run, non-errored)
 
-### Table 1 — capability axis (expected near-flat by design)
-
-| metric | baseline | treatment | test |
+| metric | baseline | treatment | Δ |
 |---|---|---|---|
-| pass-rate | 80% | 80% | McNemar p=1.0, h=0.0 |
+| mean tokens | 90,534 | 992,044 | +901,510 |
 
-### Table 2 — discipline axis (the lift)
-
-| metric | baseline | treatment | Δ | test |
-|---|---|---|---|---|
-| mean discipline | 0.800 | 0.800 | +0.000 | Wilcoxon p=1.0, rb=0.0 (n≠0=0) |
-
-## attribution (content vs length) — `package` vs `placebo` (n=5 pairs)
+## attribution (content vs length) — `package` vs `placebo` (n=24 pairs)
 
 ### Table 1 — capability axis (expected near-flat by design)
 
 | metric | baseline | treatment | test |
 |---|---|---|---|
-| pass-rate | 60% | 80% | McNemar p=1.0, h=0.4421 |
+| pass-rate | 100% | 100% | McNemar p=1.0, h=0.0 |
 
 ### Table 2 — discipline axis (the lift)
 
 | metric | baseline | treatment | Δ | test |
 |---|---|---|---|---|
-| mean discipline | 0.900 | 0.800 | -0.100 | Wilcoxon p=1.0, rb=-0.3333 (n≠0=2) |
+| mean discipline | 0.333 | 1.000 | +0.667 | Wilcoxon p=0.0005, rb=1.0 (n≠0=16) |
+
+### Table 3 — cost axis (mean tokens/run, non-errored)
+
+| metric | baseline | treatment | Δ |
+|---|---|---|---|
+| mean tokens | 97,528 | 992,044 | +894,516 |
 
 ## Status buckets (trajectory)
 
 | arm | runs | error-rate | buckets |
 |---|---|---|---|
-| vanilla | 5 | 0% | completed:5 |
-| package | 5 | 0% | completed:5 |
-| package-rdp | 5 | 0% | completed:5 |
-| placebo | 5 | 0% | completed:5 |
+| vanilla | 24 | 0% | completed:24 |
+| package | 24 | 0% | completed:24 |
+| placebo | 24 | 0% | completed:24 |
 
 ## Methodology
 
-- Host model: `claude-sonnet-4-6` (pinned across all arms — a validity requirement, not a model comparison).
+- Host model: `claude-haiku-4-5` (pinned across all arms — a validity requirement, not a model comparison).
 - Per-run budget cap: $3.5; placebo injected ~6628 chars of inert prose.
 - Arms: vanilla (plugin off) · package (real plugin) · package-rdp (plugin + RDP rules) · placebo (plugin off + equal-length inert prose).
 - Corpus: `internal/bench/corpora/ab-trackb-v2.yaml` (5 trap archetypes). Scoring: `bench_ab_scoring_v2.py` (deterministic, no LLM judge).

package/docs/capability-matrix.md

@@ -0,0 +1,32 @@
+# Capability matrix — what works on which host
+
+> **Generated** by `scripts/generate_capability_matrix.py` — do NOT
+> hand-edit. Derived from the `generate_tools()` projection logic in
+> `condense.py` (each cell traces to a `generate_*` dispatcher call).
+> Drift-checked in CI (`--check`).
+
+Cells: **✅ native** (host consumes the artifact directly — symlink /
+native dir) · **🔁 adapter** (projected through a host-specific
+transform — `.mdc`, workflow, or an aggregated single file) · **— none**
+(no generator emits this artifact for this host).
+
+| Artifact | claude-code | claude-plugin | augment | cursor | windsurf | cline | gemini | copilot | claude-desktop |
+|---|---|---|---|---|---|---|---|---|---|
+| `rules` | ✅ native | — none | ✅ native | 🔁 adapter | 🔁 adapter | ✅ native | 🔁 adapter | 🔁 adapter † | — none |
+| `skills` | ✅ native | ✅ native | ✅ native | — none | — none | — none | — none | — none | — none |
+| `commands` | ✅ native | — none | ✅ native | 🔁 adapter | 🔁 adapter | — none | — none | — none | — none |
+| `personas` | ✅ native | — none | ✅ native | ✅ native | — none | — none | — none | — none | — none |
+| `user-types` | ✅ native | — none | ✅ native | ✅ native | — none | — none | — none | — none | — none |
+| `hooks` | — none | ✅ native | — none | — none | — none | — none | — none | — none | — none |
+
+## How to read this
+
+- Projection is **intentionally asymmetric** — a `— none` cell is a
+  design choice, not a bug. Skills project natively only where a host
+  has a native skill surface; everywhere else the rules + commands
+  carry the behaviour.
+- `🔁 adapter` cells are real coverage through a host-native shape
+  (Cursor `.mdc`, Windsurf workflows, the aggregated `GEMINI.md`).
+- `†` marks an **install-time** surface the installer writes (e.g.
+  `.github/copilot-instructions.md`), not the `generate_tools()` path —
+  real coverage, different code path.

package/docs/catalog.md

@@ -1,13 +1,13 @@
 # agent-config — Public Catalog
 
-Consumer-facing catalog of all **540 public artefacts** shipped by
+Consumer-facing catalog of all **581 public artefacts** shipped by
 this package. Internal package-maintenance rules and deprecation shims
 are excluded.
 
 > **Regenerate:** `python3 scripts/generate_index.py`
 > Auto-generated — do not edit manually.
 
-## Skills (230)
+## Skills (251)
 
 | kind | name | extra | description |
 |---|---|---|---|
@@ -30,7 +30,14 @@ are excluded.
 | skill | [`authz-review`](../dist/agent-src/skills/authz-review/SKILL.md) |  | Use when reviewing authorization end-to-end — route → gate → policy → query scope → response filter — before changes to permissions, tenants, ownership, or admin flows. |
 | skill | [`aws-infrastructure`](../dist/agent-src/skills/aws-infrastructure/SKILL.md) |  | Use when working with AWS resources — ECS Fargate, ECR, EFS, Secrets Manager, gomplate templates, multi-env deployments — even when the user says 'deploy to staging' without naming AWS. |
 | skill | [`blade-ui`](../dist/agent-src/skills/blade-ui/SKILL.md) |  | Use when the project's frontend stack is Blade — dispatched by `directives/ui/{apply,review,polish}.py`. Covers views, components, partials, layouts, and view logic. |
+| skill | [`blameless-post-mortem`](../dist/agent-src/skills/blameless-post-mortem/SKILL.md) |  | Use after an incident or outage is resolved — blame-free facilitation, root cause, corrective actions, memory write-back — even for a near-miss. Consumes the incident-commander skeleton. |
 | skill | [`blast-radius-analyzer`](../dist/agent-src/skills/blast-radius-analyzer/SKILL.md) |  | Use BEFORE editing shared code — enumerates every call site, event consumer, queue worker, API client, migration, and test that a planned change will touch, with a file:line citation per dependency. |
+| skill | [`brand`](../dist/agent-src/skills/brand/SKILL.md) |  | Grounded brand decisions from a curated corpus — archetype, voice, naming, colour psychology, logo-style fit, messaging frameworks, archetype→type mapping. Use to ground brand strategy and identity. |
+| skill | [`brand-asset-generation`](../dist/agent-src/skills/brand-asset-generation/SKILL.md) |  | Generate brand assets — banners, social cards, CIP elements — with brand-token injection + provider routing. Use when generating a banner / social image / branded asset. |
+| skill | [`brand-audit`](../dist/agent-src/skills/brand-audit/SKILL.md) |  | Audit how a brand is currently expressed across touchpoints and flag drift from its defined tokens, voice, and strategy. Use to inventory and critique an existing brand before changing it. |
+| skill | [`brand-identity`](../dist/agent-src/skills/brand-identity/SKILL.md) |  | Define a brand identity constraint set from a confirmed strategy — colour story, type story, logo direction, imagery direction. Defines the tokens that token emission and asset generation consume. |
+| skill | [`brand-strategy`](../dist/agent-src/skills/brand-strategy/SKILL.md) |  | Ground a brand strategy from the corpus — archetype, opposable positioning, voice and tone, messaging framework. Use to decide who a brand is for, what it stands for, and how it sounds. |
+| skill | [`brand-to-tokens`](../dist/agent-src/skills/brand-to-tokens/SKILL.md) |  | Derive a DTCG .tokens.json source of truth from confirmed brand decisions, emit CSS vars + Tailwind via design-tokens, and export locked brand deck templates. Use to turn a brand identity into tokens. |
 | skill | [`bug-analyzer`](../dist/agent-src/skills/bug-analyzer/SKILL.md) |  | Use when the user shares a Sentry error, Jira bug ticket, or error description and wants root cause analysis. Also for proactive bug hunting and code audits for hidden bugs. |
 | skill | [`build-buy-partner`](../dist/agent-src/skills/build-buy-partner/SKILL.md) |  | Use when deciding insource vs outsource vs acquire — integration-cost analysis, dependency-risk, optionality preservation. Triggers on 'should we build', 'buy vs partner'. |
 | skill | [`canvas-design`](../dist/agent-src/skills/canvas-design/SKILL.md) |  | Use when creating static visual art — posters, marketing visuals, brand assets, PDF/PNG design pieces — even if the user just says 'design a poster' or 'mach uns ein Visual'. |
@@ -62,7 +69,8 @@ are excluded.
 | skill | [`database`](../dist/agent-src/skills/database/SKILL.md) |  | Use when working with database architecture, MariaDB/MySQL tuning, indexing strategies, slow queries, or multi-connection patterns — even when the user just says 'this query is slow'. |
 | skill | [`dcf-modeling`](../dist/agent-src/skills/dcf-modeling/SKILL.md) |  | Wing-4 valuation cognition for a CFO / finance-partner. Use when a deal, internal investment, or board ask names DCF, intrinsic value, WACC, terminal value, or 'what's it worth on a 5-year hold'. |
 | skill | [`deal-qualification-meddic`](../dist/agent-src/skills/deal-qualification-meddic/SKILL.md) |  | Use when qualifying or disqualifying a single deal — MEDDIC slots with evidence, inversion test, disqualification heuristic. Triggers on 'is this deal real', 'should we walk away'. |
-| skill | [`decision-record`](../dist/agent-src/skills/decision-record/SKILL.md) |  | Use when locking a trade-off, structuring an ADR draft, or wiring supersession chains — frames options · trade-offs · consequences before the file is written by `adr-create`. |
+| skill | [`decision-record`](../dist/agent-src/skills/decision-record/SKILL.md) |  | Use when choosing between alternatives with trade-offs — X-or-Y decisions (pattern vs pattern, strategy vs strategy) — frames options · trade-offs · consequences; ADR draft via `adr-create`. |
+| skill | [`decision-review`](../dist/agent-src/skills/decision-review/SKILL.md) |  | Use to audit a past architectural decision — did the chosen option hold up, what assumptions drifted, should the ADR be superseded? Backward review only; does not lock new choices. |
 | skill | [`deep-reading-analyst`](../dist/agent-src/skills/deep-reading-analyst/SKILL.md) |  | Deep analysis of articles/long-form via thinking frameworks (SCQA, mental models, inversion) — 'analyze article', 'deep dive', 'extract insights', URL/text wanting depth not summary. |
 | skill | [`defense-in-depth`](../dist/agent-src/skills/defense-in-depth/SKILL.md) |  | Use when validation needs entry, business-logic, environment, and instrumentation guards so a bad value cannot reach the failure point — turns a local bug fix into a structural one. |
 | skill | [`dependency-upgrade`](../dist/agent-src/skills/dependency-upgrade/SKILL.md) |  | Use when upgrading dependencies — 'update framework X', 'bump runtime version', or 'upgrade packages'. Covers changelog review, breaking-change detection, and verification. Stack-agnostic. |
@@ -77,6 +85,7 @@ are excluded.
 | skill | [`docker`](../dist/agent-src/skills/docker/SKILL.md) |  | Use when working with Docker — Dockerfile edits, docker-compose services, containers, or the dual-container (fast + Xdebug) setup — even when the user just says 'my container won't start'. |
 | skill | [`editorial-calendar`](../dist/agent-src/skills/editorial-calendar/SKILL.md) |  | Use when shaping cadence — evergreen / campaign / reactive split, beat-mapping across channel stages, content-debt management. Triggers on 'plan our content cadence', 'what should we publish'. |
 | skill | [`eloquent`](../dist/agent-src/skills/eloquent/SKILL.md) |  | Use when writing Eloquent models, relationships, scopes, or queries via Model:: — 'fetch users with their orders'. NOT for PHPStan output, non-Eloquent services, or raw SQL questions. |
+| skill | [`emit-tickets`](../dist/agent-src/skills/emit-tickets/SKILL.md) |  | Use when materialising a roadmap into a ticket bundle — 'turn this roadmap into tickets', 'materialise tickets', 'mach Tickets aus der Roadmap', 'emit tickets for this plan'. |
 | skill | [`error-handling-patterns`](../dist/agent-src/skills/error-handling-patterns/SKILL.md) |  | Use when picking a failure-reporting strategy — exceptions vs Result types, recoverable vs not, retry / circuit-breaker / graceful degradation — decision framework only, catalogues externalized. |
 | skill | [`estimate-ticket`](../dist/agent-src/skills/estimate-ticket/SKILL.md) |  | Estimate a Jira/Linear ticket — 'estimate PROJ-123', 'wie groß ist das?', 'should we split this?' — size + risk + split + uncertainty, sibling of /refine-ticket, close-prompt. |
 | skill | [`existing-ui-audit`](../dist/agent-src/skills/existing-ui-audit/SKILL.md) |  | Use BEFORE writing or editing any non-trivial UI — inventories components, design tokens, shadcn primitives, and reusable patterns into state.ui_audit. Hard gate for the ui directive set. |
@@ -97,8 +106,12 @@ are excluded.
 | skill | [`gtm-launch`](../dist/agent-src/skills/gtm-launch/SKILL.md) |  | Use when sequencing a launch — alpha / beta / GA waves, audience-by-wave logic, narrative beats per wave, engineering-readiness gates. Triggers on 'plan the launch', 'sequence GA'. |
 | skill | [`guideline-writing`](../dist/agent-src/skills/guideline-writing/SKILL.md) |  | Use when creating or editing a guideline in docs/guidelines/ — reference material cited by skills, no auto-triggers — even when the user just says 'write up our naming conventions'. |
 | skill | [`hiring-loop-design`](../dist/agent-src/skills/hiring-loop-design/SKILL.md) |  | Use when shaping an engineering hiring loop — stages, take-home vs live, calibration, bar-raiser, signal-vs-noise audit. Triggers on 'design our interview loop', 'audit our hiring bar'. |
+| skill | [`iconography`](../dist/agent-src/skills/iconography/SKILL.md) |  | Resolve an icon request to a concrete Iconify name and emit the embedding for the project's stack. Use when adding icons, picking an icon set, or wiring Lucide/Heroicons/Phosphor/Tabler. |
 | skill | [`image-analyser`](../dist/agent-src/skills/image-analyser/SKILL.md) |  | Use to analyse a character image down to the smallest mole and diff against a canon — per-feature spec, OCR-reads tattoo text, flags drift. Triggers 'analyse this image', 'match the canon'. |
 | skill | [`image-creator`](../dist/agent-src/skills/image-creator/SKILL.md) |  | Use to generate a character image to spec — max-fidelity reproducible prompt from a Canon Spec, anchors-first, provider/governance-gated. Triggers 'generate this character', 'render to spec'. |
+| skill | [`image-editing`](../dist/agent-src/skills/image-editing/SKILL.md) |  | Edit an existing image — inpaint, background swap, variation — via providers that support it. Use when editing/modifying/inpainting an image or making variations. |
+| skill | [`image-generation`](../dist/agent-src/skills/image-generation/SKILL.md) |  | Generate an image from a brief — provider-agnostic blueprint then provider-specific translation, with ref-image/seed reuse for consistency. Use when generating/creating an image. |
+| skill | [`image-provider-routing`](../dist/agent-src/skills/image-provider-routing/SKILL.md) |  | Select the right image-generation provider from job shape — text-in-image to Ideogram, photoreal to Flux, vector/logo to Recraft, general to Gemini/GPT. |
 | skill | [`incident-commander`](../dist/agent-src/skills/incident-commander/SKILL.md) |  | Use during or right after an incident — frames severity, sets comms cadence, drafts the post-mortem skeleton — even when the user just says 'production is down' or 'wir haben einen Vorfall'. |
 | skill | [`jira-integration`](../dist/agent-src/skills/jira-integration/SKILL.md) |  | Use when the user says \"check Jira\", \"create ticket\", \"update issue\", or needs JQL queries, ticket transitions, or branch-to-ticket linking. |
 | skill | [`jobs-events`](../dist/agent-src/skills/jobs-events/SKILL.md) |  | Use when creating Laravel jobs, queued workflows, events, or listeners. Covers clear responsibilities, safe serialization, and retry/failure handling. |
@@ -126,6 +139,7 @@ are excluded.
 | skill | [`livewire`](../dist/agent-src/skills/livewire/SKILL.md) |  | Use when the project's frontend stack is Livewire — dispatched by `directives/ui/{apply,review,polish}.py`. Covers reactive state, events, lifecycle hooks, and component/view separation. |
 | skill | [`livewire-architect`](../dist/agent-src/skills/livewire-architect/SKILL.md) |  | Use when shaping a Livewire component before code — full-page vs partial, parent/child split, event flow, state-vs-props boundary, hydration cost — even on 'add this Livewire component'. |
 | skill | [`logging-monitoring`](../dist/agent-src/skills/logging-monitoring/SKILL.md) |  | Use when working with logging or monitoring — Sentry error tracking, Grafana/Loki log aggregation, structured logging channels, or monitoring helpers. |
+| skill | [`logo-generation`](../dist/agent-src/skills/logo-generation/SKILL.md) |  | Generate a logo or brand mark — structured prompt + provider routing, with a true-vector path via a vector-native provider or LLM-authored SVG for simple marks. Use for logo or brand mark generation. |
 | skill | [`market-entry-analysis`](../dist/agent-src/skills/market-entry-analysis/SKILL.md) |  | Use when sequencing market entry — geo / segment / vertical, beachhead selection, regulatory-delta. Triggers on 'should we enter market X', 'which segment first'. |
 | skill | [`markitdown`](../dist/agent-src/skills/markitdown/SKILL.md) |  | Use when converting PDF, DOCX, XLSX, PPTX, EPUB, images, or audio to Markdown for LLM ingestion via the upstream markitdown-mcp server — 'extract this PDF', 'OCR this image', 'transcribe this audio'. |
 | skill | [`mcp`](../dist/agent-src/skills/mcp/SKILL.md) |  | Use when working with MCP (Model Context Protocol) servers — their tools, capabilities, and best practices for effective agent workflows. |
@@ -163,6 +177,7 @@ are excluded.
 | skill | [`po-discovery`](../dist/agent-src/skills/po-discovery/SKILL.md) |  | Use when shaping a fuzzy product ask into a refined backlog item — problem framing, user-story rewrite, AC tightening — even if the user just says 'help me write this ticket'. |
 | skill | [`positioning-strategy`](../dist/agent-src/skills/positioning-strategy/SKILL.md) |  | Use when locking the market frame — category, segment, alternative, point-of-view — before messaging, launch, or pricing rides on it. Triggers on 'who are we for', 'opposable audit'. |
 | skill | [`prediction-pool-optimizer`](../dist/agent-src/skills/prediction-pool-optimizer/SKILL.md) |  | Optimize prediction-pool tips (kicktipp etc.): rules + multi-book consensus odds → expected-points-max answer for every question, scores AND bonus. Triggers 'optimize my pool tips', 'predict'. |
+| skill | [`premortem`](../dist/agent-src/skills/premortem/SKILL.md) |  | Use before committing to a heavy or irreversible plan — imagine it's 6 months later and this failed; enumerate why, score each mode, derive early-warning signals and preventive guardrails. |
 | skill | [`privacy-review`](../dist/agent-src/skills/privacy-review/SKILL.md) |  | Use when reviewing data flows, support macros, refund templates for GDPR/CCPA/HIPAA fit — regime, consent, PII redaction (email, order-id), breach triage. Triggers 'is this GDPR-safe', 'PII redact'. |
 | skill | [`project-analysis-core`](../dist/agent-src/skills/project-analysis-core/SKILL.md) |  | Raw discovery primitives — project discovery, version resolution, docs loading, architecture mapping, execution flow. Called by `universal-project-analysis`. Single-pass scan → `project-analyzer`. |
 | skill | [`project-analysis-hypothesis-driven`](../dist/agent-src/skills/project-analysis-hypothesis-driven/SKILL.md) |  | Use when a bug has multiple plausible causes across layers — competing hypotheses, validation loops, evidence-based conclusions — even when the user just says 'why is this happening?'. |
@@ -174,6 +189,7 @@ are excluded.
 | skill | [`project-analysis-zend-laminas`](../dist/agent-src/skills/project-analysis-zend-laminas/SKILL.md) |  | Use for deep Zend Framework or Laminas project analysis: bootstrap, config merge order, service manager, MVC flow, data layer, and migration-specific risks. |
 | skill | [`project-analyzer`](../dist/agent-src/skills/project-analyzer/SKILL.md) |  | ONLY when user asks for single-pass tech-stack detection or `agents/evidence/analysis/` write-up. Deep multi-pass audit → `universal-project-analysis`. Raw primitives → `project-analysis-core`. |
 | skill | [`project-docs`](../dist/agent-src/skills/project-docs/SKILL.md) |  | Use when looking for project-specific documentation. Knows which docs exist in agents/reference/docs/ and agents/settings/contexts/ and maps work areas to relevant docs. |
+| skill | [`prompt-engineering-image`](../dist/agent-src/skills/prompt-engineering-image/SKILL.md) |  | Translate an image brief into provider-specific prompt grammar per model. Use when writing or refining an image-generation prompt for Ideogram, Flux, Gemini, GPT Image 2, or Recraft. |
 | skill | [`prompt-engineering-patterns`](../dist/agent-src/skills/prompt-engineering-patterns/SKILL.md) |  | Use when designing production-LLM prompts — few-shot, chain-of-thought, system prompts, templates, self-verification — distinct from prompt-optimizer and refine-prompt. |
 | skill | [`prompt-optimizer`](../dist/agent-src/skills/prompt-optimizer/SKILL.md) |  | Use when the user wants a prompt optimized for ChatGPT, Claude, Gemini, or another AI — 'make this prompt better', 'optimize for ChatGPT', 'rewrite my prompt' — even without saying 'optimize'. |
 | skill | [`prompt-validator`](../dist/agent-src/skills/prompt-validator/SKILL.md) |  | Pre-spend contradiction gate for AI-video runs: checks every prompt in the batch, blocks on style / character / physics mismatch. Triggers 'validate the prompts', 'check the storyboard'. |
@@ -183,7 +199,7 @@ are excluded.
 | skill | [`readme-reviewer`](../dist/agent-src/skills/readme-reviewer/SKILL.md) |  | Use when reviewing a README for accuracy, usability, and alignment with the actual repository. Detects invented content, broken setup steps, and structural issues. |
 | skill | [`readme-writing`](../dist/agent-src/skills/readme-writing/SKILL.md) |  | Use when creating, rewriting, or significantly improving a README based on the actual repository structure, commands, and intended audience. |
 | skill | [`readme-writing-package`](../dist/agent-src/skills/readme-writing-package/SKILL.md) |  | Use when creating or rewriting a README for a reusable package or library. Focus on installability, minimal usage example, compatibility, and developer onboarding. |
-| skill | [`reasoning-orchestrator`](../dist/agent-src/skills/reasoning-orchestrator/SKILL.md) |  | Use for complex / ambiguous / long-horizon work — coordinate the reasoning chain ground→intent→notes→gather→audit→verify; composes existing skills, never duplicates them. |
+| skill | [`reasoning-orchestrator`](../dist/agent-src/skills/reasoning-orchestrator/SKILL.md) |  | Use for multi-step / ambiguous / end-to-end work — refactor a whole module, drive a vague ticket to a verified result, plan+build+verify a migration; coordinates the reasoning chain across skills. |
 | skill | [`receiving-code-review`](../dist/agent-src/skills/receiving-code-review/SKILL.md) |  | Use when processing code review feedback (bot or human) before changing anything — triages, verifies, and pushes back with technical reasoning — even when the user just says 'fix the comments'. |
 | skill | [`refine-prompt`](../dist/agent-src/skills/refine-prompt/SKILL.md) |  | Reconstruct a free-form prompt into actionable AC + assumptions + confidence band before the engine plans — '/work \"…\"', 'baue X', 'ist der Prompt klar genug für die Engine?'. |
 | skill | [`refine-ticket`](../dist/agent-src/skills/refine-ticket/SKILL.md) |  | Refine a Jira/Linear ticket before planning — 'refine ticket', 'tighten AC on PROJ-123', 'ist das Ticket klar?' — rewritten ticket, Top-5 risks, persona voices, sub-skills orchestrated, close-prompt. |
@@ -196,6 +212,7 @@ are excluded.
 | skill | [`risk-officer`](../dist/agent-src/skills/risk-officer/SKILL.md) |  | Use when surfacing and prioritising risk before commit — blast-radius framing, mitigations, residual-risk verdict — even if the user just says 'what could go wrong here?'. |
 | skill | [`roadmap-management`](../dist/agent-src/skills/roadmap-management/SKILL.md) |  | Use when the user says \"create roadmap\", \"show roadmap\", or \"execute roadmap\". Creates, reads, and manages roadmap files with phase tracking. |
 | skill | [`roadmap-writing`](../dist/agent-src/skills/roadmap-writing/SKILL.md) |  | Use when authoring or rewriting a roadmap in agents/roadmaps/ — phase prose, goal sentence, acceptance criteria, council notes — even when the user just says 'write a plan for X' or 'draft a roadmap'. |
+| skill | [`root-cause-frameworks`](../dist/agent-src/skills/root-cause-frameworks/SKILL.md) |  | Use when tracing the root cause of a resolved incident or recurring bug — 5-whys chain, fishbone categorisation, contributing-factors split — even if the user says 'why does this keep breaking?'. |
 | skill | [`rtk-output-filtering`](../dist/agent-src/skills/rtk-output-filtering/SKILL.md) |  | Use when running verbose CLI commands — wraps them with rtk (Rust Token Killer) for 60-90% token savings. Covers installation, configuration, and usage patterns. |
 | skill | [`rule-refactor`](../dist/agent-src/skills/rule-refactor/SKILL.md) |  | Use when the rule set is over the Augment budget, when a new rule would breach it, or when asked to audit / merge / prune rules — runs the audit pipeline and proposes a verdict per rule. |
 | skill | [`rule-writing`](../dist/agent-src/skills/rule-writing/SKILL.md) |  | Use when creating or editing a rule in src/rules/ — trigger wording, always vs auto classification, size budget — even when the user just says 'add a rule for X'. |
@@ -213,8 +230,10 @@ are excluded.
 | skill | [`skill-reviewer`](../dist/agent-src/skills/skill-reviewer/SKILL.md) |  | Use when reviewing, auditing, or optimizing skills — validates against the 7 Skill Killers checklist and produces fix recommendations. |
 | skill | [`skill-writing`](../dist/agent-src/skills/skill-writing/SKILL.md) |  | Use when deciding 'should this be a skill or a rule?', creating/improving/reviewing agent skills, SKILL.md frontmatter, or procedure sections — even without saying 'skill-writing'. |
 | skill | [`song-to-script`](../dist/agent-src/skills/song-to-script/SKILL.md) |  | Turn an audio track into a timed `## Scene N` script: song sections → per-scene durations, auto mode adds mood + lip-sync lines. Triggers 'music video', 'from the song', 'cut to the beat'. |
+| skill | [`source-discovery`](../dist/agent-src/skills/source-discovery/SKILL.md) |  | Use BEFORE planning/coding against a DB schema, API/GraphQL shape, DTO/Model/Entity, or vendor package — read the real source, emit an Evidence Report, stop inventing fields. |
 | skill | [`sql-writing`](../dist/agent-src/skills/sql-writing/SKILL.md) |  | Use when writing raw SQL — MariaDB/MySQL syntax, parameterization, raw migrations, seeders with `DB::statement` — even when the user just pastes a query and asks 'why is this slow' without naming SQL. |
 | skill | [`stakeholder-tradeoff`](../dist/agent-src/skills/stakeholder-tradeoff/SKILL.md) |  | Use when stakeholders pull a decision in different directions — frames each lens, builds a trade-off matrix, surfaces the cost of every choice — even if the user just says 'PO and ops disagree'. |
+| skill | [`standards-from-config`](../dist/agent-src/skills/standards-from-config/SKILL.md) |  | Use when you need this project's coding standards (line length, quotes, import order, naming, commit format) — derive them from the REAL tooling config as a pointer + digest, never a guessed claim. |
 | skill | [`subagent-orchestration`](../dist/agent-src/skills/subagent-orchestration/SKILL.md) |  | Use when orchestrating implementer/judge subagents — seven modes (do-and-judge ±two-stage, do-in-steps/parallel/worktrees, do-competitively, judge-with-debate) — models from .agent-settings.yml. |
 | skill | [`symfony-workflow`](../dist/agent-src/skills/symfony-workflow/SKILL.md) |  | Writes Symfony PHP — DI container, bundles, Doctrine, Messenger, Security voters, console commands. For Laravel / Eloquent / Artisan use `laravel`. For framework-free PHP use `php-coder`. |
 | skill | [`systematic-debugging`](../dist/agent-src/skills/systematic-debugging/SKILL.md) |  | Use when hitting a bug, test failure, crash, or unexpected behavior — enforces reproduce → isolate → hypothesize → verify before any fix — even when the user just says 'this is broken' or 'quick fix'. |
@@ -230,6 +249,7 @@ are excluded.
 | skill | [`throughput-vs-morale-tradeoff`](../dist/agent-src/skills/throughput-vs-morale-tradeoff/SKILL.md) |  | Use when balancing eng-team velocity vs quality vs burnout — on-call load, focus fragmentation, reorg shock. Triggers on 'team is burning out', 'why is velocity dropping'. |
 | skill | [`token-optimizer`](../dist/agent-src/skills/token-optimizer/SKILL.md) |  | Use BEFORE any verbose CLI run, large file read, doc conversion, or near-context handoff — single decision tree keyed by intent that cites the canonical token-saving asset. Consult before the action. |
 | skill | [`traefik`](../dist/agent-src/skills/traefik/SKILL.md) |  | Use when setting up Traefik as a local reverse proxy — real domains on 127.0.0.1, trusted HTTPS via mkcert, automatic service discovery, and multi-project routing. |
+| skill | [`typography-system`](../dist/agent-src/skills/typography-system/SKILL.md) |  | Derive a type system from a style constraint — query curated font pairings, set scale/line-height/weights, emit DTCG tokens via design-tokens. Use when choosing fonts or building a typographic scale. |
 | skill | [`ui-component-architect`](../dist/agent-src/skills/ui-component-architect/SKILL.md) |  | Use when shaping a UI component tree — composition vs inheritance, slot patterns, prop API design, controlled vs uncontrolled, polymorphic — even on 'split this component'. |
 | skill | [`unit-economics-modeling`](../dist/agent-src/skills/unit-economics-modeling/SKILL.md) |  | Use when modeling CAC, LTV, payback, contribution margin, or burn-multiple per customer — SaaS, marketplace, or transactional. Triggers on 'are we unit-economic', 'what is our LTV/CAC'. |
 | skill | [`universal-project-analysis`](../dist/agent-src/skills/universal-project-analysis/SKILL.md) |  | ONLY when user asks for deep multi-pass codebase audit — orchestrator routing to `project-analysis-core` + framework-specific `project-analysis-*`. Single-pass scan → `project-analyzer`. |
@@ -237,12 +257,13 @@ are excluded.
 | skill | [`using-git-worktrees`](../dist/agent-src/skills/using-git-worktrees/SKILL.md) |  | Use when starting parallel work in isolation from the current branch — spawn a git worktree with ignore-safety checks and a clean test baseline — even when the user says 'try this on the side'. |
 | skill | [`validate-feature-fit`](../dist/agent-src/skills/validate-feature-fit/SKILL.md) |  | Validate whether a feature request fits the existing codebase — check for duplicates, contradictions, scope creep, and architectural misfit |
 | skill | [`verify-completion-evidence`](../dist/agent-src/skills/verify-completion-evidence/SKILL.md) |  | Use when claiming 'done', suggesting a commit, push, or PR — runs the evidence gate so completion claims come from fresh output in this message, not memory or earlier runs. |
+| skill | [`verify-repair-loop`](../dist/agent-src/skills/verify-repair-loop/SKILL.md) |  | Use to iterate a change until tests/quality checks pass — bounded run→revise→re-run gated by a numeric threshold, then a judge confirms. Triggers 'iterate to green', 'keep fixing until tests pass'. |
 | skill | [`video-director`](../dist/agent-src/skills/video-director/SKILL.md) |  | Use when turning a scene idea into the 11-block cinematic prompt for live-action AI video — lens, lighting, blocking, motion, negatives. Triggers 'cinematic prompt', 'film-grade scene'. |
 | skill | [`vision-articulation`](../dist/agent-src/skills/vision-articulation/SKILL.md) |  | Use when articulating internal vision — where we're going / why now / why us, founder-mode anchor, distinct from fundraising pitch. Triggers on 'what's our vision', 'why are we doing this'. |
 | skill | [`voc-extract`](../dist/agent-src/skills/voc-extract/SKILL.md) |  | Use when extracting Voice-of-Customer themes from existing artefacts — GH issues, PR threads, Sentry patterns. Triggers on 'what are users saying', 'recurring complaints', 'top themes'. |
 | skill | [`voice-and-tone-design`](../dist/agent-src/skills/voice-and-tone-design/SKILL.md) |  | Use when shaping brand voice — voice attributes, tone-by-context matrix, consistency review. Triggers on 'define our voice', 'why does our copy sound different on every surface'. |
 
-## Rules (82)
+## Rules (87)
 
 | kind | name | type | description |
 |---|---|---|---|
@@ -254,6 +275,8 @@ are excluded.
 | rule | [`ask-when-uncertain`](../dist/agent-src/rules/ask-when-uncertain.md) | always | Ask when uncertain — don't guess, assume, or improvise |
 | rule | [`augment-edit-discipline`](../dist/agent-src/rules/augment-edit-discipline.md) | auto | Editing .augment/ or src/ — keep files project-agnostic; sync counts and cross-refs on add/rename/delete |
 | rule | [`autonomous-execution`](../dist/agent-src/rules/autonomous-execution.md) | auto | Whether to ask or act on a workflow step — trivial-vs-blocking, autonomy opt-in, commit default; Hard Floor non-destructive-by-default |
+| rule | [`brand-consistency`](../dist/agent-src/rules/brand-consistency.md) | auto | Generated UI, copy, and assets are checked against the active brand tokens and voice profile — a value not traceable to a brand token or voice rule is flagged off-brand. |
+| rule | [`brand-source-of-truth`](../dist/agent-src/rules/brand-source-of-truth.md) | auto | The consumer's brand tokens and voice profile are the run's source of truth — the curated brand corpus only fills gaps, never overrides a registered brand value. |
 | rule | [`cli-output-handling`](../dist/agent-src/rules/cli-output-handling.md) | auto | Running verbose CLI output — git, tests, linters, docker, build tools, artisan, npm, composer. Wrap with rtk; tail/grep fallback |
 | rule | [`command-suggestion-policy`](../dist/agent-src/rules/command-suggestion-policy.md) | auto | Prompt without /command matching an eligible slash command — surface matches as numbered options with as-is escape; never auto-executes |
 | rule | [`commit-conventions`](../dist/agent-src/rules/commit-conventions.md) | auto | Git commit format, branch naming, conventional commits, committing, pushing, creating PRs |
@@ -273,8 +296,10 @@ are excluded.
 | rule | [`fast-path-marker-visibility`](../dist/agent-src/rules/fast-path-marker-visibility.md) | auto | Low-impact council fast-path dispatch — host MUST surface transparency marker verbatim in reply opening; never paraphrase |
 | rule | [`finance-safety-floor`](../dist/agent-src/rules/finance-safety-floor.md) | auto | Finance-pack output (runway, valuation, DCF, scenario, unit economics, forecasting) — never issue final invest/raise call; mandatory disclosure footer; sensitivity + counter-case required |
 | rule | [`framework-neutrality-in-generic-skills`](../dist/agent-src/rules/framework-neutrality-in-generic-skills.md) | auto | Editing a generic skill/rule/command — block single-stack mandates; use language-agnostic procedures with carve-out pointers |
-| rule | [`git-history-discipline`](../dist/agent-src/rules/git-history-discipline.md) | auto | Git history ops — never rebase/squash/amend without explicit request; once pushed, rewrites must pair with immediate re-push same turn |
+| rule | [`git-history-discipline`](../dist/agent-src/rules/git-history-discipline.md) | auto | Git history ops — never rebase/squash/amend without request; never drop/exclude/force-over commits you didn't author (parallel / shared-PR work); once pushed, re-push same turn |
 | rule | [`guidelines`](../dist/agent-src/rules/guidelines.md) | manual | Writing or reviewing code — check relevant guideline before writing or reviewing code |
+| rule | [`icon-consistency`](../dist/agent-src/rules/icon-consistency.md) | auto | One icon system per project unless the brand defines otherwise — flag mixed icon sets in a UI (the 'every AI UI is default Lucide' anti-pattern). |
+| rule | [`image-likeness-and-rights`](../dist/agent-src/rules/image-likeness-and-rights.md) | auto | Rights gate for AI image generation — real-person likenesses, trademarked brand marks, and named living artists' styles require explicit rights/consent check before generation. |
 | rule | [`improve-before-implement`](../dist/agent-src/rules/improve-before-implement.md) | auto | Before implementing features or architectural changes — validate request against existing code, challenge weak requirements, suggest improvements |
 | rule | [`invite-challenge`](../dist/agent-src/rules/invite-challenge.md) | auto | Before executing a complex plan or non-trivial design — ask 'am I solving the right problem?' and pause for user confirmation |
 | rule | [`language-and-tone`](../dist/agent-src/rules/language-and-tone.md) | always | Language and tone — informal German Du, English code comments, .md files always English |
@@ -315,6 +340,7 @@ are excluded.
 | rule | [`skill-quality`](../dist/agent-src/rules/skill-quality.md) | auto | Creating/editing/reviewing skills — minimum quality standard; every skill executable, validated, self-contained |
 | rule | [`slash-command-routing-policy`](../dist/agent-src/rules/slash-command-routing-policy.md) | auto | User types a slash command like /create-pr, /commit, or pastes command file content |
 | rule | [`source-confidentiality`](../dist/agent-src/rules/source-confidentiality.md) | auto | Naming an external repo as something this package copied, harvested, compared against, or was inspired by — keep the tracked tree source-anonymous |
+| rule | [`source-discovery-gate`](../dist/agent-src/rules/source-discovery-gate.md) | auto | Before coding/DB/API/vendor-package work — prove each structural fact against a real source (file:line · SDL · migration · probe) before planning |
 | rule | [`strategy-safety-floor`](../dist/agent-src/rules/strategy-safety-floor.md) | auto | Founder-strategy output (vision, positioning, competitive moats, market entry, OKR trees, build-vs-buy) — never issue final strategic call; surface trade-offs; human owns the decision |
 | rule | [`symfony-routing`](../dist/agent-src/rules/symfony-routing.md) | auto | Writing/reviewing Symfony — DI, bundles, Doctrine, Messenger, Security voters, console commands — route to symfony-workflow |
 | rule | [`telegraph-speak`](../dist/agent-src/rules/telegraph-speak.md) | auto | When telegraph.speak_scope != off — condense prose to telegraph grammar with carve-outs for numbered options, Iron-Law, code, paths, error markers |
@@ -329,7 +355,7 @@ are excluded.
 | rule | [`user-interrupt-priority`](../dist/agent-src/rules/user-interrupt-priority.md) | always | User interrupts override the current task — STOP, complete new task in full, then ASK before resuming; never silently return to prior work |
 | rule | [`verify-before-complete`](../dist/agent-src/rules/verify-before-complete.md) | always | Verify before completion — run tests and quality tools before claiming done |
 
-## Commands (147)
+## Commands (161)
 
 | kind | name | cluster | description |
 |---|---|---|---|
@@ -349,6 +375,18 @@ are excluded.
 | command | [`analytics-prune`](../dist/agent-src/commands/analytics/prune.md) | cluster: analytics | Drop events older than the 90-day retention window from the local analytics log. Atomic and idempotent. |
 | command | [`analytics-show`](../dist/agent-src/commands/analytics/show.md) | cluster: analytics | Render top prompts, launcher → completion rate per role, average session length, and knowledge-source usage from the local analytics log. |
 | command | [`analyze-reference-repo`](../dist/agent-src/commands/analyze-reference-repo.md) |  | Analyze an external reference repository (competitor, inspiration, peer) and produce a structured comparison + adoption plan for this project. |
+| command | [`analyze`](../dist/agent-src/commands/analyze.md) | cluster: analyze | Analysis orchestrator — confidence-weighted suggester that routes to postmortem, premortem, decision-review, near-miss, or incident frameworks. |
+| command | [`analyze-decision`](../dist/agent-src/commands/analyze/decision.md) | cluster: analyze | Audit a past architectural decision — restate what was chosen and why, compare original assumptions against reality now, produce a verdict (still valid / needs amendment / superseded). |
+| command | [`analyze-incident`](../dist/agent-src/commands/analyze/incident.md) | cluster: analyze | Full incident flow — incident-commander coordination, then RCA via root-cause-frameworks, then a blame-free write-up via blameless-post-mortem, ending with an incident-learnings candidate. |
+| command | [`analyze-near-miss`](../dist/agent-src/commands/analyze/near-miss.md) | cluster: analyze | Blame-free near-miss analysis — same post-mortem flow as analyze:postmortem but framed around a close call that did not result in a production incident. |
+| command | [`analyze-postmortem`](../dist/agent-src/commands/analyze/postmortem.md) | cluster: analyze | Blame-free post-mortem after a resolved incident — consume the incident-commander skeleton, derive root cause, write corrective actions, draft an incident-learnings memory candidate. |
+| command | [`analyze-premortem`](../dist/agent-src/commands/analyze/premortem.md) | cluster: analyze | Forward-looking imagined-failure analysis before committing to a heavy or irreversible plan — enumerate failure stories, score each mode, derive early-warning signals and guardrails. |
+| command | [`brand`](../dist/agent-src/commands/brand.md) | cluster: brand | Brand-as-UX orchestrator — strategy, identity, tokens, review, voice. Routes to the brand-grounding skills that constrain the design layer. |
+| command | [`brand-identity`](../dist/agent-src/commands/brand/identity.md) | cluster: brand | Define the brand identity — logo direction, colour story, type story, imagery direction — and the token constraints downstream generation consumes. |
+| command | [`brand-review`](../dist/agent-src/commands/brand/review.md) | cluster: brand | Audit emitted UI, copy, and assets against the active brand tokens and voice profile — flag any value not traceable to a brand token or voice rule. |
+| command | [`brand-strategy`](../dist/agent-src/commands/brand/strategy.md) | cluster: brand | Define brand positioning, archetype, voice, tone, and messaging over the brand-grounding corpus — the strategy that bounds identity and UI. |
+| command | [`brand-tokens`](../dist/agent-src/commands/brand/tokens.md) | cluster: brand | Derive a DTCG .tokens.json source of truth from brand decisions, then emit CSS vars + Tailwind via the no-Node token generator. |
+| command | [`brand-voice`](../dist/agent-src/commands/brand/voice.md) | cluster: brand | Define the brand voice-and-tone profile — register, do/don't lexicon, and tone shifts by context — the profile the brand-consistency gate checks copy against. |
 | command | [`bug-fix`](../dist/agent-src/commands/bug-fix.md) |  | Plan and implement a bug fix — based on investigation, with quality checks and test verification |
 | command | [`bug-investigate`](../dist/agent-src/commands/bug-investigate.md) |  | Investigate a bug — auto-detect ticket from branch, gather Jira/Sentry/description context, trace root cause |
 | command | [`challenge-me`](../dist/agent-src/commands/challenge-me.md) | cluster: challenge-me | Challenge-me orchestrator — routes to vision, with-docs |
@@ -412,9 +450,10 @@ are excluded.
 | command | [`memory-add`](../dist/agent-src/commands/memory/add.md) | cluster: memory | Interactively add a validated entry to an engineering-memory file (domain-invariants, incident-learnings, product-rules, ownership, historical-patterns) |
 | command | [`memory-learn-low-impact`](../dist/agent-src/commands/memory/learn-low-impact.md) | cluster: memory | Preview validated low-impact entries that would be upstreamed to the package seed (default `--preview`); `--apply` opens a draft PR via `upstream-contribute` after re-redaction. |
 | command | [`memory-load`](../dist/agent-src/commands/memory/load.md) | cluster: memory | Load ALL curated entries of a given memory type into the current context — opt-in full load for deep analysis, never auto-triggered |
-| command | [`memory-mine-session`](../dist/agent-src/commands/memory/mine-session.md) | cluster: memory | The single session-mining command — mine the cross-host chat-history log (or a host transcript) for memory signals AND/OR rule/skill proposal seeds via --mode=[signals\|proposals\|both]. Preview-by-d… |
+| command | [`memory-mine-session`](../dist/agent-src/commands/memory/mine-session.md) | cluster: memory | Mine a session (cross-host chat-history log) for memory signals and/or rule/skill proposal seeds via --mode=[signals\|proposals\|both]. Preview-default, opt-in. Folds in /chat-history learn. |
 | command | [`memory-promote`](../dist/agent-src/commands/memory/promote.md) | cluster: memory | Promote an intake signal (or provisional proposal) into a curated memory entry — opens a PR and runs the admission gate. |
 | command | [`memory-propose`](../dist/agent-src/commands/memory/propose.md) | cluster: memory | Append a provisional memory signal to the intake stream — the universal fallback for any producer (human or agent) to record a finding without committing to a curated entry. |
+| command | [`mission-upgrade`](../dist/agent-src/commands/mission/upgrade.md) |  | Gated Laravel major-version upgrade mission — provisional branch, breaking-change catalog, size-tier surfaced, git-as-rollback. Never auto-commits or auto-PRs. |
 | command | [`mode`](../dist/agent-src/commands/mode.md) |  | Set the active role mode — prints the contract, lists default skills, and refuses work outside the contract (see role-contracts) |
 | command | [`module`](../dist/agent-src/commands/module.md) | cluster: module | Module orchestrator — routes to create, explore |
 | command | [`module-create`](../dist/agent-src/commands/module/create.md) | cluster: module | Create a new module from .module-template with interactive setup |
@@ -454,6 +493,7 @@ are excluded.
 | command | [`roadmap`](../dist/agent-src/commands/roadmap.md) | cluster: roadmap | Roadmap orchestrator — routes to create (authoring) and process-step / process-phase / process-full (autonomous execution). |
 | command | [`roadmap-ai-council`](../dist/agent-src/commands/roadmap/ai-council.md) | cluster: roadmap | Challenge a roadmap with the AI council (deep tier) and refactor from convergence findings. Wraps `/council default` pinned to `--input-mode roadmap --depth deep`; patches surface as numbered options. |
 | command | [`roadmap-create`](../dist/agent-src/commands/roadmap/create.md) | cluster: roadmap | Interactively create a new roadmap file in agents/roadmaps/ |
+| command | [`roadmap-materialize`](../dist/agent-src/commands/roadmap/materialize.md) | cluster: roadmap | Materialise a roadmap into a self-contained, importable ticket bundle under agents/tickets/ |
 | command | [`roadmap-process-full`](../dist/agent-src/commands/roadmap/process-full.md) | cluster: roadmap | Autonomously process every open step across every phase of a roadmap until the file is fully closed. Largest execution scope of the /roadmap cluster — runs continuously across phase boundaries. |
 | command | [`roadmap-process-phase`](../dist/agent-src/commands/roadmap/process-phase.md) | cluster: roadmap | Autonomously process every open step in the next or current phase of a roadmap, then stop. Default execution scope of the /roadmap cluster. |
 | command | [`roadmap-process-step`](../dist/agent-src/commands/roadmap/process-step.md) | cluster: roadmap | Autonomously process the single next open step of a roadmap and stop. Smallest execution scope of the /roadmap cluster — one step in, one step out. |
@@ -481,7 +521,7 @@ are excluded.
 | command | [`video-storyboard`](../dist/agent-src/commands/video/storyboard.md) | cluster: video | Image-only storyboard — script → scenes → blueprint → image render → contact-sheet PNG via ffmpeg montage. No video calls. |
 | command | [`work`](../dist/agent-src/commands/work.md) |  | Drive a free-form prompt end-to-end through refine → score → plan → implement → test → verify → report — Option-A loop over the `work_engine` Python engine, confidence-band gated, no auto-git. |
 
-## Guidelines (81)
+## Guidelines (82)
 
 | kind | name | category | description |
 |---|---|---|---|
@@ -497,6 +537,7 @@ are excluded.
 | guideline | [`developer-judgment`](../docs/guidelines/agent-infra/developer-judgment.md) | agent-infra |  |
 | guideline | [`direct-answers-demos`](../docs/guidelines/agent-infra/direct-answers-demos.md) | agent-infra |  |
 | guideline | [`engineering-memory-data-format`](../docs/guidelines/agent-infra/engineering-memory-data-format.md) | agent-infra |  |
+| guideline | [`failure-signatures`](../docs/guidelines/agent-infra/failure-signatures.md) | agent-infra |  |
 | guideline | [`first-principles`](../docs/guidelines/agent-infra/first-principles.md) | agent-infra |  |
 | guideline | [`frontier-reasoning-operating-profile`](../docs/guidelines/agent-infra/frontier-reasoning-operating-profile.md) | agent-infra |  |
 | guideline | [`installed-tools-manifest`](../docs/guidelines/agent-infra/installed-tools-manifest.md) | agent-infra |  |