@event4u/agent-config 8.9.0 → 8.11.0

package/docs/benchmark.md

@@ -112,6 +112,22 @@
 Residual of the full package over `rules-kernel-dc`: Δ=+0.083, Wilcoxon p=0.37
 (only 2 discordant pairs) — **not significant**.
 
+### `full` discipline-tier disposition (council 2026-07-10)
+
+The `full` tier (~11.7×) stays **experimental, opt-in only, never surfaced as a
+recommendation**. Council (claude-sonnet-4-5 + gpt-4o, 2-round debate,
+2026-07-10) converged on **keep-and-relabel over drop**: round 1 favoured
+dropping `full`, but the rebuttal round reversed it — `p=0.37` is *absence of
+evidence*, not *evidence of absence* (an underpowered n=24 compounded by an
+`essential` ceiling effect), and removing an enum value is an **irreversible
+breaking change** for anyone pinning the tier string. An experimental opt-in
+does not violate "measured, not asserted"; an unlabeled *recommendation* would.
+**Revisit-if (drop only when):** a high-powered Claude sweep (n≥100,
+ceiling-adjusted) shows `p>0.20 AND effect <5%` **and** an open-source-host
+adapter sweep returns a null — i.e. `full` is shown *actively* useless, not
+merely unproven. Until then the experimental label stands everywhere `full` is
+documented.
+
 Three findings:
 
 1. **~95% of the lift survives at ~3× cost.** The kernel + `downstream-changes`
@@ -213,6 +229,41 @@ strong = ceiling null · GPT weak = failed replication (confounded surface).
 
 - Report: `internal/bench/reports/ab-v2/2026-07-07T10-33-53Z-ab-v2-paired.json`.
 
+## Two-host matrix (flow-learnings Phase 3, `claude-haiku-4-5`) — Gate verdict: **HONEST-NULL**
+
+First live run of the `bench_matrix` two-host composite (`internal/bench/matrix.yaml`):
+2 task families × 2 hosts × arms `vanilla` vs `rules-kernel-dc`, 2 seeds,
+n=14 paired runs per host. Result — **zero discipline lift on either host**,
+every pair a tie:
+
+| Host / family | n | discipline (van → rkdc) | capability |
+|---|---|---:|---|
+| `claude` / over-engineering-bait | 8 | 1.000 → 1.000 | 1.000 |
+| `claude` / regression-landmine | 6 | 1.000 → 1.000 | 1.000 |
+| `codex` / over-engineering-bait | 8 | 1.000 → 1.000 | **0.000** |
+| `codex` / regression-landmine | 6 | 0.667 → 0.667 | **0.000** |
+
+Two honest reads, neither a lift:
+
+1. **`claude` ceilings** on both capability and discipline (1.000 everywhere) —
+   no headroom, the injected rules are redundant here. This is the same
+   strong-/ceiling-host null the corpus shows elsewhere; these two families are
+   not the ones `downstream-changes` carries a lift on (that is the
+   scope/downstream family), so a null here **confirms** the lift is
+   family-specific, it does not contradict it.
+2. **`codex` capability_pass = 0.000 on every task, both arms** — the codex host
+   did not complete these fixtures capably at all, so its discipline column is
+   **not a meaningful lift signal** (a confounded surface, echoing the P2
+   `gpt-5-mini` replication failure above — a non-Claude host + these fixtures).
+   Reported here as a caveat, not a measurement; a bare table without this note
+   would overclaim.
+
+Net: the matrix pipeline works end-to-end and the composite is reproducible, but
+this cell set carries **no** cross-host discipline lift — `claude` has no
+headroom and `codex` is capability-confounded. Not published as a lift claim.
+
+- Reports (operator-local, untracked): four `internal/bench/reports/ab-v2/2026-07-10T19-2*Z-ab-v2-paired.json` cells (claude×2 families, codex×2 families).
+
 ## Strong host (`sonnet`, full 30-task corpus) — Gate verdict: **HONEST-NULL**
 
 - capability lift significant: `False`

package/docs/catalog.md

@@ -1,13 +1,13 @@
 # agent-config — Public Catalog
 
-Consumer-facing catalog of all **629 public artefacts** shipped by
+Consumer-facing catalog of all **642 public artefacts** shipped by
 this package. Internal package-maintenance rules and deprecation shims
 are excluded.
 
 > **Regenerate:** `./scripts-run src/scripts/generate_index`
 > Auto-generated — do not edit manually.
 
-## Skills (267)
+## Skills (271)
 
 > **Behavioural-eval coverage is measured, not implied.** A skill is
 > behaviourally evaluated only if it ships `evals/evals.json`; most do
@@ -18,9 +18,10 @@ are excluded.
 
 > **Non-coding domain correctness is scoped, not proven.** The
 > `finance` / `founder` / `ops` / `content` skills are forged on TS/PHP
-> codebases; 5 of 20 default-surface domain skills carry a sourced
-> `evals/domain-truth.json` fixture (deterministic targets, keys from
-> cited formulas); the rest are labeled `unvalidated` until they pass one
+> codebases; 9 of 20 default-surface domain skills carry a sourced
+> `evals/domain-truth.json` fixture (deterministic targets with keys from
+> cited formulas, or rubric targets matching a named external practice);
+> the rest are labeled `unvalidated` until they pass one
 > (`./scripts-run src/scripts/domain_soundness_status`). A disclaimer
 > floor bounds liability, not correctness — see [the proof page](proof.md).
 
@@ -128,6 +129,7 @@ are excluded.
 | 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 | [`html-deck`](../dist/agent-src/skills/html-deck/SKILL.md) |  | Build a slide presentation as one HTML file — fixed 1920×1080 canvas letterboxed to any viewport, layout-system-first, type floors. Use for deck, slides, presentation, or pitch requests. |
+| skill | [`humanizer`](../dist/agent-src/skills/humanizer/SKILL.md) |  | Use when removing AI-writing tells from deliverable prose — posts, articles, drafts. Triggers on 'make this sound less like AI', 'humanize this draft', 'this reads like ChatGPT wrote it'. |
 | 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'. |
@@ -260,10 +262,11 @@ are excluded.
 | 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 | [`spreadsheet-authoring`](../dist/agent-src/skills/spreadsheet-authoring/SKILL.md) |  | Use when building or editing a spreadsheet or model — formulas over hardcoded values, read-back after writes, official-source data, pivot-first charts. Triggers on 'spreadsheet', 'build a model'. |
 | 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`; fires even on a pasted query asking 'why is this slow'. |
 | 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 | [`subagent-orchestration`](../dist/agent-src/skills/subagent-orchestration/SKILL.md) |  | Use when orchestrating implementer/judge subagents — form gate + eight modes (do-and-judge ±two-stage, steps/parallel/worktrees, competitively, debate, live-app-judge). |
 | skill | [`supply-chain-intake`](../dist/agent-src/skills/supply-chain-intake/SKILL.md) |  | Before adding/installing any dependency the agent named — verify the package exists (slopsquatting: ~1 in 5 AI suggestions are hallucinated), isn't typo-adjacent, is pinned + locked, and CVE-scanned |
 | 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 on a bug, test failure, crash, or unexpected behavior — enforce reproduce → isolate → hypothesize → verify before any fix; fires even on 'this is broken' / 'quick fix'. |
@@ -272,6 +275,7 @@ are excluded.
 | skill | [`technical-specification`](../dist/agent-src/skills/technical-specification/SKILL.md) |  | Use when the user says \"write a spec\", \"create RFC\", \"write a PRD\", or \"document this decision\". Writes technical specifications, PRDs, RFCs, and ADRs with clear structure. |
 | skill | [`terraform`](../dist/agent-src/skills/terraform/SKILL.md) |  | Use when writing Terraform — AWS modules, resources, variables, outputs, remote state — even when the user just says 'provision this infra' or 'add an S3 bucket' without naming Terraform. |
 | skill | [`terragrunt`](../dist/agent-src/skills/terragrunt/SKILL.md) |  | Use when working with Terragrunt — DRY multi-env configs, module dependencies, remote state orchestration — even when the user just says 'deploy this to staging and prod' without naming Terragrunt. |
+| skill | [`test-case-discovery`](../dist/agent-src/skills/test-case-discovery/SKILL.md) |  | Use BEFORE writing any test — enumerate cases per behavior (happy / boundary / error / abuse), prioritize by likelihood × impact, cross-check via subagent — even if the user just says 'add tests'. |
 | skill | [`test-driven-development`](../dist/agent-src/skills/test-driven-development/SKILL.md) |  | Use when implementing a feature, fixing a bug, or refactoring — write a failing test first, then the code — even if the user just says 'add this function' or 'fix this bug'. |
 | skill | [`test-performance`](../dist/agent-src/skills/test-performance/SKILL.md) |  | Use when optimizing test suite performance — database setup, seeder optimization, parallel testing, CI pipeline efficiency, or RefreshDatabase alternatives. |
 | skill | [`testing-anti-patterns`](../dist/agent-src/skills/testing-anti-patterns/SKILL.md) |  | Use BEFORE writing/changing tests, adding mocks, or test-only methods on production classes — vs mocking-the-mock, production pollution, partial mocks, and overfit/tautological assertions |
@@ -293,8 +297,9 @@ are excluded.
 | 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'. |
 | skill | [`wireframe`](../dist/agent-src/skills/wireframe/SKILL.md) |  | Explore a flow or layout with 3+ disposable lo-fi greyscale wireframes on a named axis, before any hi-fi work. Use when the user wants to sketch directions or explore structure. |
+| skill | [`worktree-lifecycle`](../dist/agent-src/skills/worktree-lifecycle/SKILL.md) |  | Use when governing a worktree across its whole life — scope-lock declaration, merge-readiness status, scoped verification, and safe cleanup that refuses while unique unmerged commits exist. |
 
-## Rules (101)
+## Rules (103)
 
 | kind | name | type | description |
 |---|---|---|---|
@@ -311,6 +316,7 @@ are excluded.
 | rule | [`brand-source-of-truth`](../dist/agent-src/rules/brand-source-of-truth.md) | auto | Consumer brand tokens + voice profile are the run's source of truth — the corpus fills gaps, never overrides |
 | rule | [`broken-access-control`](../dist/agent-src/rules/broken-access-control.md) | auto | Endpoint/query returning user or tenant data — authenticated ≠ authorized; enforce a server-derived ownership/tenant/role check + the three negative tests (401/non-owner/cross-tenant) |
 | rule | [`cli-output-handling`](../dist/agent-src/rules/cli-output-handling.md) | auto | Verbose CLI output (git, tests, linters, docker, npm, composer) — wrap with rtk; tail/grep fallback |
+| rule | [`code-comment-discipline`](../dist/agent-src/rules/code-comment-discipline.md) | auto | Writing/editing code in any language — a comment states a WHY or a constraint the code cannot show; never restate what names/types already say; no signature-mirroring docblocks |
 | rule | [`command-suggestion-policy`](../dist/agent-src/rules/command-suggestion-policy.md) | auto | Prompt matches an eligible slash command — surface as numbered options with as-is escape; never auto-execute |
 | rule | [`commit-conventions`](../dist/agent-src/rules/commit-conventions.md) | auto | Git commit format, branch naming, conventional commits, committing, pushing, creating PRs |
 | rule | [`commit-policy`](../dist/agent-src/rules/commit-policy.md) | always | Commit policy — never commit and never ask about committing unless the user said so this turn, the roadmap authorizes it, or a commit command is invoked |
@@ -385,6 +391,7 @@ are excluded.
 | 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 this package copied/harvested/compared against — keep the tracked tree source-anonymous |
 | rule | [`source-discovery-gate`](../dist/agent-src/rules/source-discovery-gate.md) | auto | Before coding/DB/API/vendor work — prove structural facts against a real source (file:line, SDL, probe) |
+| rule | [`spreadsheet-source-quality`](../dist/agent-src/rules/spreadsheet-source-quality.md) | auto | Financial data in a spreadsheet uses official sources first (IR, regulatory filings); aggregator/news/social figures need explicit permission + a cell-level unofficial mark |
 | rule | [`strategy-safety-floor`](../dist/agent-src/rules/strategy-safety-floor.md) | auto | Founder-strategy output (vision, positioning, moats, OKRs) — never a final call; human owns the decision |
 | rule | [`symfony-routing`](../dist/agent-src/rules/symfony-routing.md) | auto | Symfony work (DI, bundles, Doctrine, Messenger, voters, console) — route to symfony-workflow |
 | rule | [`telegraph-speak`](../dist/agent-src/rules/telegraph-speak.md) | auto | telegraph.speak_scope != off — telegraph the prose; carve-outs (options, Iron-Law, code, paths) stay byte-stable |
@@ -400,7 +407,7 @@ are excluded.
 | rule | [`user-interrupt-priority`](../dist/agent-src/rules/user-interrupt-priority.md) | auto | New user instruction mid-flight — STOP the current task, run the new one in full, ASK before resuming |
 | 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 (172)
+## Commands (178)
 
 | kind | name | cluster | description |
 |---|---|---|---|
@@ -479,6 +486,7 @@ are excluded.
 | command | [`ghostwriter-show`](../dist/agent-src/commands/ghostwriter/show.md) | cluster: ghostwriter | Render a single ghostwriter profile in full — identity, style fingerprint, voice samples, taboos, source URLs. Read-only. |
 | command | [`ghostwriter-write`](../dist/agent-src/commands/ghostwriter/write.md) | cluster: ghostwriter | Draft a markdown post in the voice of a captured public-figure ghostwriter profile; appends the mandatory non-removable disclosure footer. |
 | command | [`grill-me`](../dist/agent-src/commands/grill-me.md) | cluster: challenge-me | Alias for /challenge-me — interactive grill-style interview that sharpens a fuzzy plan/idea into a copyable Markdown pitch |
+| command | [`humanize`](../dist/agent-src/commands/humanize.md) | cluster: humanize | Remove AI-writing tells from pasted text or a file — runs the humanizer skill's draft→audit→final loop and prints the rewrite plus a detector summary. |
 | command | [`image`](../dist/agent-src/commands/image.md) | cluster: image | Character-image fidelity orchestrator — analyse, create, and verify a character image against its canon. Routes to analyse, create, verify. |
 | command | [`image-analyse`](../dist/agent-src/commands/image/analyse.md) | cluster: image | Analyse a character image down to the smallest mole and diff it against a canon — per-feature spec, OCR tattoo text, severity-ranked drift report. |
 | command | [`image-create`](../dist/agent-src/commands/image/create.md) | cluster: image | Generate a character image to spec — assemble a max-fidelity, anchors-first prompt from a Canon Spec; governance- and provider-gated, dry-run by default. |
@@ -576,8 +584,13 @@ are excluded.
 | command | [`video-stitch`](../dist/agent-src/commands/video/stitch.md) | cluster: video | Re-stitch existing clips in `<project>/scenes/*/` after operator edits — no re-render. ffmpeg concat driven by manifest.json. |
 | 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` engine, confidence-band gated, no auto-git. |
+| command | [`worktree`](../dist/agent-src/commands/worktree.md) | cluster: worktree | Worktree orchestrator — routes to create, status, verify, cleanup |
+| command | [`worktree-cleanup`](../dist/agent-src/commands/worktree/cleanup.md) | cluster: worktree | Safe worktree removal gate — refuses while the branch holds commits on no other ref; never force-deletes |
+| command | [`worktree-create`](../dist/agent-src/commands/worktree/create.md) | cluster: worktree | Create a governed worktree and write its scope-lock note — propose-once branch naming, host-native primitive preferred |
+| command | [`worktree-status`](../dist/agent-src/commands/worktree/status.md) | cluster: worktree | List active worktrees — ownership (scope lock), dirty state, ahead/behind, merge-readiness incl. verification evidence |
+| command | [`worktree-verify`](../dist/agent-src/commands/worktree/verify.md) | cluster: worktree | Run the scoped verification for a worktree's declared change — narrow probes matched to the diff, never the full CI pipeline |
 
-## Guidelines (89)
+## Guidelines (90)
 
 | kind | name | category | description |
 |---|---|---|---|
@@ -621,6 +634,7 @@ are excluded.
 | guideline | [`scqa-framework`](../docs/guidelines/agent-infra/scqa-framework.md) | agent-infra |  |
 | guideline | [`security-lint-containment`](../docs/guidelines/agent-infra/security-lint-containment.md) | agent-infra |  |
 | guideline | [`self-improvement-pipeline`](../docs/guidelines/agent-infra/self-improvement-pipeline.md) | agent-infra |  |
+| guideline | [`simplicity-and-goal-demos`](../docs/guidelines/agent-infra/simplicity-and-goal-demos.md) | agent-infra |  |
 | guideline | [`six-hats`](../docs/guidelines/agent-infra/six-hats.md) | agent-infra |  |
 | guideline | [`size-and-scope`](../docs/guidelines/agent-infra/size-and-scope.md) | agent-infra |  |
 | guideline | [`skill-quality-checklist`](../docs/guidelines/agent-infra/skill-quality-checklist.md) | agent-infra |  |

package/docs/command-flows.md

@@ -7,7 +7,7 @@
 
 > Every command is classified in `src/flows/surface-map.yaml` (coverage enforced by `scripts/lint_command_flow_coverage.py`). The four user-work flows carry rich definitions in `src/flows/<flow>.yaml`.
 
-**172 commands** across **10 surfaces** (4 user-work flows + 6 platform/domain surfaces).
+**178 commands** across **10 surfaces** (4 user-work flows + 6 platform/domain surfaces).
 
 ## User-work flows
 
@@ -63,6 +63,11 @@ _Build it. The core "make the change" front — drive a prompt, ticket, or featu
 - `tests-execute` — Run the project's test suite — stack-adaptive (pest / phpunit / vitest / jest / pytest / …)
 - `update-form-request-messages` — Sync the messages() method of a FormRequest class — add missing entries, link them to language keys, and cl…
 - `work` — Drive a free-form prompt end-to-end through refine → score → plan → implement → test → verify → report — Op…
+- `worktree` — Worktree orchestrator — routes to create, status, verify, cleanup
+- `worktree-cleanup` — Safe worktree removal gate — refuses while the branch holds commits on no other ref; never force-deletes
+- `worktree-create` — Create a governed worktree and write its scope-lock note — propose-once branch naming, host-native primitiv…
+- `worktree-status` — List active worktrees — ownership (scope lock), dirty state, ahead/behind, merge-readiness incl. verificati…
+- `worktree-verify` — Run the scoped verification for a worktree's declared change — narrow probes matched to the diff, never the…
 
 ### Review
 
@@ -235,6 +240,7 @@ _Ghostwriter + post-as voice pipeline._
 - `ghostwriter-list` — List captured ghostwriter profiles under agents/reference/ghostwriter/ as a numbered table with confidence,…
 - `ghostwriter-show` — Render a single ghostwriter profile in full — identity, style fingerprint, voice samples, taboos, source UR…
 - `ghostwriter-write` — Draft a markdown post in the voice of a captured public-figure ghostwriter profile; appends the mandatory n…
+- `humanize` — Remove AI-writing tells from pasted text or a file — runs the humanizer skill's draft→audit→final loop and…
 - `post-as` — Consumer-facing write entry points — :me drafts in the maintainer's own voice from .agent-user.md (no discl…
 - `post-as-ghostwriter` — Thin alias for /ghostwriter:write — drafts a copyable markdown post in a captured public-figure voice with…
 - `post-as-me` — Draft a copyable markdown post in the maintainer's own voice (style source = .agent-user.md.voice_sample).…

package/docs/contracts/CHANGELOG-conventions.md

@@ -55,6 +55,12 @@ The test-count line is enforced for any release that ships changes to
 `scripts/`, `internal/workers/`, or `dist/agent-src/` content; it can be omitted for
 pure-docs releases.
 
+Minor / major sections (`## [X.Y.0]`) additionally carry a `Rollback:` line for
+every introduced or substantially reworked subsystem — required by
+[`release-sizing.md`](release-sizing.md) and enforced by
+`src/scripts/lint_changelog_rollback.ts` for versions above the current
+`package.json` version (historical sections never retro-fail).
+
 ## What counts as breaking
 
 A change is **breaking** (and MUST appear under `### BREAKING CHANGES`

package/docs/contracts/ai-council-config.md

@@ -159,6 +159,15 @@ Implications:
   user opt into a per-day cap; counter state persists at
   `~/.event4u/agent-config/cli-calls.json` with daily UTC reset (wired in
   Phase 1 of the CLI-transport roadmap).
+- **Omitting `model:` for a vendor `cli` member is a PIN, not "latest".**
+  Each vendor CLI client (`anthropic` / `openai` / `gemini`) falls back to a
+  dedicated `DEFAULT_*_CLI_MODEL` constant when `model` is unset
+  (`clients.ts`); `xai` / `perplexity` CLIs are community API wrappers and
+  reuse their `DEFAULT_*_MODEL` API constant. The value is a deliberate pin;
+  the vendor CLI's own default may be newer. Bump the constant intentionally —
+  never assume the omitted default tracks the provider's latest release. The
+  CLI constants are separate from the API ones because the two can legitimately
+  diverge — `openai` API `gpt-4o` vs CLI `gpt-5` is the proof.
 - **Quota observability (step-8 D1, D4):** every `council run` /
   `council debate` prints a one-line `council:quota · <provider>
   used/limit · …` summary before the first member fires. Only
@@ -366,6 +375,89 @@ _artefact mode: full|redacted (counts only)_
 
 Findings are ranked by `consensus_strength` descending. Empty sessions
 emit the heading plus `*No findings were extracted for this session.*`.
+The trailer additionally carries two aggregate lines — **Evidence spread**
+(high/medium/low counts across findings) and **Provider spread** (distinct
+providers that deliberated) — folded in beside `_artefact mode:_`.
+
+### Stance tally (Phase 1 — option-level verdict)
+
+`consensus_scoring` scores *findings*; `stance_tally` produces an
+*option-level* verdict for "A or B?" questions. **Default-off**; with the
+block absent the council path is byte-identical to today.
+
+**Configuration.**
+
+- `stance_tally.enabled` (bool, default `false`) — master switch. A
+  non-bool value is rejected at config load (`CouncilConfigError`); unknown
+  values are not silently coerced.
+
+**Behaviour when enabled.** The final round appends a mandatory closing-line
+contract — `STANCE: <label> | CONFIDENCE: high|med|low | DEALBREAKER: yes|no`
+— parsed deterministically (`stance_tally.ts`), never inferred from prose.
+Weights are confidence factors (`high 1.0 / med 0.75 / low 0.5`); `W_total`
+sums base weights over every member with a parseable stance (abstentions
+included, so they raise the bar). Consensus requires an option to clear
+`⅔ × W_total`; below threshold a structured **split** is returned to the
+user — never a forced winner, never an auto-added round. The synthesis gains
+a **Vote Tally** section (one line per option, the threshold, and a
+cleared-or-escalated line). The final-round wiring is LIVE (2026-07-12): `consult` appends the contract to
+the final round and `render` emits the Vote Tally block, threaded via
+`payload.stance_tally`. A member whose stance line is missing or unparseable is
+a repair-marker; the bounded stance-line-only repair CALL (policy: `repair_action`
+— confirm-interactive / auto-fire under `--auto-continue`) and its estimate row
+are the remaining dispatch wiring.
+
+### Chairman synthesis (Phase 2 — opt-in)
+
+The skill's own Iron Law argues the host, having framed the artefact, cannot
+independently judge it. `chairman` lets a **non-deliberating member** author the
+synthesis instead. **Default `host`** = today's behaviour, byte-identical.
+
+**Configuration.**
+
+- `chairman.mode` (enum `host` | `member` | `auto`, default `host`) — an unknown
+  value is rejected at config load.
+- `chairman.member` (string, required when `mode: member`) — must name a member
+  that exists AND is enabled; **fails closed** at load otherwise.
+- `members.<name>.tier` (int ≥ 1, optional) — capability rank used only as the
+  `auto` tie-break (higher = stronger); non-integer / < 1 rejected at load.
+
+**Selection** (`chairman.ts` `select_chairman`, pure): `host` → host synthesis;
+`member` → the named member, but only if it did **not** deliberate this session
+(a member that argued cannot self-judge — else host fallback with a visible
+annotation); `auto` → **provider-family difference primary, tier tie-break,
+config-order final** — decided by the contested-design council pass
+(claude-sonnet-4-5 + gpt-4o, 2-round debate, 2026-07-12): independence from the
+deliberators' priors is the binding constraint for a judge, so `auto` picks a
+non-deliberating member (provider-different by construction under the
+one-member-per-provider invariant); among candidates the optional
+`members.<name>.tier` wins, else the deterministic config order; no
+non-deliberating member → annotated host fallback. The billable chairman
+dispatch (rendering the synthesis as one member call in `cmd_run`) is the
+remaining wiring step.
+
+### Debate enforcement gates (Phase 3 — opt-in)
+
+- `debate_gates.enabled` (bool, default `false`) — when on, round-2+ debate
+  prompts carry the **anti-conformity directive** (`prompts.ANTI_CONFORMITY_DIRECTIVE`:
+  defend a position; change only on a specific named flaw; agreement without a
+  named reason is conformity). Byte-identical across api/cli/manual (it is part of
+  the shared `user_prompt`). Default-off keeps the debate path byte-identical.
+- `restate.enabled` (bool, default `false`) — reserved for the pre-round-1
+  restatement pass.
+
+The deterministic post-round detectors — dissent-quota (`debate_gates.dissent_quota_met`)
+and the novelty gate (`debate_gates.is_near_duplicate`, reusing the shared
+Jaccard util) — are implemented and tested as pure functions.
+
+**Repair-call policy** (`debate_gates.repair_action`) — decided by the
+contested-design council pass (claude-sonnet-4-5 + gpt-4o, 2026-07-12): a cost
+estimate is an upper bound, not a spend commitment, and repairs are failure-mode
+responses — so **interactive runs get a one-line confirm** before each repair
+call; **unattended runs (`--auto-continue`) auto-fire** under the hard cap
+(≤ 1 repair per member per round, absolute — an already-repaired member is
+skipped in every mode); manual-transport members follow the same policy. The
+repair-dispatch wiring in `run_debate` is the remaining step.
 
 ### Decision resolution by impact (Phase 10, ask-user routing)
 

package/docs/contracts/command-clusters.md

@@ -48,6 +48,7 @@ column 1 of this table.
 | `orchestrate` | — | _(none yet — cluster head only)_ | new — runtime executor for YAML pipelines under `.agent-config/orchestrations/` per the [`orchestration-dsl-v1`](orchestration-dsl-v1.md) contract; chains personas / skills / commands / sub-agents deterministically. Single cluster head; sub-commands deferred until a second verb is needed. |
 | `sync` | 4 | `agent-settings` · `gitignore` · `gitignore-fix` | new cluster 2026-07-08 — absorbs the former single-sub `sync-gitignore` cluster (slug-neutral nests: `sync-agent-settings`, `sync-gitignore`, `sync-gitignore-fix` keep their slugs; the gitignore node keeps its own `fix` sub-dir, mirroring the `agents/user` deep-nest precedent). Bare `/sync` shows the menu. |
 | `ghostwriter` | — | `fetch` · `write` · `list` · `show` · `delete` | new cluster 2026-05-15 — third voice primitive for AI-assisted writing in the public voice of a public figure. Hybrid storage: real-person profiles live consumer-side under `agents/reference/ghostwriter/<slug>.md` (gitignored by default); package source ships only `fictional: true` fixtures. Zero network code in the package — `:fetch` delegates web-fetch / web-search to the host agent. Mandatory disclosure footer on every `:write` output (no opt-out). Schema: [`ghostwriter-schema`](ghostwriter-schema.md). |
+| `humanize` | — | _(none yet — cluster head only)_ | new cluster 2026-07-11 (`road-to-humanized-writing` Phase 3) — on-demand AI-tell removal for deliverable prose (pasted text or file path) via the [`humanizer`](../../src/skills/humanizer/SKILL.md) skill's draft→audit→final loop + the `detect_ai_tells.ts` detector; `--voice=<slug\|me>` reuses the write-engine style-source resolution (no second voice mechanism). Counterpart to the engine-internal step 4b in [`write-engine`](write-engine.md). Single cluster head; sub-commands deferred until a second verb is needed. |
 | `post-as` | — | `me` · `ghostwriter` | new cluster 2026-05-15 — consumer-facing write entry points. `:me` reads `.agent-user.md.voice_sample` and drafts in the maintainer's own voice (no disclosure footer — the user is the author); `:ghostwriter` is a thin alias for `/ghostwriter:write` with the mandatory disclosure footer. Both share the procedural [`write-engine`](write-engine.md) contract — style source and footer are the only axes of variation. |
 | `video` | — | `from-script` · `from-song` · `scene` · `storyboard` · `stitch` | new cluster 2026-05-17 — AI video generation pipeline. Cluster head orchestrates the full flow; `:scene` runs a single scene end-to-end (script → blueprint → still → motion → clip); `:storyboard` expands a script into per-scene blueprints + reference stills with character-lock JSON; `:from-script` walks a multi-scene script through storyboard + per-scene generation; `:from-song` builds a music-video from a song + reference images — derived/briefed timed script (via the `song-to-script` skill + `probe-audio.sh` hybrid segmentation), optional character-lock, then stitch with the song muxed as the master track and a mandatory AI-generation disclosure; `:stitch` concatenates scene clips with `ffmpeg` against a scene manifest. Provider-agnostic via the adapter contract under `scripts/media/lib/adapter-contract.md`; cost-gated with mandatory `AIV_DRYRUN=true` default and explicit confirmation before live provider calls. |
 | `knowledge` | — | `ingest` · `list` · `forget` · `cross-repo` | local-knowledge namespace (employee-product Phase 7); `:cross-repo` added 2026-05-30 (`road-to-leaner-core-and-discovery` Phase 4) — read-only targeted retrieval over opted-in `linked_projects` siblings (ADR-032 Option A), per [`cross-repo-retrieval`](cross-repo-retrieval.md). The pre-existing `ingest`/`list`/`forget` sub-commands are recorded in the registry here for the first time. |

package/docs/contracts/design-artifact-lifecycle.md

@@ -0,0 +1,93 @@
+# Design-Artifact Lifecycle Contract
+
+Phase 1 of `road-to-design-artifact-fidelity`.
+One lifecycle every design/artifact skill points at, so "context before taste"
+and "rendered artifact before claim" are a shared workflow, not per-skill folklore.
+Design work is a **pipeline** — understand, inspect, plan, build, verify, hand
+off — not a bag of styling tips.
+
+This contract is advisory (staged-rollout stage 1 per
+[`design-artifact-verification` § Staged rollout](design-artifact-verification.md#staged-rollout)):
+skills reference these stages; nothing here is a default gate yet.
+
+## The lifecycle
+
+Six stages. Every design task runs the stages its branch (below) selects — never
+skips straight to "build".
+
+| # | Stage | What it does | Exercised by fixtures |
+|---|---|---|---|
+| 1 | **Understand** | Medium, audience, fidelity, target host. What *kind* of artifact (screen, deck, doc, component, prototype), for whom, at what polish, verifiable how (per the capability table). | `daf-no-context` |
+| 2 | **Inspect** | Read the existing design system + code **before** styling — code over screenshots when available; copy the visual vocabulary; confirm assets exist. Ask when no context is attached. | `daf-inaccessible-design-system`, `daf-missing-asset` |
+| 3 | **Plan** | Define the visual system + the variation plan: which axis varies, how many options, labelled. No unrequested variations. | `daf-requested-variations`, `daf-unwanted-variations` |
+| 4 | **Build** | Produce the artifact against the system. Surgical on edits; no invented filler (§ Design constraints). | `daf-edit-preservation` |
+| 5 | **Verify** | Prove the rendered artifact — render / load / responsive / export — via a primitive the host has, else caveat honestly (never fake). | `daf-overlapping-text`, `daf-mobile-fit`, `daf-export-readback-failure` |
+| 6 | **Handoff** | Brief, honest handoff: what was built, what is verified vs caveated, implementation intent, preserved comment anchors. | `daf-export-readback-failure` |
+
+Fixtures are defined in [`tests/design-artifacts/eval-fixtures.md`](../../tests/design-artifacts/eval-fixtures.md);
+the ids are stable so skill edits in later phases can prove the stage is operational.
+
+## Skill → stage map
+
+Skills own the *depth* at each stage; the lifecycle owns the *order*. A skill
+cites the stage(s) it serves instead of re-describing the workflow.
+
+| Stage | Primary skills |
+|---|---|
+| Understand | [`fe-design`](../../src/skills/fe-design/SKILL.md), [`design-review`](../../src/skills/design-review/SKILL.md) |
+| Inspect | [`existing-ui-audit`](../../src/skills/existing-ui-audit/SKILL.md), [`brand-audit`](../../src/skills/brand-audit/SKILL.md), [`brand-to-tokens`](../../src/skills/brand-to-tokens/SKILL.md) |
+| Plan | [`fe-design`](../../src/skills/fe-design/SKILL.md), [`ui-component-architect`](../../src/skills/ui-component-architect/SKILL.md) |
+| Build | [`ui-component-architect`](../../src/skills/ui-component-architect/SKILL.md), [`html-deck`](../../src/skills/html-deck/SKILL.md) (decks), [`doc-coauthoring`](../../src/skills/doc-coauthoring/SKILL.md) (documents) |
+| Verify | [`playwright-testing`](../../src/skills/playwright-testing/SKILL.md), [`design-review`](../../src/skills/design-review/SKILL.md), [`markitdown`](../../src/skills/markitdown/SKILL.md) (export readback) |
+| Handoff | [`design-review`](../../src/skills/design-review/SKILL.md), [`design-system-capture`](../../src/skills/design-system-capture/SKILL.md) |
+
+(The roadmap's conceptual "presentations" / "PDF / document" skills map to the
+real `html-deck`, `markitdown`, and `doc-coauthoring` skills above.)
+
+## Branch rules
+
+The lifecycle is not linear for every task. Pick the branch first; it selects
+which stages run and which fixtures gate it (each branch has ≥1 fixture).
+
+| Branch | Trigger | Stages run | Gating fixtures |
+|---|---|---|---|
+| **New design** | Greenfield artifact, no prior version | 1→2→3→4→5→6 (full) | `daf-no-context`, `daf-inaccessible-design-system`, `daf-requested-variations` |
+| **Targeted edit** | Change one named thing in an existing artifact | 2 (light) → 4 → 5 | `daf-edit-preservation`, `daf-unwanted-variations` |
+| **Iteration** | Refine an existing artifact across a version bump | 1 (delta) → 3 → 4 → 5; **preserve the prior version** on a major revision | `daf-requested-variations` |
+| **Design-system extraction** | Derive tokens/components from existing artifacts | 2 (deep) → 6 | `daf-inaccessible-design-system` |
+| **Handoff to production code** | Turn a design into implementation intent | 5 → 6 | `daf-overlapping-text`, `daf-mobile-fit`, `daf-export-readback-failure` |
+
+**Targeted edit stays surgical** — no redesign of neighbours, no reformatting of
+untouched regions, comment anchors preserved (the `daf-edit-preservation`
+contract; mirrors [`minimal-safe-diff`](../../src/rules/minimal-safe-diff.md) for
+visual work). **Iteration preserves the prior version** on a major revision so a
+regression is recoverable.
+
+## Design constraints — do not invent filler
+
+```
+EMPTY SPACE IS A COMPOSITION PROBLEM, NOT PERMISSION TO ADD MATERIAL.
+NEVER INVENT FAKE SECTIONS, FAKE METRICS, LOREM-STYLE COPY, OR STOCK
+DECORATION TO FILL A LAYOUT. ASK BEFORE ADDING MATERIAL THAT ISN'T IN THE BRIEF.
+```
+
+- **Do not invent filler.** A sparse layout is solved with composition
+  (spacing, scale, hierarchy), not with fabricated content. Fake KPIs, invented
+  testimonials, placeholder charts with made-up numbers, and decorative
+  stock-like imagery are content the user did not ask for and cannot trust.
+- **Ask before adding material.** If the artifact genuinely needs content that
+  isn't supplied (a section the brief implies but doesn't provide), surface the
+  gap and ask — do not silently manufacture it. Realistic placeholder clearly
+  labelled as placeholder is acceptable when the user asked for a mock; passing
+  invented data off as real is not.
+
+This is the design-surface instance of the no-invented-facts discipline
+([`direct-answers`](../../src/rules/direct-answers.md) Iron Law 2) and the
+no-placeholder-slop rule ([`output-discipline`](../../src/rules/output-discipline.md)).
+
+## Related
+
+- [`design-artifact-verification`](design-artifact-verification.md) — the Phase-0 host-capability & degrade contract this lifecycle's Verify stage runs against.
+- [`tests/design-artifacts/eval-fixtures.md`](../../tests/design-artifacts/eval-fixtures.md) — the nine fixtures the stages + branches gate on.
+- [`design-fidelity`](../../src/rules/design-fidelity.md) — the provided-design-is-the-spec rule the Inspect stage enforces.
+- [`fe-design`](../../src/skills/fe-design/SKILL.md), [`existing-ui-audit`](../../src/skills/existing-ui-audit/SKILL.md), [`design-review`](../../src/skills/design-review/SKILL.md), [`ui-component-architect`](../../src/skills/ui-component-architect/SKILL.md) — the design skills that cite these stages.

package/docs/contracts/design-artifact-verification.md

@@ -1,6 +1,6 @@
 # Design-Artifact Verification — Host-Capability & Degrade Contract
 
-Phase 0 substrate for [`road-to-design-artifact-fidelity`](../../agents/roadmaps/road-to-design-artifact-fidelity.md).
+Phase 0 substrate for `road-to-design-artifact-fidelity`.
 Design work is only production-grade if the agent **verifies the rendered
 artifact** — but a verification step the host cannot run must degrade honestly,
 never block the work or fake a green check.
@@ -78,6 +78,35 @@ When the needed primitive is `❌` (or a `⚠️` probe fails):
    console errors") for a check that did not run — that is an invented fact
    ([`direct-answers`](../../src/rules/direct-answers.md) Iron Law 2).
 
+## Verification checklist
+
+Run before claiming a design artifact done. Each step is gated by the primitive
+it needs — a step whose primitive is absent is **skipped with a caveat**, never
+faked (§ Honest-degrade). "Looks good" is not a verification result.
+
+1. **Open the artifact** (`local_browser` / `playwright` / `pdf_render` / `doc_export`) — it opens and paints; a static-only host inspects the source instead.
+2. **Console / load errors** (`console_inspect`) — no runtime errors or failed loads on open.
+3. **Desktop + mobile viewport** (`screenshot`) — inspect a desktop width and ~375px; no overflow / clipping.
+4. **Text fit / no overlap** (`screenshot`, degrade `static_inspect`) — no collisions or truncation at the target breakpoints.
+5. **Referenced assets decode** (`image_decode`) — every referenced image / font resolves and decodes (no broken `src`).
+6. **Key interaction state** (`playwright`) — the primary interaction (open / submit / toggle) behaves; description-only where unavailable.
+7. **Capture evidence only when supported** (`screenshot`) — attach a screenshot / diff when the host can; otherwise cite what was statically checked.
+
+**Completion contract.** A design task with render capability present cannot
+claim "done" without at least steps 1–5 as evidence. Where capability is absent
+(no browser / renderer), report that plainly (§ Rollback language) and keep the
+completion claim scoped to what was actually checked. The checklist is exercised
+by the verification golden tasks in
+[`eval-fixtures.md`](../../tests/design-artifacts/eval-fixtures.md)
+(`daf-nonblank-canvas`, `daf-mobile-fit`, `daf-missing-asset`,
+`daf-overlapping-text`, `daf-broken-interaction`, `daf-export-readback-failure`).
+
+Skills wire this in: [`playwright-testing`](../../src/skills/playwright-testing/SKILL.md)
+runs it when a browser primitive is present; [`design-review`](../../src/skills/design-review/SKILL.md)
+gates its verdict on it; static decks / documents use the deck / PDF / document
+verification path ([`html-deck`](../../src/skills/html-deck/SKILL.md),
+[`markitdown`](../../src/skills/markitdown/SKILL.md) readback).
+
 ## Staged rollout
 
 Design-artifact fidelity rolls out in three stages so nothing becomes a hard

package/docs/contracts/evidence-based-pruning.md

@@ -94,6 +94,7 @@ candidate; the human, seeing the evidence, makes the call.
 
 ## See also
 
+- [`ADR-118`](../decisions/ADR-118-loop-engineering-boundaries.md) — engagement counts stay ONE input; the pruning decision is never automated (disposition #2).
 - [`local-analytics.md`](local-analytics.md) — the measurement events + privacy floor.
 - [`capability-packs.md`](capability-packs.md) — sibling per-pack budget governance.
 - [`ADR-041`](../decisions/ADR-041-controlled-command-verbs.md) — sibling command-surface governance.

package/docs/contracts/hook-architecture-v1.md

@@ -192,6 +192,31 @@ Phase 7.4 ships a regression test that spawns two concurrent
 dispatcher invocations against the same event and asserts no torn
 writes (file ends with valid JSON, last-writer-wins).
 
+## Hook-resilience shim — every registered command degrades silently
+
+Every hook command the installer registers (Claude managed block + plugin
+`hooks/hooks.json`, Cursor, Windsurf, Gemini, the Augment trampoline) follows
+one shape (road-to-opt-subagent-harvest P1.4):
+
+1. **Resolve the dispatcher** — project-local binary first, PATH fallback
+   where the platform supports it (Claude: `$CLAUDE_PROJECT_DIR/agent-config`
+   → `agent-config`).
+2. **Missing dispatcher → silent `exit 0`.** A hook must never error-spam or
+   block the agent loop on a repo where the suite is not (yet) installed.
+   This is the honest degrade even for `fail_closed` concerns: an absent
+   dispatcher cannot evaluate anything, so there is nothing to fail closed
+   ON — the deny power exists only where the suite exists.
+3. **Present dispatcher → exit code PROPAGATES.** No `|| true` around the
+   dispatch call itself: a `fail_closed: true` concern (e.g.
+   `block-no-verify`) keeps its deny. Fail-open of crashed concerns is
+   handled INSIDE `dispatch_hook.ts` per the manifest's `fail_closed` flag,
+   never by the outer shim.
+
+The Augment trampoline (`src/scripts/hooks/augment-dispatcher.sh`) is the
+reference implementation of the same contract in shell form (`set -u`,
+silent bails, unconditional `exit 0` — Augment concerns are all
+observe-only, so blanket exit 0 is correct there).
+
 ## Copilot fallback pattern
 
 Copilot has no hook surface. Concerns whose source rule cites

package/docs/contracts/kernel-membership.md

@@ -302,3 +302,38 @@ with the trigger-relaxed parameter, lock new value, re-attempt.
 | 2026-05-06 | `agents/runtime/council/sessions/20260506T044941Z-phase1-cross-check-r2.json` | Council R2 (3500 tokens) — locks median r, splits criterion #3, adds criterion #5, raises per-rule cap to 2.5k, defines abort criteria | <!-- council-ref-allowed: contract decision trace -->
 | 2026-05-06 | this file | kernel set locked: 9 rules, projected 23 071 chars (median r = 0.712) |
 | 2026-05-06 | P2.2 condensation + `scripts/iron_law_sha.py --all-kernel` | empirical: 25 590 chars (r_actual = 0.795 across kernel; longer rules condense less than the pilot median) — see `docs/decisions/ADR-002-kernel-bucket-overrides.md` (KERNEL_HARD raised 25k → 26k, 6 per-rule overrides ≤ 4k ceiling, all Iron-Law SHAs preserved) |
+
+## § 10 — Changing a protected invariant
+
+The semantic-invariants gate (`src/scripts/check_rule_invariants.ts` over
+`tests/golden/invariants.json`, 19 protected strings across the 9 kernel
+rules) enforces string presence in BOTH `src/rules/` and the
+`dist/agent-src/rules/` projection. String matching is deliberately the
+current enforcement: it is zero-cost and trips on casual edits. Its known
+brittleness — a semantically equivalent rewording breaks the gate — is
+handled by process, not by weakening the gate.
+
+**Rewording a protected string is allowed, but never "update the gate
+green".** A PR that changes an entry in `tests/golden/invariants.json`
+MUST:
+
+1. Name WHICH invariant changes and WHY the wording changes (PR body).
+2. State old/new side-by-side with an explicit assertion-equivalence
+   sentence ("the new wording still guarantees X").
+3. Re-run and quote `check_rule_invariants.ts --mutation-selftest` in the
+   PR (the selftest guards the checker against silently-green
+   normalisation bugs after the edit).
+4. Cite the behavioral eval covering the invariant where one exists; where
+   none exists, say so explicitly — an uncovered invariant rewording gets
+   extra review scrutiny, not less.
+
+Kernel-edit slow-rollout rules (own PR, ≥ 24 h soak between kernel merges,
+per `scope-control § kernel-rule-edits`) apply on top — the invariants file
+is part of the kernel surface.
+
+**ID migration is gated, not planned.** Migrating string fragments to
+frontmatter invariant IDs happens only after behavioral evals cover ≥ 10
+of the 19 invariants. Until then, IDs would claim guarantees nothing
+verifies — an ID whose text drifted validates nothing, and that failure is
+silent, unlike a string miss (council convergence, anthropic/
+claude-sonnet-4-5 + openai/gpt-4o, 2026-07-10).

package/docs/contracts/measurement-baseline.md

@@ -96,6 +96,7 @@ P2 roadmap reads — not the live `internal/bench/reports/` directory.
 
 ## Cross-references
 
+- [`ADR-118`](../decisions/ADR-118-loop-engineering-boundaries.md) · bench-drift stays advisory by decision — never a blocking gate (disposition #4)
 - [`benchmark-report-schema.md`](benchmark-report-schema.md) · per-report JSON schema
 - [`benchmark-corpus-spec.md`](benchmark-corpus-spec.md) · corpus YAML schema
 - [`condensation-default-kill-criterion.md`](condensation-default-kill-criterion.md) · decision table read by step-4 closeout