@event4u/agent-config 9.3.0 → 9.4.0

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": "9.3.0",
+    "version": "9.4.0",
     "keywords": [
       "agent-config",
       "skills",

package/CHANGELOG.md

@@ -166,6 +166,29 @@ gated on the telemetry from 6.0.0-C. Deferred to 6.0.0-C: a
 `skills_discoverable` field, reactive just-in-time pack activation, and the
 per-pack budget lint.
 
+### Added — team mode: governed cross-model review (default-off, `road-to-team-mode`)
+
+A new default-off `/team` command family (`review`, `adversarial`, `delegate`,
+`status`) that governs the official `openai/codex-plugin-cc` as the Claude-Code
+transport — a second strong model reviewing the real working-tree diff (depth),
+the complement to the council's neutral-artefact breadth.
+
+- **Default-off + fail-closed.** With `ai_team.enabled: false` (default) no
+  command is suggested and invocation prints an enable pointer — byte-identical
+  to pre-roadmap behaviour. On Claude-Code hosts the wrappers are thin
+  delegations to `/codex:*`; absent the plugin they fail closed with the
+  `agent-config doctor --check team` remediation, never a silent no-op.
+- **Multi-host fallback (review lens only).** On non-Claude-Code hosts
+  `/team:review` sends a size-capped repo-diff bundle through the existing
+  subscription `OpenAICliClient`, with an honest capability-delta header.
+- **Governed, not rebuilt.** Nothing upstream-maintained is reimplemented; the
+  Review-Gate stays upstream's (we add an opt-in loop-bound + ledger line), and
+  `/team:delegate` (write access) sits behind a second opt-in
+  `ai_team.allow_delegate: false`. Config: `docs/contracts/ai-team-config.md`.
+- **No quality claim yet.** Cross-model defect-finding lift is unproven until
+  the Phase 5 benchmark runs (spend-gated); the docs describe workflow value
+  only, never a lift claim.
+
 ### Breaking — v4.0.0 unified setup (`road-to-unified-setup`)
 
 `v4.0.0` is a **hard-cut** release. The legacy Python installer at
@@ -1033,6 +1056,61 @@ our recommendation order, not its support status.
 > that forces a new era split (`# Era: 9.3.x`, etc.) — see
 > [`docs/contracts/CHANGELOG-conventions.md § Era splits`](docs/contracts/CHANGELOG-conventions.md).
 
+## [9.4.0](https://github.com/event4u-app/agent-config/compare/9.3.0...9.4.0) (2026-07-20)
+
+### Features
+
+* **self-review:** large-diff / claim-affecting ai-council escalation (detect + recommend) ([1308e22](https://github.com/event4u-app/agent-config/commit/1308e220179600424d4ac590ae9295b522f3f22c))
+* **council:** cross-round prompt-cache read unlock ([5faf32b](https://github.com/event4u-app/agent-config/commit/5faf32bc3b0522e7e0af3b28a108ce808133a56e))
+* **council:** auto model-tiering gated on the A1<->A3 cache coupling ([1a693bf](https://github.com/event4u-app/agent-config/commit/1a693bffe79addde715becc9a366c5185e9545b9))
+* **council:** stance repair fires only on genuinely unparseable STANCE ([40196bd](https://github.com/event4u-app/agent-config/commit/40196bdac2489dc50ac1213976e776d94f3f89c7))
+* **adoption:** wedge promise, opt-in first-run instrument, honest positioning surface ([c93e314](https://github.com/event4u-app/agent-config/commit/c93e314b102ba437afcbef994306a5f0c42d2476))
+* **routing:** reciprocal cluster routing for the weighted-matrix mode ([6be7bc5](https://github.com/event4u-app/agent-config/commit/6be7bc5b7d042bdfc000c5a51270a7c9da5a2f28))
+* **skill:** weighted-matrix mode in decision-record ([7eaf4db](https://github.com/event4u-app/agent-config/commit/7eaf4db125eebe19cb0d57ac32f15f917530b206))
+* **command:** /contribution-precheck — contributor self-service gate subset ([5e7de9b](https://github.com/event4u-app/agent-config/commit/5e7de9b6b828653bb0e49e1711f42ee56c18e4cd))
+* **catalog:** provenance source column + CREDITS.md ([10cca8a](https://github.com/event4u-app/agent-config/commit/10cca8af8a244aa30d0ee036126e24c506c82e48))
+* **ci:** wire lint_originality --changed as the originality-gate PR job ([00c3754](https://github.com/event4u-app/agent-config/commit/00c3754df8d9a95c30a84c294bfb3ab9cfbbe509))
+* **skills:** add learning-tutor skill — six structured tutoring modes ([8ed343d](https://github.com/event4u-app/agent-config/commit/8ed343d282ad669489866cda84a6a214f1943ca6))
+* **skill:** evaluate-llm-feature — black-box LLM-feature evaluator ([b94249f](https://github.com/event4u-app/agent-config/commit/b94249fb067c39d8fa5c8f4fa6cfe2b1290e336b))
+* **flows:** optional team annotation + resolver ([7b14ed5](https://github.com/event4u-app/agent-config/commit/7b14ed5cbba5bec6b4e5500fb68c6770ad7d5f87))
+* **mcp:** lazy catalog router — index, scoring, stub tools ([d17b9e0](https://github.com/event4u-app/agent-config/commit/d17b9e05fc5742f922177febab086c4723796029))
+* **originality:** anti-reskin shingle-overlap gate ([dae4760](https://github.com/event4u-app/agent-config/commit/dae4760c7b041844bde10fa3e2eb6ae5f34a9fa6))
+
+### Bug Fixes
+
+* **skill:** keep subagent-orchestration under the 400-line size gate ([c419da9](https://github.com/event4u-app/agent-config/commit/c419da949db135c6c1723d85e78906669ee881a2))
+* **portability:** drop task-ci literals from the shipped precheck command ([a0d83d3](https://github.com/event4u-app/agent-config/commit/a0d83d33984847143749131fe0e01509c72edbbb))
+* **ci:** CAPABILITIES 277 count + defang injection-probe examples ([c1d4036](https://github.com/event4u-app/agent-config/commit/c1d4036dd615fa2bcbd670e66583f8eac15fbb6a))
+* **originality:** close the adversarial DF batch-masking hole ([dd84403](https://github.com/event4u-app/agent-config/commit/dd8440363a7ecda67934cca27cb0df4b69ba34e6))
+* **mcp:** version the catalog-index cache filename ([93d980a](https://github.com/event4u-app/agent-config/commit/93d980aff254ceb9d31bf290f36a249377e81eea))
+
+### Documentation
+
+* **team:** CHANGELOG entry + close-out (Phase 6 + prereqs); upstream re-verified ([a6405c5](https://github.com/event4u-app/agent-config/commit/a6405c5ade5e4e1a22c7cb60eaf0d31f7f212b9e))
+* **team:** three-way router disambiguation cross-links (council / team / subagents) ([f82ed16](https://github.com/event4u-app/agent-config/commit/f82ed168f81c48ef98b0e561f44bc13c8691ce77))
+* **self-review:** document the escalation path; flip Phase 1 step (part c) ([9f26716](https://github.com/event4u-app/agent-config/commit/9f267166b1305f9833f89ae8119638105ecd42c1))
+* **roadmap:** archive road-to-api-cost-optimization — A3 executed, fully closed ([94e2044](https://github.com/event4u-app/agent-config/commit/94e20444f215491d6f5350b09910d37a928a090e))
+* **cost:** B2 index-branch pointers (deferred follow-up closed) ([7d68245](https://github.com/event4u-app/agent-config/commit/7d68245ebc013b5fa05f0790473e910e45227a5e))
+* **roadmap:** adoption roadmap — second autonomous slice landed ([0febec6](https://github.com/event4u-app/agent-config/commit/0febec66d629dc2cca6410bfaa07c841711e1966))
+* **announcements:** draft the honest-launch story (drafted, not posted) ([8e1b757](https://github.com/event4u-app/agent-config/commit/8e1b757f53f367c1fdc7d7150eed4ff8edc1e426))
+* **roadmap:** archive road-to-weighted-decision-matrix — fully executed ([4586dcd](https://github.com/event4u-app/agent-config/commit/4586dcd5432c618ffd007af2f0977a24249945aa))
+* **roadmap:** originality-gate + contributor-funnel roadmap, executed and parked ([4d0e73b](https://github.com/event4u-app/agent-config/commit/4d0e73b67298cd78b509778514ab170fcc75e930))
+* **probe:** anti-reskin-gate demand probe + extraction floor ([b849580](https://github.com/event4u-app/agent-config/commit/b8495802f93a966bcf5808e01b15b93e4017fd9a))
+* **roadmap:** complete + archive the ecosystem-harvest index hub ([e1752d1](https://github.com/event4u-app/agent-config/commit/e1752d176fbf948aff364fb1271532164bb2b755))
+* regenerate proof page for the new skill count (277) ([2476284](https://github.com/event4u-app/agent-config/commit/247628404098690ba2f68fa1bef6fdba1753ee13))
+* **roadmap:** complete + archive ecosystem-harvest domain-watch ([d07e81e](https://github.com/event4u-app/agent-config/commit/d07e81e017a90e92863d9bcffd1818b232fefaeb))
+* **domain-watch:** watch-notes for the two gated verticals ([26bb9dd](https://github.com/event4u-app/agent-config/commit/26bb9dd77c7c6adb1bebc9677f5096d8e66ef999))
+* **roadmap:** correct the flip-gate checkbox and tighten the flow-team criterion ([89a2d26](https://github.com/event4u-app/agent-config/commit/89a2d26721090cc7545a19ef73877689a445420f))
+* **roadmap:** persona-library harvest — executed and archived ([1c6940a](https://github.com/event4u-app/agent-config/commit/1c6940a2693c94ad366ddc31f791d13870da6d07))
+* correct outdated Antigravity host claims ([fca90e2](https://github.com/event4u-app/agent-config/commit/fca90e2c3413465e0a4bfbfd65d1da01ea15bef7))
+
+### Chores
+
+* **meta:** sync pack README with shortened precheck description ([601fdc1](https://github.com/event4u-app/agent-config/commit/601fdc111553d8d4c55796d43c3203d938b5c179))
+* **ci:** wire lint-originality and validate-flow-teams into the pipeline ([48bc88a](https://github.com/event4u-app/agent-config/commit/48bc88a2ce24bfffd1f98e4194163986b3adf245))
+
+Tests: 7833 (+63 since 9.3.0)
+
 ## [9.3.0](https://github.com/event4u-app/agent-config/compare/9.2.0...9.3.0) (2026-07-16)
 
 ### Features

package/CONTRIBUTING.md

@@ -127,6 +127,20 @@ the review floor, not around it.
   specific consumer project, domain, or stack. The
   [`augment-portability`](dist/agent-src/rules/augment-portability.md) rule and
   `scripts/check_portability.py` enforce this in CI.
+- **External contributions get credited.** A merged community skill carries
+  `provenance: community` in its frontmatter — the public catalog
+  ([`docs/catalog.md`](docs/catalog.md)) renders it as `community` in the
+  `source` column — and gets a row in [`CREDITS.md`](CREDITS.md)
+  (§ Community contributions). Maintainers add both on merge; if you were
+  missed, open an issue — attribution gaps are treated as bugs.
+- **Originality is CI-gated.** Every PR touching skills, personas, or domain
+  commands runs `lint_originality --changed` (the anti-reskin gate, see the
+  `originality-gate` job in `.github/workflows/skill-lint.yml`). Run it
+  locally before pushing:
+  `./scripts-run src/scripts/lint_originality --changed <changed files>` —
+  or run the whole contributor precheck in one pass via the
+  [`/contribution-precheck`](src/domains/meta/contribution-precheck/command.md)
+  command (frontmatter schema + skill lint + originality, Node-only).
 
 ## Agent-assisted contribution workflow
 

package/README.md

@@ -4,11 +4,13 @@
 
 [![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-276-orange?style=flat-square)](dist/agent-src/skills/) [![Rules](https://img.shields.io/badge/Rules-105-orange?style=flat-square)](dist/agent-src/rules/) [![Commands](https://img.shields.io/badge/Commands-184-orange?style=flat-square)](dist/agent-src/commands/) [![Guidelines](https://img.shields.io/badge/Guidelines-101-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-278-orange?style=flat-square)](dist/agent-src/skills/) [![Rules](https://img.shields.io/badge/Rules-105-orange?style=flat-square)](dist/agent-src/rules/) [![Commands](https://img.shields.io/badge/Commands-190-orange?style=flat-square)](dist/agent-src/commands/) [![Guidelines](https://img.shields.io/badge/Guidelines-101-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.
 
-**Try it in 30 seconds** — drop one read-only subagent into any repo and watch it gate "done": `@production-validator check this branch is actually done`. No wizard, no lock-in, nothing else installed — the [30-second wedge ↓](#quickstart) is the whole first step. Full docs: **[event4u-app.github.io/agent-config](https://event4u-app.github.io/agent-config)**.
+**Try it in 30 seconds** — drop one read-only subagent into any repo and watch it gate "done": `@production-validator check this branch is actually done`. No wizard, no lock-in, nothing else installed — the [30-second wedge ↓](#quickstart) is the whole first step. Start at the proof, not the catalog: **[event4u-app.github.io/agent-config/proof/](https://event4u-app.github.io/agent-config/proof/)**.
+
+![The trust surface running green — every "verify it yourself" command from a real, CI-re-executed run](docs/media/proof-demo.gif)
 
 **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.
 
@@ -120,8 +122,14 @@ is generated from source: a claim→evidence table (every public claim binds to
 resolvable pointer, or CI fails), honest-null benchmarks *including the runs where
 the package changed nothing*, and a "verify it yourself" block you run on a fresh
 checkout. The proof page fails CI if it drifts from its sources — reproducibility
-is the proof. Browse it on the deployed docs site:
-[event4u-app.github.io/agent-config](https://event4u-app.github.io/agent-config).
+is the proof. Browse it on the deployed docs site — the proof page is the primary entry:
+[event4u-app.github.io/agent-config/proof/](https://event4u-app.github.io/agent-config/proof/).
+The honest comparison frame lives at
+[`docs/us-vs-the-category.md`](docs/us-vs-the-category.md).
+
+Maintaining a skills catalog yourself? The **anti-reskin gate** that blocks
+find-replace re-skin PRs here runs on your catalog too —
+[`docs/anti-reskin-gate.md`](docs/anti-reskin-gate.md).
 
 Audit-disciplined by construction — every memory consult, decision
 key, and hook concern lands in `agents/runtime/state/` so you can replay it.

package/dist/agent-src/commands/contribution-precheck.md

@@ -0,0 +1,100 @@
+---
+model_tier: medium
+name: contribution-precheck
+pack: meta
+tier: 2
+visibility: internal
+skills: [lint-skills, check-refs]
+description: "Contributor self-service precheck: run the PR-relevant lint subset (skill linter, originality gate, frontmatter schema) on changed files locally — a verdict with fix hints before opening a PR."
+suggestion:
+  eligible: false
+  rationale: "Package-internal — contributors to event4u/agent-config invoke it explicitly before opening a PR."
+workspaces:
+  - agent-config-maintainer
+packs:
+  - meta
+---
+
+# contribution-precheck
+
+Run the same gates a PR will hit — locally, Node-only, before pushing. Mirrors
+the CI enforcement path (`originality-gate` + skill-lint jobs in
+`.github/workflows/skill-lint.yml`) so a contributor never learns about a
+failure from remote CI first.
+
+Requires only Node + installed `node_modules` (the `./scripts-run` shim invokes
+`tsx` directly — no task runner, no full CI toolchain).
+
+## Instructions
+
+### 1. Compute the changed set
+
+```bash
+BASE=$(git merge-base origin/main HEAD 2>/dev/null || echo HEAD)
+CHANGED=$(git diff --name-only --diff-filter=ACMR "$BASE" -- \
+  'src/skills/*/SKILL.md' \
+  'src/agent-src/personas/*.md' \
+  'src/domains/**/command.md' \
+  | grep -v '^src/agent-src/personas/_' || true)
+```
+
+Uncommitted work counts: append `git diff --name-only` + `git diff --cached
+--name-only` output filtered to the same patterns. Empty set → report
+"nothing to precheck — no changed skills / personas / domain commands" and
+stop (that is an honest no-op, not a pass).
+
+### 2. Run the three gates, in order
+
+| Gate | Command | Mirrors |
+|---|---|---|
+| Frontmatter schema | `./scripts-run src/scripts/validate_frontmatter --root src` | CI schema validation |
+| Skill lint | `./scripts-run src/scripts/skill_linter <changed SKILL.md files>` | `skill-lint` job (`--changed`) |
+| Originality (anti-reskin) | `./scripts-run src/scripts/lint_originality --changed $CHANGED` | `originality-gate` job |
+
+Notes:
+
+- `skill_linter` takes positional paths — pass the changed `SKILL.md` files
+  explicitly (its own `--changed` derivation filters to the projected trees,
+  not `src/`, and would silently check nothing on authored edits).
+- `lint_originality --changed` needs the explicit file list from step 1 — it
+  does not self-derive.
+
+### 3. Emit the verdict
+
+One compact block, worst gate first:
+
+```
+Precheck: <N> changed file(s)
+  ✅|❌ frontmatter — <0 failing | list failing files + first error each>
+  ✅|❌ skill lint  — <pass/warn/fail counts | per-file errors>
+  ✅|❌ originality — <no overlap ≥ WARN | offending pair + overlap %>
+Verdict: READY | FIX FIRST (<n> blocking finding(s))
+```
+
+For every ❌ add one fix hint: the failing file, the rule/pair it tripped, and
+the smallest change that clears it (e.g. "overlap 72% with `<skill>` — rewrite
+the shared procedure sections in your own words; find-replace re-skins score
+~100% because entities are neutralized").
+
+### 4. Degraded mode (no git remote / shallow clone)
+
+`origin/main` missing → fall back to `git diff --name-only HEAD` (working
+tree) for step 1 and say so in the verdict header. Never claim the CI result
+will match exactly in degraded mode — the PR gate diffs against the real base.
+
+## Gotcha
+
+- A clean precheck is **necessary, not sufficient** — remote CI additionally
+  runs the per-pack matrix, security linters and reference checks. The
+  precheck covers the gates that most commonly fail external contributions.
+- Do not "fix" an originality failure by shuffling words until the score dips
+  under the threshold — the entity-neutralized shingle gate is calibrated for
+  find-replace re-skins; a borderline score means the artifact needs its own
+  substance, not better camouflage.
+
+## Do NOT
+
+- Do NOT run the full local CI pipeline as a substitute — this command exists precisely so a
+  contributor without the full toolchain gets a verdict.
+- Do NOT skip step 1's empty-set report — "0 files checked" is INCONCLUSIVE,
+  never a pass (same guard as CI).

package/dist/agent-src/commands/team.md

@@ -146,6 +146,10 @@ measured improvement.
 
 - `/council` — breadth under a neutrality contract; the complement, not the
   competitor.
+- `subagent-orchestration` skill — the in-session, same-weights variant (no
+  network, no spend); team is cross-model with repo access. The three-way
+  router split: council = independent breadth, team = collaborative depth,
+  subagents = in-session same-weights.
 - `adversarial-review` skill — the free single-model first rung below
   `/team adversarial`.
 - `docs/contracts/ai-team-config.md` — the `ai_team` settings block

package/dist/agent-src/contexts/model-recommendations.md

@@ -58,6 +58,12 @@ ABOVE the implementer tier (ladder in
 [`subagent-configuration`](subagent-configuration.md)). Downshifting an
 implementer never downshifts its judge.
 
+## Cost cross-link
+
+Tier choice is also a **billing lever** — for the dollar side (caching, batch,
+model tiering, effort right-sizing) route via `token-optimizer` skill's index
+branch (`api-cost-levers` row); `/cost:report` names the dominant lever.
+
 ## Detection Heuristics
 
 | Signal | Task Type | Tier |

package/dist/agent-src/rules/token-efficiency.md

@@ -30,6 +30,13 @@ IF YOU CATCH YOURSELF REPEATING → STOP, RETHINK, ASK.
 
 When a tool returns a value (branch name, file path, PR number), use that EXACT value in subsequent API calls. NEVER substitute a value from earlier in the conversation. Context decay causes silent mismatches — fresh output is the only source of truth.
 
+## API-dollar levers
+
+Large stable context reused across turns (caching), non-interactive bulk
+cohorts (batch), or cost-aware model/effort decision → route via
+[`token-optimizer`](../skills/token-optimizer/SKILL.md) index branch
+(`api-cost-levers` row) — single source of truth for billing levers.
+
 ## Mechanics
 
 Anti-loop patterns, act-skip-narration / stop-early / minimize-tool-calls clauses, and small-output / debugging exceptions: [`token-efficiency-mechanics`](../contexts/communication/rules-auto/token-efficiency-mechanics.md). Precedence: never overrides `user-interaction` or command rules.

package/dist/agent-src/skills/adversarial-review/SKILL.md

@@ -27,6 +27,11 @@ Do NOT use when:
 - The user explicitly asked for a quick/rough draft.
 - You're exploring options, not committing to one yet.
 
+**Inbound delegation:** [`decision-record`](../decision-record/SKILL.md)
+§ Weighted-matrix mode delegates a scoped attack here after the weighted
+sums ("attack the winner, using the losing options' strongest criteria") —
+treat the matrix + sensitivity block as the artifact under review.
+
 ## Procedure: Adversarial review
 
 1. **Inspect the artifact** — Read the plan, diff, or draft you are about to critique; note its scope, assumptions, and the explicit asks before attacking.

package/dist/agent-src/skills/ai-council/SKILL.md

@@ -958,6 +958,9 @@ fast-path entries (clean session is not an error).
 - `/council` command — the user-facing entry point.
 - `subagent-orchestration` skill — internal multi-agent variant (no
   network, no spend, but no diversity of weights either).
+- `/team` command — collaborative cross-model review WITH repo access
+  (depth); council is breadth on an artefact, team is one strong model in
+  the repo. Different mechanism, not a competitor.
 - `scripts/ai_council/prompts.ts` — neutrality preamble + per-mode
   system prompts.
 - `scripts/ai_council/advisors.ts` — replace-mode planning + persona

package/dist/agent-src/skills/build-buy-partner/SKILL.md

@@ -109,6 +109,7 @@ Pick one. Emit a build-buy-partner ADR via the `adr-create` skill, citing this s
 - Scenario shape comparison — route to [`scenario-modeling`](../scenario-modeling/SKILL.md) (O4); P1 consumes O4's `scenario-bundle.md`.
 - Org-shape changes (reorg, team-split) — route to [`org-design`](../org-design/SKILL.md) (Q1); P1 composes Q1 for the "build" option's team shape.
 - Decision-record authoring mechanics — route to [`adr-create`](../adr-create/SKILL.md); P1 emits an ADR via that skill.
+- A generic multi-option choice on custom user-weighted criteria (not build/buy/partner-shaped) — route to [`decision-record`](../decision-record/SKILL.md) § Weighted-matrix mode; this skill stays the domain-specific instance.
 
 ## When the agent should load this
 

package/dist/agent-src/skills/decision-record/SKILL.md

@@ -1,7 +1,7 @@
 ---
 model_tier: high
 name: decision-record
-description: "Use when choosing between alternatives with trade-offs — X-or-Y decisions (pattern vs pattern, strategy vs strategy) — frames options · trade-offs · consequences; ADR draft via `adr-create`."
+description: "Use when choosing between alternatives with trade-offs — X-or-Y decisions or a weighted decision matrix / gewichtete Entscheidungsmatrix ('score my options'); ADR via `adr-create`."
 status: active
 tier: senior
 domain: process
@@ -126,6 +126,35 @@ If this decision overrides a prior ADR:
 Output the structured payload (below). The user — or
 `adr-create` — turns it into the file.
 
+## Weighted-matrix mode (quantitative)
+
+Optional numeric variant of step 3. **Gate — fire only when ALL hold:**
+≥ 3 options · no single dominant criterion · costly / hard-to-reverse ·
+commensurable criteria (no values conflict). 2-option or reversible choice →
+one-line redirect: just decide, or qualitative matrix above. Full procedure,
+anchors, worked example: [`references/weighted-matrix.md`](references/weighted-matrix.md).
+
+1. User states decision + options.
+2. **User lists criteria + weights (1-10) BEFORE any scoring** — AI may
+   append missed criteria afterward, each labeled `(AI-suggested)`. Never
+   propose criteria first (anchoring).
+3. Criteria hygiene: cap 4-8, merge near-synonyms (double-counting check).
+4. Score options 1-10 against **fixed anchors** (each criterion declares
+   what 1 and what 10 mean — never relative-to-best-in-set).
+5. Weighted sums, then **sensitivity block — the load-bearing gate**:
+   close-call margin (< 10 % = "no clear winner — decide on unquantified
+   factors"), smallest weight change that flips the winner, ±1-score flip
+   test. Fragile winner reported as fragile, never as "the rational choice".
+6. Delegate argue-against to
+   [`adversarial-review`](../adversarial-review/SKILL.md), scoped: "attack
+   the winner, using the losing options' strongest criteria" (`premortem`
+   delegation pattern — never reimplemented inline).
+
+Output appends matrix + sensitivity block + attack summary + intuition
+caveat (resistance to the result signals a wrong weight or unquantified
+information — surface it, don't ignore it). **The score is a structured
+argument, not a verdict.** Hand-off to `adr-create` unchanged.
+
 ## Related Skills
 
 **WHEN to use this**
@@ -147,6 +176,9 @@ Output the structured payload (below). The user — or
   payload, not the file.
 - The risk shape is the dominant question — route to
   [`risk-officer`](../risk-officer/SKILL.md) first, then return.
+- MANY items to rank on the fixed R×I×C/E formula (backlog, feature
+  list) — route to [`rice-prioritization`](../rice-prioritization/SKILL.md);
+  the weighted-matrix mode here is for ONE choice on custom criteria.
 - The decision is reversible and cheap — write a one-line note and
   move on; ADRs are for irreversible or expensive constraints.
 
@@ -157,6 +189,8 @@ Output the structured payload (below). The user — or
 - "Wir müssen ein ADR draus machen."
 - "Trade-off-Matrix für X vs Y."
 - "Diese Entscheidung überschreibt das alte ADR-NN."
+- "Weighted decision matrix für die Optionen" / "score my options
+  against my criteria" — fires the weighted-matrix mode (gate permitting).
 
 ## Output
 

package/dist/agent-src/skills/decision-record/evals/triggers.json

@@ -1,17 +1,87 @@
 {
   "skill": "decision-record",
-  "last_eval": "2026-06-16",
-  "description": "5 should-trigger + 5 should-not-trigger. Seeded from the RDP `decision` discipline rows in tests/reasoning-layer-eval/trigger-fixtures.json (choice among alternatives with real tradeoffs -> decision ledger; escalate to ADR only when cross-task/structural). Should-not covers tasks with no alternatives to weigh (mechanical / single-path).",
+  "last_eval": "2026-07-20",
+  "description": "5 should-trigger + 5 should-not-trigger. Seeded from the RDP `decision` discipline rows in tests/reasoning-layer-eval/trigger-fixtures.json (choice among alternatives with real tradeoffs -> decision ledger; escalate to ADR only when cross-task/structural). Should-not covers tasks with no alternatives to weigh (mechanical / single-path). Extended 2026-07-20 with 5+5 weighted-matrix-mode cases: quantitative scoring asks trigger; RICE-shaped ranking, 2-option reversible, stakeholder-conflict, pure prioritization and explicit rice-prioritization asks do not.",
   "queries": [
-    { "q": "should we use the Action pattern or a Service class for this workflow?", "trigger": true },
-    { "q": "should we adopt Redis or Postgres for the rate-limiter store? weigh the tradeoffs", "trigger": true },
-    { "q": "pick a migration strategy for the column rename: expand-contract or big-bang", "trigger": true },
-    { "q": "do we put authorization in middleware or a policy layer here?", "trigger": true },
-    { "q": "choose between optimistic and pessimistic locking for the checkout flow", "trigger": true },
-    { "q": "use the existing UserRepository to load the user", "trigger": false },
-    { "q": "add a created_at timestamp column to the orders table", "trigger": false },
-    { "q": "rename the variable usr to user in this function", "trigger": false },
-    { "q": "import the logger and log the request id", "trigger": false },
-    { "q": "format this file with the project formatter", "trigger": false }
+    {
+      "q": "should we use the Action pattern or a Service class for this workflow?",
+      "trigger": true
+    },
+    {
+      "q": "should we adopt Redis or Postgres for the rate-limiter store? weigh the tradeoffs",
+      "trigger": true
+    },
+    {
+      "q": "pick a migration strategy for the column rename: expand-contract or big-bang",
+      "trigger": true
+    },
+    {
+      "q": "do we put authorization in middleware or a policy layer here?",
+      "trigger": true
+    },
+    {
+      "q": "choose between optimistic and pessimistic locking for the checkout flow",
+      "trigger": true
+    },
+    {
+      "q": "use the existing UserRepository to load the user",
+      "trigger": false
+    },
+    {
+      "q": "add a created_at timestamp column to the orders table",
+      "trigger": false
+    },
+    {
+      "q": "rename the variable usr to user in this function",
+      "trigger": false
+    },
+    {
+      "q": "import the logger and log the request id",
+      "trigger": false
+    },
+    {
+      "q": "format this file with the project formatter",
+      "trigger": false
+    },
+    {
+      "q": "build me a weighted decision matrix for our three hosting options",
+      "trigger": true
+    },
+    {
+      "q": "gewichtete Entscheidungsmatrix für die vier Anbieter, Kriterien gewichte ich selbst",
+      "trigger": true
+    },
+    {
+      "q": "help me decide between 4 job offers — I want to weight my criteria and score each",
+      "trigger": true
+    },
+    {
+      "q": "score my options against my criteria with weights and show which one wins",
+      "trigger": true
+    },
+    {
+      "q": "we have 3 vendor candidates; weigh cost, support and lock-in and compute a winner",
+      "trigger": true
+    },
+    {
+      "q": "rank our backlog of 40 feature ideas by reach, impact, confidence and effort",
+      "trigger": false
+    },
+    {
+      "q": "tabs or spaces for this repo? quick call, easily reversible",
+      "trigger": false
+    },
+    {
+      "q": "PO wants to ship, ops wants stability — who should win this conflict?",
+      "trigger": false
+    },
+    {
+      "q": "prioritize this quarter's initiatives for the roadmap",
+      "trigger": false
+    },
+    {
+      "q": "run rice-prioritization on these feature requests",
+      "trigger": false
+    }
   ]
 }

package/dist/agent-src/skills/decision-record/references/weighted-matrix.md

@@ -0,0 +1,119 @@
+# Weighted-matrix mode — full procedure
+
+Quantitative variant of the `decision-record` trade-off matrix. Loaded from
+[`SKILL.md § Weighted-matrix mode`](../SKILL.md) when the gate fires; this
+file carries the elicitation detail, anchor discipline, sensitivity math and
+a worked example. The score is a **structured argument, not a verdict**.
+
+## Gate — when the mode fires (all four, else stay qualitative)
+
+1. **≥ 3 options.** Two options rarely need weights — the qualitative matrix
+   or a plain decision is faster and less pseudo-precise.
+2. **No single dominant criterion.** If one criterion decides it (a hard
+   budget cap, a regulatory constraint), the matrix is theatre — decide on
+   the constraint.
+3. **Costly / hard to reverse.** Reversible decisions get a one-line "just
+   decide" redirect; the mode's overhead is only worth a one-way door.
+4. **Commensurable criteria.** When options conflict on *values* (privacy vs
+   revenue, safety vs speed-to-market), numbers hide the conflict instead of
+   resolving it — route to `stakeholder-tradeoff` first.
+
+## Elicitation — user first, always
+
+1. User states the decision in one sentence and names the options.
+2. **User lists criteria and assigns weights 1-10 BEFORE any scoring.** Do
+   not propose criteria first: an AI-proposed list anchors the user onto the
+   AI's frame (anchoring evidence — the council overruled AI-first
+   elicitation on exactly this ground, 2026-07-19). Prompt shape: *"Which
+   criteria matter for this decision, and how much does each weigh, 1-10?"*
+3. After the user's list is locked, the AI may append missed criteria — each
+   explicitly labeled `(AI-suggested)`, each weighted by the user, never by
+   the AI.
+4. **Criteria hygiene:** cap the list at 4-8. Merge near-synonyms
+   ("maintainability" + "ease of change" = one criterion) — two names for
+   one concern double-counts its weight. Check independence: if scoring one
+   criterion forces another's score, merge or drop.
+
+## Scoring — fixed anchors, never relative
+
+Score every option 1-10 per criterion against a **fixed anchor line the
+matrix declares up front**:
+
+```
+Criterion: Operational cost (weight 8)
+  1  = needs a dedicated on-call rotation
+  10 = fully managed, zero routine operations
+```
+
+Never score relative-to-best-in-set ("this one is the cheapest → 10") — a
+new option would silently re-scale every row. Anchors make scores
+re-checkable and the matrix extensible.
+
+## Sensitivity block — the load-bearing gate
+
+Compute weighted sums, then ALWAYS report, in this order:
+
+1. **Close-call margin.** Winner's sum vs runner-up as a percentage of the
+   winner. **< 10 % → "no clear winner — the matrix says the options are
+   equivalent; decide on unquantified factors."** Never present a < 10 %
+   margin as a verdict.
+2. **Weight-flip threshold.** The smallest single weight change that flips
+   the winner (*"raise Operational cost from 6 to 8 and Option B wins"*). A
+   one-step flip is a fragile result — say so.
+3. **±1-score flip test.** Does any single score changed by ±1 flip the
+   winner? User-guessed scores carry at least ±1 of noise; a winner inside
+   that noise band is reported as fragile, never as "the rational choice".
+
+Rationale: user-guessed scores × user-guessed weights is pseudo-precision
+unless the fragility is surfaced — the sensitivity block, not the
+argue-against step, is what keeps the mode honest (council dissent encoded
+2026-07-19).
+
+## Argue against the winner — delegated, scoped
+
+After the sums, delegate to `adversarial-review` — the `premortem`
+delegation pattern, never an inline reimplementation:
+
+> Attack the top-scoring option. Use the losing options' strongest criteria
+> as the attack surface: what did the weights hide, what breaks first, which
+> anchor was scored generously?
+
+Fold the attack summary into the output. If the attack finds a criterion the
+matrix missed, re-run elicitation step 3 — do not silently patch the score.
+
+## Output contract (appended to the standard payload)
+
+```
+Weighted matrix (weights 1-10, scores 1-10 vs fixed anchors):
+  | Criterion (weight) | <opt 1> | <opt 2> | <opt 3> |
+  | ...                |         |         |         |
+  Weighted sums:  <opt 1>: NN · <opt 2>: NN · <opt 3>: NN
+
+Sensitivity:
+  margin: NN %  (< 10 % → no clear winner)
+  weight-flip: <smallest change that flips> | none within ±2
+  ±1-score flip: yes → fragile | no
+
+Attack summary (adversarial-review, scoped to the winner):
+  <2-4 bullets>
+
+Intuition caveat: the matrix complements intuition — resistance to the
+result signals a wrong weight or unquantified information; surface it,
+don't ignore it.
+
+The score is a structured argument, not a verdict.
+```
+
+Then hand off to `adr-create` exactly as the qualitative flow does.
+
+## Worked example (compressed)
+
+Decision: pick a queue backend (4 options, no dominant criterion, one-way
+door — gate passes). User criteria/weights: Operational cost 8, Ecosystem
+maturity 6, Throughput headroom 5, Migration effort 4; AI appends
+`Vendor lock-in (AI-suggested)`, user weights it 3. Anchors declared per
+criterion; scores land; sums: A 178 · B 171 · C 149 · D 122. Margin 3.9 % →
+**no clear winner** — report equivalence, surface that A vs B differ mainly
+on lock-in (unquantified confidence), delegate the attack on A, let the
+user decide on the surfaced residual. The matrix did its job by *refusing*
+to hand down a verdict.