@event4u/agent-config 8.10.0 → 8.12.0

package/.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "description": "Bootstrap shim for the event4u agent-config suite. This plugin ships ONLY the dispatcher hooks plus one install-pointer skill — ALL content (skills, rules, commands) is installed via `npx -y @event4u/agent-config init`, which writes the file projection AND registers the same hooks in ~/.claude/settings.json. DEPRECATED as a content channel; kept so the marketplace listing stays discoverable and existing installs keep working hooks.",
-    "version": "8.10.0",
+    "version": "8.12.0",
     "keywords": [
       "agent-config",
       "skills",

package/AGENTS.md

@@ -18,6 +18,7 @@ task ci                # full pipeline — green before PR
 ## Pointers
 
 - **Self-orientation**: [`package-self-orientation`](docs/contracts/package-self-orientation.md).
+- **System map (maintainers)**: [`system-map`](docs/maintainers/system-map.md) — the one-page how-it-fits-together.
 - **Kernel + Router** — 9 Iron-Law rules, tier-1/2 routing: [`kernel-membership`](docs/contracts/kernel-membership.md) + [`rule-router`](docs/contracts/rule-router.md).
 - **Trust & Safety** — enum, HRR banner, floors: [`trust-and-safety`](docs/contracts/trust-and-safety.md) + [`ADR-018`](docs/decisions/ADR-018-trust-and-safety-layer.md).
 - **Content pipelines** (A→D): [`docs/architecture.md`](docs/architecture.md).

package/CHANGELOG.md

@@ -94,6 +94,23 @@ One question — answer in [Discussions](https://github.com/event4u-app/agent-co
 This gates the read-only MCP discovery helper (`agent-config mcp:search`) and the
 deferred auto-install question (`ADR-086`).
 
+### Added — humanizer (AI-tell removal for deliverable prose) (`road-to-humanized-writing` + `road-to-humanizer-hardening`)
+
+- **`humanizer` skill + `/humanize` command** (gtm-marketing pack) — remove
+  AI-writing tells from deliverable prose (posts, articles, drafts) via a
+  draft→audit→final loop; scoped to deliverable text only, never chat replies
+  or repo docs.
+- **`detect_ai_tells.ts` detector** — deterministic hard-tell / weighted-cluster
+  / em-dash-density scan (EN + DE), with a hidden-unicode ingestion scan and a
+  ReDoS length bound on untrusted input.
+- **Behavior change — write-engine step 4b is default-on.** Ghostwriter /
+  `post-as` drafts now pass a humanize audit before delivery; opt out per run
+  with `--raw`. The mechanical detector pass runs when a Node runtime is
+  present and degrades to a prose-only audit otherwise — the new
+  `humanizer-runtime` doctor check reports which path an install gets.
+- **Disclosure footer stays inviolable** through the audit; quoted/secondhand
+  text is never rewritten.
+
 ### Added — `agents/` directory contract + gitignore hygiene (`road-to-agents-dir-and-gitignore-hygiene`)
 
 - **`docs/contracts/agents-layout.md`** — authoritative contract for every top-level entry in `agents/` (purpose, git policy, retention, consumer-scope); includes the User Inbox Workflow (`agents/tmp/` → `agents/tmp.old/`).
@@ -991,171 +1008,72 @@ our recommendation order, not its support status.
 > keeps the active era under the 250-line drift cap enforced by
 > `tests/test_changelog_eras.py`.
 
-# Era: 8.9.x — current
-
-> Started at `8.9.0`. Full entries live inline below.
-> The drift test caps this era at 250 lines of entry body; growth past
-> that forces a new era split (`# Era: 8.10.x`, etc.) — see
-> [`docs/contracts/CHANGELOG-conventions.md § Era splits`](docs/contracts/CHANGELOG-conventions.md).
-
-## [8.10.0](https://github.com/event4u-app/agent-config/compare/8.9.0...8.10.0) (2026-07-10)
-
-### Features
-
-* **bus-factor:** dogfooded self-review gate (advisory, inert without secret) ([f5afbca](https://github.com/event4u-app/agent-config/commit/f5afbca154e5a62fff7c3f3a3409334457a05e84))
-* **domain-soundness:** author 4 rubric-target domain-truth fixtures (candidates) ([b391a0c](https://github.com/event4u-app/agent-config/commit/b391a0cf13051946ea9b024b68353e6c9a31c124))
-* **evals:** skill-eval-coverage — default-surface set (29 evals) + close + archive ([119328e](https://github.com/event4u-app/agent-config/commit/119328e62410573561c09e6a4076adeece167b3f))
-* **evals:** skill-eval-coverage — behavioural evals for the rich + router sets ([84f066e](https://github.com/event4u-app/agent-config/commit/84f066eb9131310dc0ce3526162565dd3f3cc7ac))
-* **quality:** frontier-quality-operating-system Phases 3–8 — close + archive ([e75d52d](https://github.com/event4u-app/agent-config/commit/e75d52d29787f8dcfcdc7a321df6221e3cb252ec))
-* **testing:** wire mandatory case discovery into TDD, /tests create, stack skills ([d2e9ec5](https://github.com/event4u-app/agent-config/commit/d2e9ec565419fa4166ff04e6b43039226fab8bde))
-* **skill:** add test-case-discovery — enumerate-before-write coverage funnel ([6dc2e76](https://github.com/event4u-app/agent-config/commit/6dc2e76dadc7188c8e64e49e04f7c1fd21d64288))
-* **quality:** frontier-quality-operating-system Phases 1+2 — mechanism matrix + eval-harness spine ([92ad083](https://github.com/event4u-app/agent-config/commit/92ad083a6ce7cd33bfdbc36f04b500b0f0594f56))
-* **work:** consumer-flow intake wiring + retrieval quality metrics ([1ca3b7d](https://github.com/event4u-app/agent-config/commit/1ca3b7d9535b5d49f5d61011a92366ca762cf763))
-* **worktree:** governed worktree layer — skill + /worktree:* thin cluster ([e662249](https://github.com/event4u-app/agent-config/commit/e6622494f5f5d8f00337bf93a3ac750defcc69e1))
-* **telemetry:** delegation quality pair — first_pass_success + escalated ([ded001f](https://github.com/event4u-app/agent-config/commit/ded001f22e4d4eb70a0f4318f47d2aa4323ede58))
-* **sizing:** release-sizing contract + CHANGELOG Rollback: gate ([e591098](https://github.com/event4u-app/agent-config/commit/e591098665eb10561e55b064a1f99e29f3c649e4))
-* **invariants:** kernel semantic-invariant gate (guards lost-merge-content class) ([59c58d5](https://github.com/event4u-app/agent-config/commit/59c58d5995a4127ebae82ea2fd48109ac508928f))
-* **surface:** surface-specific-agent-contracts Phases 2+3 — close + archive ([4899010](https://github.com/event4u-app/agent-config/commit/489901079c538a04f39d293f747fac9040e981f7))
-* **release-gate:** pack-based consumer matrix, release-adjacent dry-runs, red-workflow tripwire ([3742c9a](https://github.com/event4u-app/agent-config/commit/3742c9a8f290156f9696f51f51cf981f49ba97be))
-* **surface:** surface-specific-agent-contracts Phases 0/1/4/5/6/7 — backbone + fixtures ([9bff235](https://github.com/event4u-app/agent-config/commit/9bff2351b2e28703033084be0bf3541458731ea7))
-* **design:** design-artifact-fidelity Phases 5–7 + close + archive ([d92355a](https://github.com/event4u-app/agent-config/commit/d92355ac333d429803270219f1b8d1a4d24f6a85))
-* **design:** design-artifact-fidelity Phase 4 — variation & canvas planning ([b1ae817](https://github.com/event4u-app/agent-config/commit/b1ae817d3a76c9cc859f206a28278b29c9795778))
-* **design:** design-artifact-fidelity Phase 3 — surgical edit preservation ([065fd17](https://github.com/event4u-app/agent-config/commit/065fd1712f6256a662f0073f828491f8b0bc3433))
-* **design:** design-artifact-fidelity Phase 2 — resource-first context gate ([4a40217](https://github.com/event4u-app/agent-config/commit/4a40217e6f86b3d6a5b8f3e25cceeaeea10b550a))
-* **design:** design-artifact-fidelity Phase 1 — lifecycle contract ([1256d47](https://github.com/event4u-app/agent-config/commit/1256d47e94f5a3c874b726e6b24045aca6f74513))
-
-### Bug Fixes
-
-* **ci:** heal post-merge reds — portability literal, ranking regression, proof drift ([319a2f8](https://github.com/event4u-app/agent-config/commit/319a2f82e67fd2c498a113a627df9ae77871b327))
-* **skill:** playwright-testing — add run-verification note (clears skill_linter warnings) ([68db2b6](https://github.com/event4u-app/agent-config/commit/68db2b629a2689926fc6befdcdd944ea006e4652))
+# Era: pre-8.12.0 — archived
 
-### Chores
+> All entries before `8.12.0` live in
+> [`docs/archive/CHANGELOG-pre-8.12.0.md`](docs/archive/CHANGELOG-pre-8.12.0.md).
+> The archive is read-only; git tags remain the canonical
+> source for what shipped. Splitting them out of the main file
+> keeps the active era under the 250-line drift cap enforced by
+> `tests/test_changelog_eras.py`.
 
-* regenerate docs/proof.md — skill-count claim 269 → 270 ([0ec4c58](https://github.com/event4u-app/agent-config/commit/0ec4c5831941aa95b55613bb2c1ffe61c8724ab3))
-* **roadmap:** close + archive command-structure-optimization (deferred items → later/ follow-up) ([fa9a1b7](https://github.com/event4u-app/agent-config/commit/fa9a1b71e4623f4138123299b3fbbf5179d7eb68))
-* regenerate counts, pack manifests, condensation hashes ([1ba1a86](https://github.com/event4u-app/agent-config/commit/1ba1a863de5e52e139ca1283ef36f252672f7ba5))
-* fix command-count badges to 177 (counts-update missed hero badge + browse line) ([4d6551d](https://github.com/event4u-app/agent-config/commit/4d6551d14c80e936135125cdb98476b6fb575913))
-* sync counts, manifests, projections, dashboards; archive completed roadmap ([5178af3](https://github.com/event4u-app/agent-config/commit/5178af3bd66dffb1071607e03b0551a2c5e74d01))
+# Era: 8.12.x — current
 
-Tests: 7212 (+24 since 8.9.0)
+> Started at `8.12.0`. Full entries live inline below.
+> The drift test caps this era at 250 lines of entry body; growth past
+> that forces a new era split (`# Era: 8.13.x`, etc.) — see
+> [`docs/contracts/CHANGELOG-conventions.md § Era splits`](docs/contracts/CHANGELOG-conventions.md).
 
-## [8.9.0](https://github.com/event4u-app/agent-config/compare/8.8.0...8.9.0) (2026-07-10)
+## [8.12.0](https://github.com/event4u-app/agent-config/compare/8.11.0...8.12.0) (2026-07-12)
 
 ### Features
 
-* **rules:** simplicity-first bans, own-orphan cleanup, goal-driven execution ([3e4de80](https://github.com/event4u-app/agent-config/commit/3e4de80f9d1f7ece41162503fbcd6309620bf331))
-* **design:** design-artifact-fidelity Phase 0 — verification capability + eval baseline ([da9ff3a](https://github.com/event4u-app/agent-config/commit/da9ff3a41381e6ce0e749a74fd499de28b3ee7ea))
-* **kernel:** re-land direct-answers no-duration + never-cite-the-rule (#844 content lost from main) ([2c46e7f](https://github.com/event4u-app/agent-config/commit/2c46e7f3b194ad2179b92307939d588cdb3971f3))
-* **lint:** fail skills that claim a Claude Code built-in name ([4c0cd39](https://github.com/event4u-app/agent-config/commit/4c0cd39b9a0bf604e436bbc80327b0bddf26b9e3))
-* **install:** withhold Claude Code built-in names from /name projections ([6dcba71](https://github.com/event4u-app/agent-config/commit/6dcba71bc2e5660a00c3dd7106ece65754c71633))
-* **kernel:** re-land action-authority sharpening (#840 content lost from main) ([13f244c](https://github.com/event4u-app/agent-config/commit/13f244c9bcb5d92641e5c87e3964c5d4212c8b46))
-* **domain-soundness:** deterministic domain-truth fixtures + scorer + candidate run ([dfb27a2](https://github.com/event4u-app/agent-config/commit/dfb27a2e8f1871f436bac19446d76c569f33e3c6))
-* **execution:** amend-trap, tool-tier ladder, disconfirmation search, anti-over-engineering, authoring guidelines (P2-P6) ([2e7d4d2](https://github.com/event4u-app/agent-config/commit/2e7d4d2a6210672289a50441295f84e21f4f442a))
-* **design:** same-ramp contrast, componentization threshold, async-verifier, handoff template (P3/P4/P5) ([be49527](https://github.com/event4u-app/agent-config/commit/be49527050f235d9396c14f2fe077c3c38209798))
-* **design:** diagram-type routing + geometric pre-checks + embedded register (P1/P2/P4) ([32947b8](https://github.com/event4u-app/agent-config/commit/32947b8a63abc464edeec399929b3f5605b19ddb))
-* **handoff:** verbatim-first lossless template in agent-handoff (P4) ([76a5455](https://github.com/event4u-app/agent-config/commit/76a54557fb5c366b31b72e67d726a105de9e7a74))
-* **memory:** save-successes + reference-shape + verify-then-repair + derivability (P2/P3) ([d4c6e81](https://github.com/event4u-app/agent-config/commit/d4c6e810df365c8990ef9cf75f0289f970eb4a9a))
-* **orchestration:** worker-prompt contract in subagent-orchestration (P1) ([ba65867](https://github.com/event4u-app/agent-config/commit/ba65867f28273b97c16e7799a7c68d00bc16fccd))
-* **memory:** hostile-input write-guards at persist-time (P3) ([e08287b](https://github.com/event4u-app/agent-config/commit/e08287b663a56b4f6e85d0295f6229ca59cb77da))
-* **security:** found-instructions quarantine + injection-signal taxonomy (P1/P2) ([446909a](https://github.com/event4u-app/agent-config/commit/446909a007c2f7dbffee14adf32fc6cdcef9504e))
-* **lint:** cover human-gate phase headings and exit criteria; sharpen step patterns ([68c8738](https://github.com/event4u-app/agent-config/commit/68c8738d1ee10d5b433de02eaaaf3bf3f836b826))
-* **lint:** warn on human-gate checkbox steps in roadmap complexity lint ([64c5f6c](https://github.com/event4u-app/agent-config/commit/64c5f6cbbe5be69eaf4d84c523b6b6935a351ed9))
-* **knowledge:** document slicer (B8) + external code-graph interop rule (B9) ([c09bcb9](https://github.com/event4u-app/agent-config/commit/c09bcb994577f2ed87a19b7e11b617708bf60561))
-* **memory:** seed the curated corpus from the maintainer memory index ([2422f51](https://github.com/event4u-app/agent-config/commit/2422f51e4f07d5ab2b55ab5c9bf74b5950513957))
-* **bench:** self-measuring benchmark command + Cohen's Kappa judge (B7) ([58b9687](https://github.com/event4u-app/agent-config/commit/58b96878931ef976dce92dc333a966021d3b8e08))
-* **discovery:** stat-index primitive + lazy graph rebuild skip (B5a) ([04c34c6](https://github.com/event4u-app/agent-config/commit/04c34c65bc0b08331a9d8d2a1a9fae7ee20102c6))
-* **discovery:** artefact relation-graph + `affected`/`explain` verbs (B4) ([d9ffe0b](https://github.com/event4u-app/agent-config/commit/d9ffe0bff5f8326f4e077c9b27b7f604180d8242))
-* **memory:** merge learning-sidecar verdicts into retrieve() output (B3) ([46ddf98](https://github.com/event4u-app/agent-config/commit/46ddf98e915db50e6c4b75ef5dcf5ebc13b7c721))
-* **memory:** learning-sidecar aggregator — decay + corroboration + dead-ends (B3) ([11fc4a2](https://github.com/event4u-app/agent-config/commit/11fc4a28bf5e724eb09bf5eb07e66076ebfbc689))
-* **memory:** activate the lexical index in retrieve() above the tripwire (B2) ([6d6dbe8](https://github.com/event4u-app/agent-config/commit/6d6dbe8ae8153868c33fe6f867b953ceae375158))
-* **memory:** measure lexical ranking lift — the B2 ship-gate (proven) ([9f4feb9](https://github.com/event4u-app/agent-config/commit/9f4feb923a30f0462362ef1ae25cd3d482225247))
-* **memory:** add hand-rolled BM25 + trigram lexical index (B2) ([971c86e](https://github.com/event4u-app/agent-config/commit/971c86e982a7afc2ab28424195a7783f7ce1f1e9))
-* **lint:** add versioned-cache gate (B5b) ([5bfe14a](https://github.com/event4u-app/agent-config/commit/5bfe14a78e07b9eac130ee3b8e835080752d1424))
-* **memory:** add token_budget compact read surface to retrieve_v1 ([44b8c4c](https://github.com/event4u-app/agent-config/commit/44b8c4c8d6c4e014c5a1d91219fce57dfe60bfde))
-* **security:** sanitize floor on retrieval read-surfaces (B6) ([07802d6](https://github.com/event4u-app/agent-config/commit/07802d69a8ab501435b965a5a6aa9bf86d2004f7))
-* **orchestration:** modeled cost-% for the downshift rate win ([6a4ec50](https://github.com/event4u-app/agent-config/commit/6a4ec50350cf980fe17ba888957c37c615cc68ce))
-* **hooks:** pre-push changed-TypeScript static pass (typecheck + lint) ([640b789](https://github.com/event4u-app/agent-config/commit/640b789c76a2ac1637fa50fe3917557b7789f2a5))
-* **orchestration:** recorder that emits validated telemetry per dispatch ([12aa7b1](https://github.com/event4u-app/agent-config/commit/12aa7b131c7852734df85f920f079f5f1e01357b))
-* **second-brain:** retrieval-precision harness + store + pinned report ([350e9b7](https://github.com/event4u-app/agent-config/commit/350e9b7a3534cd3030272113a06818b3e384a278))
-* **security:** harden agentic-security rules + skills (Fable5 follow-ups) ([e6fdb23](https://github.com/event4u-app/agent-config/commit/e6fdb23bd919789374a3001a7c6d89170426907a))
-* **second-brain:** paired-run harness + pinned PASS report (Phase 2) ([85c9898](https://github.com/event4u-app/agent-config/commit/85c9898bcef8dfb2439096e38531b5d904233eb8))
+* **rules:** P4 migration Batch A — 9 rule bodies to their existing homes (−51.7% stub bytes) ([94dc19c](https://github.com/event4u-app/agent-config/commit/94dc19cac62ff21449afd5a373c1363ee3d6215c))
+* **explain-run:** plain-language Summary section ([257d8fc](https://github.com/event4u-app/agent-config/commit/257d8fc4d2ef69e9696f9a143d653a1a0a771e2c))
+* **complexity:** report v2 — proxy honesty, coupling metric, soft-ratchet baseline ([8328bae](https://github.com/event4u-app/agent-config/commit/8328bae0b791da4215fd704a90734123df0f6b13))
+* **bench:** live retrieval benchmark executed — decisive PASS ([25d9f03](https://github.com/event4u-app/agent-config/commit/25d9f03756e33870fbc507bc1bc964c5b6c83403))
+* **bench:** persona-placebo benchmark — executed, HONEST NULL (identity adds nothing) ([000c3e7](https://github.com/event4u-app/agent-config/commit/000c3e77081d7aa39e3d617f98ba67ef27121218))
+* **reports:** complexity report, explain-run v0, rule-backlinks — all report-only with kill criteria ([e718f13](https://github.com/event4u-app/agent-config/commit/e718f1396562e0cb94fab344b75332a73a34ac35))
+* **knowledge:** per-card sensitivity classes, promotion gate, revocation trail (ADR-121) ([a14b1ad](https://github.com/event4u-app/agent-config/commit/a14b1ad54b750d86ff288cd96ad9e76fe58fcdc5))
+* **consumer-matrix:** live hook-lifecycle leg + dist import-graph completeness ([1f1d9e1](https://github.com/event4u-app/agent-config/commit/1f1d9e1f8f8186de51071f47ca20ed649fad01f3))
+* **bench:** length-neutral judge rerun — executed, SECOND INCONCLUSIVE (gate closed-by-diagnosis) ([66ba0a3](https://github.com/event4u-app/agent-config/commit/66ba0a3e7a995fb8f7db1b795d33682328dc8596))
+* **council:** restate pass — the last wiring item (pre-round-1, transport-safe) ([4df6069](https://github.com/event4u-app/agent-config/commit/4df6069e127a0467f5a86aea57ea4c90929746a1))
+* **council:** stance-line repair call in consult (bounded, transport-gated) ([91fd10e](https://github.com/event4u-app/agent-config/commit/91fd10e25429d7d35f460ba8560c76565007b0c6))
+* **council:** debate-gate repair dispatch in run_debate (bounded, policy-gated) ([e7f6380](https://github.com/event4u-app/agent-config/commit/e7f6380639835d61c72b4b89cb79d77a5c90cb9c))
 
 ### Bug Fixes
 
-* **roadmap:** accept dotted sub-phase ids in PHASE_RE ([aaa54c3](https://github.com/event4u-app/agent-config/commit/aaa54c3ab7060b3e300bac99788325848400f954))
-* **skills:** mcp and code-review opt out of slash registration ([67d261a](https://github.com/event4u-app/agent-config/commit/67d261af0c06147ca3e771b3b6d57ceec34ede63))
-* **roadmap:** live-verify PR merge state before any in-flight/merged claim ([54ae7b0](https://github.com/event4u-app/agent-config/commit/54ae7b063a0bd641a931db423264ed0b8a4452f7))
-* **cli:** rename graph verb explain→graph-explain (collides with decision-chain explain); register verbs; recompile router ([8489858](https://github.com/event4u-app/agent-config/commit/84898580de0df92ec9f2f748d26c9a455c8c2468))
-* **rules:** assign new rules to the `meta` pack, not `core` (strict discovery) ([2a4d118](https://github.com/event4u-app/agent-config/commit/2a4d118fbacaf167d5a005803ef90e9524a7c7b5))
-* **roadmap:** harden /roadmap:process-full as law + add question-not-instruction rule ([b1eee65](https://github.com/event4u-app/agent-config/commit/b1eee65f0ff386b6461b72a39cae577b6582559f))
-* **memory:** align check_memory KNOWN_TYPES with the five write-side types ([1905648](https://github.com/event4u-app/agent-config/commit/1905648dabdfb0680ea1cf610bf43e8f07abda32))
-* **memory:** concrete summary type for measure_lexical_ranking (typecheck) ([475e7be](https://github.com/event4u-app/agent-config/commit/475e7be9af36b6fd7beff717502687f7a84a3e58))
-* **memory:** drop unused import + regenerate proof.md (CI) ([e415eb6](https://github.com/event4u-app/agent-config/commit/e415eb6184b697f1bb667872d6f1b8d08dea1ce6))
-* **second-brain:** restore proof § 3 heading + noUncheckedIndexedAccess guards ([b684a6c](https://github.com/event4u-app/agent-config/commit/b684a6cd1774dfd47d720d5be4cbe32ca854e213))
-* **verify:** require a changed-files static pass before pushing source ([ba3a9b5](https://github.com/event4u-app/agent-config/commit/ba3a9b5f467c5e4621637297366a4e58f84059b2))
-* **security:** post-review nits — through-line pack + FE-render greps + lint desc ([712a338](https://github.com/event4u-app/agent-config/commit/712a3389463453d01df19c421a310ed991a1fc9f))
-* **ci:** pin publish-npm to npm 11 for Node 20 compat ([4c0ed33](https://github.com/event4u-app/agent-config/commit/4c0ed33af0229b53e423a863d9e6946a49d08868))
+* **ci:** roadmap-ci-steps-mechanics joins the task-invocation skip class ([659d775](https://github.com/event4u-app/agent-config/commit/659d775099bd67168beac8a5742a4efbe773b690))
+* **ci:** skill description under the 200-char linter cap + modernize a migrated legacy path ([893ce69](https://github.com/event4u-app/agent-config/commit/893ce6922df759ac2432b221e28951a292233a47))
+* **proof:** move the honest-null entry into the build_proof generator ([5c1a12c](https://github.com/event4u-app/agent-config/commit/5c1a12c152d35fd320e40f0173b27f842fb39903))
+* **ci:** regenerate proof.md post-merge + de-literalize example imports ([6ff330d](https://github.com/event4u-app/agent-config/commit/6ff330d5a84c4682fae63eb2331ec3f645473cb4))
+* **claims:** thin-projection honesty + pre-register the council-vs-solo baseline ([6aee669](https://github.com/event4u-app/agent-config/commit/6aee669e311261121f582793e47698e029b0c8ae))
+* **identity:** resolve the placeholder git identity and guard against recurrence ([b17a801](https://github.com/event4u-app/agent-config/commit/b17a801dd16ddda9c3bcfd6b269dc65aff5a5e41))
+* **counts:** regenerate CAPABILITIES.yaml and close the structured-surface drift gap ([55aafb5](https://github.com/event4u-app/agent-config/commit/55aafb58b7f0e775b73a100d0b83f55b13defea0))
 
 ### Documentation
 
-* **contracts:** document the reserved host-name floor ([7ef51e9](https://github.com/event4u-app/agent-config/commit/7ef51e99d913f1d0e3ce48dd8caefc8804612ea5))
-* **roadmap:** flip execution-discipline non-kernel phases; counts + dashboard + hashes ([9da5da5](https://github.com/event4u-app/agent-config/commit/9da5da576c08f0eae3d7577079cd4f913a7f69ca))
-* **design:** reference-over-vendor pointer + close design-mechanism harvest (P6) ([e41f45c](https://github.com/event4u-app/agent-config/commit/e41f45cdc1297a6fa4293836b5a7a5cbf43a1c00))
-* **roadmap:** record drift-audit disposition (P5); flip + archive orchestration-memory harvest ([a6caca8](https://github.com/event4u-app/agent-config/commit/a6caca8cd5857be9a188ec5c704835e11921c16e))
-* **roadmap:** blocker sweep per template rule 22 — resolve 7 non-gates, unblock ci-native Phase 1 ([fabbbc3](https://github.com/event4u-app/agent-config/commit/fabbbc320dd65be51dc552ff12bde628ee7402a6))
-* **roadmap:** flip injection-authority Phases 1-3,5; sync hashes + dashboard ([0ca2310](https://github.com/event4u-app/agent-config/commit/0ca2310b0007c15f66ed4f95e5e1260b9b6b83be))
-* **contracts:** draft injected-block authenticity model (P5, proposal only) ([0738dad](https://github.com/event4u-app/agent-config/commit/0738dad234ef545c40d0294fdc47b2b116f2c7aa))
-* **roadmap:** separate external blockers from human gates; risk-based autonomous recommendation ([dc049e1](https://github.com/event4u-app/agent-config/commit/dc049e1fe68612367c576db9fae693abf04b1cc5))
-* **roadmap:** autonomy-first authoring — human gates are the exception ([c007ac7](https://github.com/event4u-app/agent-config/commit/c007ac7db79184805d2815ff21da0c4ba7858402))
-* **memory:** name the separator-recall limit in the retrieval scope + ADR-116 ([0c8a6f8](https://github.com/event4u-app/agent-config/commit/0c8a6f8a065347e8a6a4df8b08b319ce23a6f5b5))
-* sync counts (+2 rules), CLAIMS/proof, archive completed roadmap ([101c801](https://github.com/event4u-app/agent-config/commit/101c8015532f258671af28934048bb4049e16ed4))
-* **roadmap:** mark B3 display-merge done — Phase 3 complete ([3fa451a](https://github.com/event4u-app/agent-config/commit/3fa451aff07a9d1309e594614cef5cd1868b6e15))
-* **roadmap:** mark B3 aggregator done (Phase 3 checkbox 1) ([43ba766](https://github.com/event4u-app/agent-config/commit/43ba76606659310d529cbb73b1ad1e1539f6e2fb))
-* **roadmap:** mark B2 activation done — Phase 2 complete ([89f6ae4](https://github.com/event4u-app/agent-config/commit/89f6ae448123e8a633e4e9f990ca0bae442f045c))
-* **memory:** record ADR-061 <-> FTS5 resolution for retrieval ranking (B2) ([0e54680](https://github.com/event4u-app/agent-config/commit/0e546807489e9e8c0c68e8db45fe661a8e3b1790))
-* **roadmap:** resolve retrieval-substrate design council pass; promote to ready ([9194898](https://github.com/event4u-app/agent-config/commit/9194898cfa0b80f2c1bd5f4b3783eaec7337c037))
-* **roadmap:** draft retrieval-substrate hardening (source-anonymous borrow) ([708ac89](https://github.com/event4u-app/agent-config/commit/708ac89d930301fbf9880e59908552d2e8b1d175))
-* **orchestration:** document dispatch_tokens + session_tier telemetry fields ([f59562a](https://github.com/event4u-app/agent-config/commit/f59562a598c610a42a16fd1ced4dfa769eab2f15))
-* **token-saving:** run the live thin-vs-eager judge — honest INCONCLUSIVE ([3ad161b](https://github.com/event4u-app/agent-config/commit/3ad161b104c1a037b22774738e9545f4b65cc0ca))
-* **claims:** repoint hidden-instruction claim to the release gate ([a41815d](https://github.com/event4u-app/agent-config/commit/a41815db830ba90e5daaa512f6b55b6ee8be4f81))
-* **orchestration:** wire the recorder into the emit procedure + delegation-policy ([69042ad](https://github.com/event4u-app/agent-config/commit/69042ad1568bd9e16a520e63c91744cd385567a1))
-* **proof:** regenerate proof page for the new hidden-instruction claim ([45f5a7a](https://github.com/event4u-app/agent-config/commit/45f5a7a106c4c5c5b3b003ed3c3fd8e6be4f8425))
-* **claims:** bind the hidden-instruction CI scan to the claims ledger ([55fe74e](https://github.com/event4u-app/agent-config/commit/55fe74ed2122959d465b9fcc4f2fc6daffd30445))
-* **second-brain:** publish the retrieval-precision result across the surfaces ([3ee930a](https://github.com/event4u-app/agent-config/commit/3ee930a4bc61e3f1c01c7a02b204099f96042e2a))
-* **frontier-quality:** Phase 0 metrics + provenance + contract + pilot proposal ([0e738fb](https://github.com/event4u-app/agent-config/commit/0e738fb32a4645f499055940e386295b265fdc8d))
-* **second-brain:** publish the measured recall lift + decline the export ([8fbaeaf](https://github.com/event4u-app/agent-config/commit/8fbaeaf0fa8a361d9b469dad4d8046d677b4c9a7))
-
-### Refactoring
-
-* **skill:** extract topology hints from subagent-orchestration to context ([4918ef2](https://github.com/event4u-app/agent-config/commit/4918ef2372d7cb2c6e24a71ba9e3307946426899))
-
-### Tests
-
-* **memory:** land the Phase 0-pre substrate-validation foundations ([474df9a](https://github.com/event4u-app/agent-config/commit/474df9af95f8edd2ba10d6ba7ff88465a534d12d))
-
-### CI
-
-* **security:** fail-closed agent-security gate on the publish path ([f8934f7](https://github.com/event4u-app/agent-config/commit/f8934f739a4f27a11e3c0bd8df7c9943ddba519f))
-* **second-brain:** wire the retrieval-precision dry-run into ci + ci-strict ([da4ec36](https://github.com/event4u-app/agent-config/commit/da4ec36e7c84765203864cb9f8e99e62aaf85e53))
-* **security:** wire lint-agent-security into CI and scan dist/agent-src ([453095f](https://github.com/event4u-app/agent-config/commit/453095f28bcf9aaa9c9419872dc732571d9971e3))
-* **consistency:** trigger required check on any workflow change ([e629624](https://github.com/event4u-app/agent-config/commit/e629624644e33fa1926c763f8b1a05c730c0fcdc))
+* **posture:** knowledge scaling reality + local_auto_run as deliberate design ([ad9f43b](https://github.com/event4u-app/agent-config/commit/ad9f43baaa52cea533f6e1fd91ca012d95d35e9e))
+* **maintainers:** one-page system map + prepared branch protection ([efe63d0](https://github.com/event4u-app/agent-config/commit/efe63d006ff7ef97b1f4e201c29e53824ef3af95))
+* **claims:** pre-register the utilization-window decision criteria ([4667adf](https://github.com/event4u-app/agent-config/commit/4667adf085af9d2e178932b0a3fc9e2d674d6d2c))
+* **roadmap:** complete + archive road-to-opt-retrieval-and-memory ([cfc8657](https://github.com/event4u-app/agent-config/commit/cfc86578b7033945d227db80d98821aef33b8917))
+* **roadmap:** complete + archive road-to-opt-council-deliberation ([8777a8e](https://github.com/event4u-app/agent-config/commit/8777a8ebf90c2fc32362cfcbe1e58f8bee8f56d7))
+* **proof:** persona-identity-placebo-null — backed claim + honest-null story ([0d0de13](https://github.com/event4u-app/agent-config/commit/0d0de1387b6cd61a0165ec26a1db695172dcc2bd))
+* **rules:** rule-body migration inventory + P4 batches into request-scoped-rule-load ([c5abc40](https://github.com/event4u-app/agent-config/commit/c5abc40e4edc09d92681afbeae5f837f63784e29))
+* **bench:** record the closed-by-diagnosis disposition ([e02f7d7](https://github.com/event4u-app/agent-config/commit/e02f7d765d1aa2d61ae7bd1e879b27a1711fe595))
+* **roadmap:** flip the restate step + the confirmed harness prerequisite ([6415b3e](https://github.com/event4u-app/agent-config/commit/6415b3e672a659e8453159ca7e421d2ce7fdb9da))
+* **roadmap:** flip the stance-repair + chairman-ADR steps ([c1278a0](https://github.com/event4u-app/agent-config/commit/c1278a092027bb1659ba37d3281b9692a2c4066e))
+* **adr:** ADR-120 — council chairman mode supersedes always-host synthesis ([9e593f4](https://github.com/event4u-app/agent-config/commit/9e593f42bcd5ff844332eb7eca4fbb545be7d8fd))
+* **roadmap:** flip the debate-gate repair-dispatch step ([d4bba6b](https://github.com/event4u-app/agent-config/commit/d4bba6b31c1ceca01480f66ea80174a27887ab88))
 
 ### Chores
 
-* **roadmap:** add + close road-to-simplicity-and-goal-discipline ([026bf11](https://github.com/event4u-app/agent-config/commit/026bf1159e9af14cee1f76ccfa240d7f7b7076f4))
-* **roadmap:** close + archive execution-discipline-harvest (kernel content landed) ([49134d4](https://github.com/event4u-app/agent-config/commit/49134d4cb4178a7baa1cad8dbd38265b9c0d457f))
-* **roadmap:** close + archive injection-and-authority-harvest (kernel content landed) ([810df58](https://github.com/event4u-app/agent-config/commit/810df58e7b7525b781f3cf5f93a1b651a85927fc))
-* **install:** regenerate install bundle ([f167954](https://github.com/event4u-app/agent-config/commit/f1679547063d9cf6c9354c1d25d026f740445169))
-* **condense:** refresh stale hash for commands/optimize/project.md ([fa9c0ec](https://github.com/event4u-app/agent-config/commit/fa9c0ecb57653a6157a1eacdc8eba2fd77a357c5))
-* **condense:** project phases-4-7 rule/command/context edits into dist/agent-src ([7d727db](https://github.com/event4u-app/agent-config/commit/7d727db49522669d2aba3ac8e87cdbf5c9410898))
-* **tasks:** unify task test to include the vitest suite ([e0ca766](https://github.com/event4u-app/agent-config/commit/e0ca766bc7a15ebf17347ac246257d57c04bf63f))
-* **roadmap:** retrieval-substrate-hardening Phase 0 B6 done ([671f8d5](https://github.com/event4u-app/agent-config/commit/671f8d519a885bd93302d9962b3fc5c78469715a))
-* **roadmap:** record the inconclusive live judge run on token-saving Phase 0 ([2356ec8](https://github.com/event4u-app/agent-config/commit/2356ec88527366fe6122fdaeb71e0ff1284f364c))
-* **sync:** regenerate pack manifests after through-line pack move ([adde3de](https://github.com/event4u-app/agent-config/commit/adde3de8e94a7f03a6ebdc31e7837c0696b47209))
-* **roadmap:** frontier-quality Phase 0 authored (proposal, checkpoint pending) ([0912362](https://github.com/event4u-app/agent-config/commit/0912362aedf6a90ae122ad1ea4f167e741c40dae))
-* **roadmap:** close + archive second-brain-delta-proof (PASS) ([ec0909d](https://github.com/event4u-app/agent-config/commit/ec0909d78264d33e7ba71e6387ae553bd3494354))
-
-Tests: 7188 (+161 since 8.8.0)
+* **sync:** propagate the shortened skill description into the generated domain README ([ec2a931](https://github.com/event4u-app/agent-config/commit/ec2a931e76b148c0c653dad3353f6f11590edf33))
+* **roadmaps:** feedback-8.11-2 disposition executed and archived ([0037d52](https://github.com/event4u-app/agent-config/commit/0037d521c62699d3757b5e975dafbec54beab1b4))
+* **condense:** record knowledge-card template condensation hash ([7ce68cc](https://github.com/event4u-app/agent-config/commit/7ce68cc38d976a4e10666bdf006db4059d788305))
+* **roadmaps:** feedback-8.11 disposition executed and archived ([960179f](https://github.com/event4u-app/agent-config/commit/960179fa08e343a8e1bb1856bce76e2025abe8d3))
+
+Tests: 7509 (+130 since 8.11.0)
 
 # Era: pre-4.0.0 — archived
 

package/README.md

@@ -1,10 +1,10 @@
 <p align="center"><a href="https://event4u.app"><img alt="event4u Agent Config" src=".github/assets/banner.png"></a></p>
 
-# Agent Config — every claim machine-checked, including "zero runtime"
+# Agent Config — every claim machine-checked, including "zero runtime daemon"
 
 [![Smoke](https://github.com/event4u-app/agent-config/actions/workflows/smoke.yml/badge.svg)](https://github.com/event4u-app/agent-config/actions/workflows/smoke.yml) [![Public install smoke (3 OS × 2 Node)](https://github.com/event4u-app/agent-config/actions/workflows/smoke-public-install.yml/badge.svg)](https://github.com/event4u-app/agent-config/actions/workflows/smoke-public-install.yml) [![npm](https://img.shields.io/npm/v/@event4u/agent-config?style=flat-square&label=npm&color=orange)](https://www.npmjs.com/package/@event4u/agent-config) [![agent-config MCP server](https://glama.ai/mcp/servers/event4u-app/agent-config/badges/score.svg)](https://glama.ai/mcp/servers/event4u-app/agent-config)
 
-[![Skills](https://img.shields.io/badge/Skills-270-orange?style=flat-square)](dist/agent-src/skills/) [![Rules](https://img.shields.io/badge/Rules-103-orange?style=flat-square)](dist/agent-src/rules/) [![Commands](https://img.shields.io/badge/Commands-177-orange?style=flat-square)](dist/agent-src/commands/) [![Guidelines](https://img.shields.io/badge/Guidelines-90-orange?style=flat-square)](docs/guidelines/) [![Personas](https://img.shields.io/badge/Personas-29-orange?style=flat-square)](dist/agent-src/personas/) [![Advisors](https://img.shields.io/badge/Advisors-5-orange?style=flat-square)](dist/agent-src/personas/advisors/)
+[![Skills](https://img.shields.io/badge/Skills-271-orange?style=flat-square)](dist/agent-src/skills/) [![Rules](https://img.shields.io/badge/Rules-104-orange?style=flat-square)](dist/agent-src/rules/) [![Commands](https://img.shields.io/badge/Commands-178-orange?style=flat-square)](dist/agent-src/commands/) [![Guidelines](https://img.shields.io/badge/Guidelines-91-orange?style=flat-square)](docs/guidelines/) [![Personas](https://img.shields.io/badge/Personas-29-orange?style=flat-square)](dist/agent-src/personas/) [![Advisors](https://img.shields.io/badge/Advisors-5-orange?style=flat-square)](dist/agent-src/personas/advisors/)
 
 > **Choose your experience — developer · founder · content · agency · finance · ops. Add packs. Get a focused command set, not a 500-artefact dump.** Bring your own AI provider.
 
@@ -12,13 +12,13 @@
 
 **Every public claim in this README is machine-checked — [verify it yourself](docs/proof.md).** In a market that runs on unbacked headline numbers, this one binds each claim to resolvable evidence or fails its own build.
 
-**270 skills, 177 commands, 103 governed rules** — plus a capability router that loads the right skill on intent, and multi-agent orchestration with consensus review. The whole layer is compiled into 7+ host agents (Claude Code, Cursor, Augment, Cline, Windsurf, Copilot, Gemini) with **zero runtime daemon**.<!-- claim:no-runtime-daemon --> Six role-shaped entry paths sit on top, so any host becomes a reliable team member — without locking you to a single model or vendor.
+**A deep library of skills, commands, and governed rules** — plus a capability router that loads the right skill on intent, and multi-agent orchestration with consensus review. The whole layer is compiled into 7+ host agents (Claude Code, Cursor, Augment, Cline, Windsurf, Copilot, Gemini) with **zero runtime daemon**.<!-- claim:no-runtime-daemon --> Six role-shaped entry paths sit on top, so any host becomes a reliable team member — without locking you to a single model or vendor.
 
 ### What's different
 
 It is both deep **and** disciplined — and honest about what it deliberately is not:
 
-- **Depth that routes itself** — 270 skills + 177 commands, with a capability router that loads the right one on intent, not a 500-artefact context dump.
+- **Depth that routes itself** — a deep skill and command library, with a capability router that loads the right one on intent, not a 500-artefact context dump.
 - **Governance on every host** — rules compiled into each tool's native format at projection time; deterministic runtime hooks added on hook-capable hosts. This config-space, host-agnostic governance is the moat ([the governance advantage](docs/governance-advantage.md) · [enforcement by host](docs/enforcement-by-host.md)).
 - **Surgical uninstall** — removes only its own keys from a shared host config (matched by JSON-pointer + SHA-256), never a neighbour tool's entries.<!-- claim:surgical-uninstall -->
 - **Pack-scoped install** — writes the active pack only, not a 500-artefact dump.
@@ -67,7 +67,7 @@ what is *not* loaded · examples):
 
 ### Workflows, not raw commands
 
-You don't memorize 177 commands — you run a **work journey**. Four flows span the
+You don't memorize every command — you run a **work journey**. Four flows span the
 developer story end-to-end; each names the command you TYPE to start and the
 skills it composes:
 
@@ -462,7 +462,7 @@ When a prompt matches a command's purpose ("setze ticket ABC-123 um" → `/imple
 | [**Migration**](docs/MIGRATION.md) | Per-version upgrade steps |
 | [**Showcase**](docs/showcase.md) | More examples & expected behavior |
 
-Browse content: [all 177 commands](dist/agent-src/commands/) · [skills catalog](docs/skills-catalog.md) · [full catalog](docs/catalog.md) · [`llms.txt`](llms.txt).
+Browse content: [all commands](dist/agent-src/commands/) · [skills catalog](docs/skills-catalog.md) · [full catalog](docs/catalog.md) · [`llms.txt`](llms.txt).
 
 ---
 

package/dist/agent-src/commands/challenge-me/vision.md

@@ -34,7 +34,10 @@ Drop the seed — a plan, idea, ticket draft, or design sketch — and I'll
 walk you through a decision tree, one question per turn, until I'm 95%
 sure what you want. Then you get a copyable Markdown pitch.
 
-Stop early any time by typing `!pitch` (or `!Vision pitchen`).
+End the interview early any time:
+  `!pitch`              — emit pitch, hand back
+  `!roadmap`            — emit pitch + auto-route to `/roadmap:create`
+  `!ai` / `!council`    — poll the AI council for the open question(s), continue (cost auto-accepted)
 ```
 
 Skip the welcome if the user invokes `/challenge-me vision <seed>` directly.
@@ -138,7 +141,7 @@ NEVER ASK WHAT `grep`, `view`, OR `codebase-retrieval` ANSWERS IN SECONDS.
 2. **Look up before asking.** Existing routes, model fields, conventions,
    feature flags, previous similar features → resolve from the repo.
    Surface findings briefly in the next question block ("Repo says X
-   already exists at `path/to/file.php`"). The user should never have to
+   already exists at `path/to/file`"). The user should never have to
    answer a question the codebase already answers.
 3. **List the open dimensions** internally — goal, scope, users, data,
    constraints, success criteria, edge cases, rollback. Do not surface
@@ -164,9 +167,11 @@ constraint this unblocks>.
 3. <alternative option>
 4. Skip / not relevant
 
-> Reply with a number, a free-form answer, or type **`!pitch`**
-> (or **`!Vision pitchen`**) to lock in the current understanding and
-> get the Markdown pitch.
+> Reply with a number, a free-form answer, or one of:
+> **`!pitch`** — emit pitch and hand back ·
+> **`!roadmap`** (or **`!roadmap:create`**) — emit pitch + auto-route to `/roadmap:create` ·
+> **`!ai`** (alias **`!ai-council`** / **`!council`**) — poll the council on the open question(s),
+> cost auto-accepted, then continue the interview.
 ````
 
 **Rules for the question block.**
@@ -188,25 +193,37 @@ constraint this unblocks>.
 1. Number reply (`1`, `2`, …) → adopt that option.
 2. Free-form reply → integrate verbatim, do not re-interpret.
 3. "Skip" / "skip" / "n/a" → branch closed, do not revisit unless reopened.
-4. Pitch trigger fired → jump straight to Step 4, even if confidence < 95%.
+4. Trigger fired → branch by trigger type (see table below):
+   - `!pitch` → jump to Step 4, then Step 5 (emit pitch), then Step 6 hand-back.
+   - `!roadmap` / `!roadmap:create` → Step 4 → Step 5 (emit pitch) → Step 6 with **roadmap routing**.
+   - `!ai` / `!ai-council` / `!council` → jump to **Step 4-bis (Council poll)**, then resume Step 1 with the answers integrated.
 
-#### Pitch trigger — strict matching
+#### Triggers — strict matching
 
-The pitch trigger requires **explicit syntax** to avoid false positives
-on natural sentences like "I'd pitch this to the team".
+Three trigger families end or branch the interview. All require
+**explicit syntax** to avoid false positives on natural prose
+("I'd pitch this to the team", "let's run a council later").
+
+| Trigger | Action | Cost gate |
+|---|---|---|
+| `!pitch` · `/pitch` · whole reply `pitch` | Emit pitch (Step 5), hand back (Step 6) | none |
+| `!roadmap` · `!roadmap:create` · `/roadmap` · `/roadmap:create` · whole reply `roadmap` | Emit pitch (Step 5), then route to `/roadmap:create` with the pitch as seed (Step 6) | none — roadmap creation is text-only |
+| `!ai` · `!ai-council` · `!council` · `/ai` · `/ai-council` · `/council` · whole reply `ai` / `council` | Snapshot open question(s), invoke `/council default` to draft answers, integrate, resume Step 1 | **auto-accepted** — typing the trigger is the consent (per user opt-in to the trigger contract) |
+
+Match rules apply to **every** trigger above:
 
 | Match | Example | Fires? |
 |---|---|---|
-| `!pitch` (or any `!`-prefixed variant) at line start | `!pitch`, `!Vision pitchen`, `!pitch it` | yes |
-| `/pitch` at line start | `/pitch` | yes |
-| Whole reply is exactly `pitch` (case-insensitive, no other words) | `pitch` | yes |
-| `pitch` inside a sentence | "I would pitch this on Monday" | **no** |
-| `pitch mich` / `ship vision` inside prose | natural-language fragment | **no** |
+| `!<trigger>` at line start | `!pitch`, `!roadmap`, `!council`, `!Vision pitchen` | yes |
+| `/<trigger>` at line start | `/pitch`, `/roadmap:create`, `/ai-council` | yes |
+| Whole reply exactly the trigger word (case-insensitive) | `pitch`, `roadmap`, `council` | yes |
+| Trigger word inside a sentence | "I would pitch this on Monday", "let's poll the council later" | **no** |
+| Natural-language fragment (`pitch mich`, `ship vision`) | prose | **no** |
 
-`DE: "!Vision pitchen", "/Vision pitchen", "/pitche das", whole reply "pitch" · EN: "!pitch the vision", "/pitch the vision", whole reply "pitch"`
+`DE: "!Vision pitchen", "!roadmap erstellen", "!Council befragen", whole reply "pitch" · EN: "!pitch the vision", "!roadmap it", "!council on this", whole reply "pitch"`
 
-If the agent is unsure whether the user pitched, it confirms once
-(numbered options: `1. emit pitch · 2. continue interview`) instead of
+If the agent is unsure **which** trigger fired (e.g. `!council and pitch`),
+it confirms once with numbered options listing the candidates instead of
 guessing.
 
 ### Step 3: Re-score and continue
@@ -218,7 +235,7 @@ the next question. If reached, go to Step 4 without asking.
 
 Before emitting the pitch, run this checklist internally:
 
-1. All four 95%-conditions hold (or the user fired the pitch trigger).
+1. All four 95%-conditions hold (or the user fired `!pitch` / `!roadmap`).
 2. Every adopted answer is reflected in the pitch — no orphan branches.
 3. Acceptance criteria are observable and testable in the project's
    existing test surface — not "works correctly" / "looks better".
@@ -226,6 +243,41 @@ Before emitting the pitch, run this checklist internally:
 
 If any check fails, ask one more question instead of pitching.
 
+### Step 4-bis: Council poll (`!ai` / `!ai-council` / `!council` only)
+
+Fires **instead of** Step 4/5 when an AI trigger matches. Cost gate is
+auto-accepted by the trigger contract — do **not** re-ask.
+
+1. **Snapshot** the current interview state:
+   - The seed (verbatim).
+   - All adopted answers so far (as `<question> → <answer>` lines).
+   - Open branches and the very-next question on the table.
+   - Any open assumptions surfaced so far.
+2. **Build the council prompt** as a single block:
+
+   ```
+   You are reviewing an in-progress /challenge-me vision interview.
+   Seed: <verbatim>
+   Adopted: <list>
+   Open question(s): <list>
+   For each open question, recommend an answer with one-line rationale,
+   plus any unstated risk you spot. Be terse.
+   ```
+3. **Invoke** `/council default prompt:"<above>"` non-interactively
+   (auto-accepted cost gate). Pass the host's `ai_council.min_rounds`
+   default — do **not** raise rounds inside the trigger.
+4. **Integrate** the council output:
+   - Surface each council answer **labelled with the source** (e.g.
+     `Council recommends: <answer> — rationale: <one line>`).
+   - Do **not** silently adopt — the user still picks (`1` to accept,
+     free-form to refine, `skip` to discard).
+5. **Resume Step 1** with the very-next question, now showing the
+   council's recommendation as option 1 (with the existing recommended
+   option pushed to option 2 if they differ).
+
+If the council call fails (network, budget, missing member), report the
+error in one line and resume Step 1 unchanged — do **not** re-trigger.
+
 ### Step 5: Emit the pitch
 
 Output a single fenced Markdown block the user can copy verbatim. Shape:
@@ -262,22 +314,50 @@ Output a single fenced Markdown block the user can copy verbatim. Shape:
 The outer fence uses four backticks so the inner triple-backtick stays
 literal when the user copies it.
 
-### Step 6: Hand back
+### Step 6: Hand back — HARD STOP after artifact
 
-After the pitch is emitted, end the turn. Do **not** propose to also
-implement the pitch, write it to a roadmap, or commit anything — the
-pitch is conversational output the user copies into the next command
-(`/work`, `/roadmap-create`, `/feature-plan`, …).
+```
+PITCH OR ROADMAP LANDED → STOP. NEVER PROPOSE IMPLEMENTATION,
+NEVER ASK "READY TO START?". THE USER PICKS THE NEXT MOVE WITH AN
+EXPLICIT EXECUTION VERB ON A LATER TURN.
+```
 
-If the user wants the next step run, they invoke it explicitly.
+Branch on which trigger fired (or the natural 95%-stop):
+
+- **Natural stop or `!pitch`** — end the turn after emitting the pitch.
+  Do **not** propose to also implement, write to a roadmap, or commit —
+  the pitch is conversational output the user copies into the next
+  command (`/work`, `/roadmap:create`, `/feature-plan`, …).
+- **`!roadmap` / `!roadmap:create`** — emit the pitch (Step 5) **and**
+  immediately route to [`/roadmap:create`](../roadmap/create.md) using
+  the pitch as the seed for its Step 1 ("Title / goal", "Context",
+  "Phases"). The user keeps full control inside `/roadmap:create` —
+  this is opt-in routing, not silent execution. Mention the route in a
+  single line under the pitch (e.g. *"Routing to `/roadmap:create` —
+  this pitch becomes the seed for title + context + phase 1."*).
+  The chain ends when `/roadmap:create` saves the file — its own Step
+  9 is a hard stop ([`roadmap/create § 9`](../roadmap/create.md)), no
+  execution offer rides on the back of `!roadmap`.
+- **`!ai` / `!ai-council` / `!council`** — handled by Step 4-bis, never
+  reaches Step 6.
+
+If the user wants any other follow-up, they invoke it explicitly. The
+"Recommended next step" line in the pitch (Step 5) names a *command*
+(`/work`, `/roadmap:create`, …) — it is a suggestion the user copies,
+**not** an offer this command auto-routes through.
 
 ## Output format
 
 1. **Per-turn question block** — one numbered question with a recommended
-   option, until 95% or pitch trigger.
+   option, until 95% or a trigger (`!pitch` / `!roadmap` / `!ai`).
 2. **Final pitch** — a single copyable fenced Markdown block (Step 5 shape).
 3. **One-line handoff suggestion** under the pitch — which command to run
-   next (`/work`, `/roadmap-create`, `/feature-plan`, etc.).
+   next (`/work`, `/roadmap:create`, `/feature-plan`, etc.).
+   - For `!roadmap` triggers, this line is the route announcement
+     instead of a suggestion (Step 6).
+4. **Council-poll output** (only if `!ai` fired) — labelled council
+   answers integrated into the next question block (Step 4-bis), not a
+   final pitch. The interview resumes.
 
 ## Examples
 
@@ -310,17 +390,26 @@ If the user wants the next step run, they invoke it explicitly.
 - **One question per turn** — non-negotiable, per
   [`ask-when-uncertain`](../../rules/ask-when-uncertain.md) Iron Law.
 - **No auto-execution** — emit the pitch, not the implementation it
-  describes. Do not chain into `/work` or `/roadmap-create` without
-  explicit user invocation.
-- **No file writes** — the pitch is conversational. No commits, no
-  roadmap edits, no `agents/` writes.
+  describes. Do not chain into `/work` or `/roadmap:create` without
+  explicit user invocation. The `!roadmap` trigger **is** explicit
+  invocation by user opt-in; routing under it is permitted **and ends
+  at file save** — never propose "ready to start Phase 1?" after the
+  roadmap lands. See [`scope-mechanics § Post-artifact hard stop`](../../contexts/authority/scope-mechanics.md).
+- **No file writes from /challenge-me itself** — the pitch is
+  conversational. No commits, no roadmap edits, no `agents/` writes.
+  The `!roadmap` trigger routes to `/roadmap:create`, which writes
+  under its own contract (with its own user confirmation in Step 6).
+- **Council cost gate is auto-accepted under `!ai`** — typing the
+  trigger is the consent. Do not surface a second confirmation. If
+  `personal.autonomy: auto`, the trigger still consents on its own —
+  the user explicitly opted in by typing it.
 - **Codebase first** — Step 0 forbids asking what `grep`, `view`, or
   `codebase-retrieval` would answer in seconds.
 - **Welcome once** — render the welcome only on the first no-body
   invocation per session.
 - **Mirror the user's language** — the question blocks and pitch use
-  the language the user wrote in (`language-and-tone` Iron Law). The
-  pitch trigger syntax (`!pitch`, `/pitch`, whole reply `pitch`) stays
+  the language the user wrote in (`language-and-tone` Iron Law). All
+  trigger syntax (`!pitch`, `!roadmap`, `!ai` and their aliases) stays
   literal in any language.
 
 ## Do NOT