@event4u/agent-config 7.1.0 → 7.3.0

package/.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "description": "Shared agent configuration — skills for AI coding tools (Claude Code, Augment, Cursor, Cline, Windsurf, Gemini CLI).",
-    "version": "7.1.0",
+    "version": "7.3.0",
     "keywords": [
       "agent-config",
       "skills",
@@ -258,6 +258,7 @@
         "./dist/agent-src/skills/design-intelligence",
         "./dist/agent-src/skills/design-review",
         "./dist/agent-src/skills/design-tokens",
+        "./dist/agent-src/skills/design-system-capture",
         "./dist/agent-src/skills/devcontainer",
         "./dist/agent-src/skills/developer-like-execution",
         "./dist/agent-src/skills/discovery-interview",

package/CHANGELOG.md

@@ -948,6 +948,86 @@ our recommendation order, not its support status.
 > that forces a new era split (`# Era: 7.1.x`, etc.) — see
 > [`docs/contracts/CHANGELOG-conventions.md § Era splits`](docs/contracts/CHANGELOG-conventions.md).
 
+## [7.3.0](https://github.com/event4u-app/agent-config/compare/7.2.0...7.3.0) (2026-06-25)
+
+### Features
+
+* **bench:** opt-in hardened arms for governance-enforcement eval ([af9a0e0](https://github.com/event4u-app/agent-config/commit/af9a0e07a2c2312f6b53782a8fcb44b2bde35635))
+* **evals:** cross-model canary workflow + robust smoke (T-005) ([d062095](https://github.com/event4u-app/agent-config/commit/d06209535731d27446768442c081fcac151b3f20))
+* **evals:** cross-model trigger smoke — SDK-free fetch routers + runner (Phase 0 T-004 keystone) ([1a8df9c](https://github.com/event4u-app/agent-config/commit/1a8df9cc83f2a9ace2e4a45eb9d66be6b51be5ae))
+* **evals:** finding_floor assertion kind — deterministic count gate (Phase 1) ([7f0e9e6](https://github.com/event4u-app/agent-config/commit/7f0e9e617a741b1f778d9cacdde145ef4a300994))
+* **evals:** graded negative-control discrimination primitive (Phase 0 T-003) ([5407121](https://github.com/event4u-app/agent-config/commit/54071210ecbfc8b6807fa37d726ea27654d22158))
+
+### Bug Fixes
+
+* **skills:** declare top-level skill field in bug-analyzer/code-review evals ([7c7f2e3](https://github.com/event4u-app/agent-config/commit/7c7f2e3adf181f2a1e936cb028538b3471e8f15e))
+* **skill-linter:** accept finding_floor eval assertion kind ([bb629f9](https://github.com/event4u-app/agent-config/commit/bb629f98c41c09912a6d67d31ceef25a49becb56))
+* **evals:** GeminiRouter JSON output contract — closes the format divergence (Phase 0b) ([f739b32](https://github.com/event4u-app/agent-config/commit/f739b320a1dcb54350d44a67009e634a421034ed))
+* **evals:** drop legacy-path literal from a comment (ADR-051 guard) ([48328f0](https://github.com/event4u-app/agent-config/commit/48328f0bd0f9c36cd8d0f11c2bbc206c49faefc6))
+* **harvest:** drop illustrative ellipsis path that tripped check_references ([94e6098](https://github.com/event4u-app/agent-config/commit/94e6098bf7d4a6e5127729db103a04b61dfc8f39))
+
+### Documentation
+
+* **roadmap:** enforcement honest-null; archive positioning roadmap ([226bf33](https://github.com/event4u-app/agent-config/commit/226bf3394b905a7dbd45fd74c55ab3a001ddaf2f))
+* **readme:** lead with capability; add host-enforcement matrix ([531327d](https://github.com/event4u-app/agent-config/commit/531327d465ed0cc2803b1ee1900d5b551dacbdc0))
+* **harvest:** wider-coverage baseline (10 skills) + agent-ide-plugin security-lessons note ([4a2aaaa](https://github.com/event4u-app/agent-config/commit/4a2aaaaac0b6fbd1467b254207690f5adaacf7d8))
+* **harvest:** Phase 0b resolved — record the 3-variant format-fix evidence + flip checkbox ([a64dcab](https://github.com/event4u-app/agent-config/commit/a64dcab235efb41170cb28fd4603ae2f3fd1de25))
+* **harvest:** cross-model baseline + outcome read (T-006); credential blocker resolved ([b4e8453](https://github.com/event4u-app/agent-config/commit/b4e84534064fe91f4609e2e06fbd04e957f2e2fa))
+* **harvest:** Phase 0 evidence — capability matrix, fixture-portability audit, vendor-credential gate decision ([cb64570](https://github.com/event4u-app/agent-config/commit/cb64570b414c3a4d2e3ec34dda70137f513bbfa5))
+
+### Tests
+
+* **evals:** starter behavioral evals.json fixtures (Phase 1, T-001 0-fixtures gap) ([dd6861b](https://github.com/event4u-app/agent-config/commit/dd6861bff4d66d7458468f0a9b2490ac088157c7))
+
+### Chores
+
+* **roadmap:** archive operator-runtime-harvest (core complete) + park residuals in later/ ([69ef1ac](https://github.com/event4u-app/agent-config/commit/69ef1ac91af47c3c462f4453f74eeb94fece310b))
+* **roadmap:** defer Phase 2 (won't-build-speculatively) — undershoot guard + catalog target ([9f37fa8](https://github.com/event4u-app/agent-config/commit/9f37fa8fcf29f1822a5739d916b5510047a9f23d))
+* **roadmap:** close T-005 + Phase G (honest-null) + plugin note; mark human/parallel residuals ([a0d7f80](https://github.com/event4u-app/agent-config/commit/a0d7f806ac5ed048b19b9c20e41ba392328f3393))
+* **roadmap:** Phase 0 — T-004 + T-006 done (live smoke ran); T-005 re-scoped (cost), Phase 0b actionable ([036e66f](https://github.com/event4u-app/agent-config/commit/036e66f98d3cc805e0128a86ab01ee15fd771bb1))
+* **dist:** sync eval-fixture projection for the new behavioral evals.json ([01cc089](https://github.com/event4u-app/agent-config/commit/01cc08994ebf11d7cf894822b73a4374b7ef0ee9))
+* **roadmap:** Phase 1 — finding_floor mechanism + fixtures done; calibration deferred on P0 ([3a5bc28](https://github.com/event4u-app/agent-config/commit/3a5bc28083206118352b1dd641d76326ac58114d))
+* **roadmap:** Phase 0 — mark T-000..T-003 done, T-004..T-006 deferred on credentials ([4f302ee](https://github.com/event4u-app/agent-config/commit/4f302ee9270b02488d1dce6d285520984d01ab40))
+
+## [7.2.0](https://github.com/event4u-app/agent-config/compare/7.1.0...7.2.0) (2026-06-24)
+
+### Features
+
+* **design-craft:** wire existing design/frontend skills into the anti-slop layer ([4ac512c](https://github.com/event4u-app/agent-config/commit/4ac512c294c47c54c04e71a12d2a85e6a8600d93))
+* **design-craft:** add anti-slop enforcement + design memory + token governance ([4c07b60](https://github.com/event4u-app/agent-config/commit/4c07b60195db52a938f41445a347a0bec3331bc2))
+* **product-clarity:** process wins (release-story, trunk-drift, explainability) ([f91b898](https://github.com/event4u-app/agent-config/commit/f91b898d7ae833bd4eb7b1577e7ae5f78ee96be4))
+* **governance:** capability lifecycle view + complete capability-governance ([f299791](https://github.com/event4u-app/agent-config/commit/f2997914a3f9e25fc0a26b4a202e3f521a0471b7))
+* **governance:** subagent boundary contract ([8ed4181](https://github.com/event4u-app/agent-config/commit/8ed4181afbff73cb99b764ac695354c0bb1f073f))
+* **governance:** skill-growth gate in the authoring flow ([a9a3b80](https://github.com/event4u-app/agent-config/commit/a9a3b80ab7dfbcfee0cb8f0c51d5744aabb03bd7))
+* **governance:** capability-boundary matrix + risk_class invariant ([7b683b8](https://github.com/event4u-app/agent-config/commit/7b683b864188f40424c4a9399a6a931081e14291))
+* **legal-review-prep:** attorney-framing-review promotion tripwire ([551fe8b](https://github.com/event4u-app/agent-config/commit/551fe8b4b7e817c5f81adddfe8d85220f3ef30a7))
+* **legal-review-prep:** high-risk pack metadata ([554282e](https://github.com/event4u-app/agent-config/commit/554282e4b12575dc884c078f45b560facea60be1))
+* **legal-review-prep:** council / deep-research gate on legal work-product ([7b44c89](https://github.com/event4u-app/agent-config/commit/7b44c8961d94ae9a5b99329a80ff725db2d0c6d5))
+* **legal-review-prep:** install consent gate (checkbox + flag + floor refusal) ([af2ee1d](https://github.com/event4u-app/agent-config/commit/af2ee1dbc18446f77f0d13e79b11551634f15d2c))
+* **legal-review-prep:** hard individual-case STOP in the floor + lint ([71860da](https://github.com/event4u-app/agent-config/commit/71860da9699d8537a81942ff4d59aeca6fbd2a96))
+
+### Bug Fixes
+
+* **lint:** trim telegraph-speak amendment to clear long_rule warning ([95d54c6](https://github.com/event4u-app/agent-config/commit/95d54c6852c2344f3402f5f9730185a400fc4941))
+* **lint:** add model_tier to design-system-capture skill ([57c3a6d](https://github.com/event4u-app/agent-config/commit/57c3a6defd57a771a9f86805b9634f3b73a6afee))
+* **framework-neutrality:** drop npm-install literal in design-intelligence ([aeadec5](https://github.com/event4u-app/agent-config/commit/aeadec54038c0d43aed75ea30f30574a2d6b7d65))
+* **ci:** Zod settings parity + router minification for tokens.rich_skills ([88930da](https://github.com/event4u-app/agent-config/commit/88930da1786731a9cc1317b841646477f77ad1d1))
+* **ci:** strict-TS null-safety in design-craft linters ([3cac522](https://github.com/event4u-app/agent-config/commit/3cac522ed8234190a6d361735bc323616b11393b))
+* **ci:** broken refs + unused var in design-craft additions ([2e0c2a7](https://github.com/event4u-app/agent-config/commit/2e0c2a785596c67fb4114ead09caea57aeb6e0ab))
+* **portability:** drop task-invocation from shipped /create-pr command ([e03f97a](https://github.com/event4u-app/agent-config/commit/e03f97a14ea38439ba41427448f7d77c868959c4))
+
+### Documentation
+
+* **roadmaps:** add legal-review-prep + capability-governance + product-clarity roadmaps ([e3ad120](https://github.com/event4u-app/agent-config/commit/e3ad120893dd20cea79c7875558137f42d2797da))
+
+### Refactoring
+
+* **legal:** rename legal pack to legal-review-prep ([fb34133](https://github.com/event4u-app/agent-config/commit/fb3413305718d321b435514e5f0ab0f4122e37b7))
+
+### Chores
+
+* **sync:** condense design-craft skills/rules + sync dist/agent-src/ ([3a3e6e1](https://github.com/event4u-app/agent-config/commit/3a3e6e1f668128e386ca7d19ffe031a09a391fcd))
+
 ## [7.1.0](https://github.com/event4u-app/agent-config/compare/7.0.2...7.1.0) (2026-06-24)
 
 ### Features

package/README.md

@@ -4,17 +4,22 @@
 
 [![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-258-orange?style=flat-square)](dist/agent-src/skills/) [![Rules](https://img.shields.io/badge/Rules-93-orange?style=flat-square)](dist/agent-src/rules/) [![Commands](https://img.shields.io/badge/Commands-162-orange?style=flat-square)](dist/agent-src/commands/) [![Guidelines](https://img.shields.io/badge/Guidelines-86-orange?style=flat-square)](docs/guidelines/) [![Personas](https://img.shields.io/badge/Personas-26-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.
 
-Six role-shaped entry paths, one shared **skills + rules + commands** layer that turns any host agent (Claude Code, Augment, Cursor, Copilot, Windsurf) into a reliable team member — without locking you to a single model or vendor.
+**258 skills, 162 commands, 93 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**. 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
 
-Three things this package ships that a README scan slides right past:
+It is both deep **and** disciplined — and honest about what it deliberately is not:
 
+- **Depth that routes itself** — 258 skills + 162 commands, 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 ([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.
 - **Pack-scoped install** — writes the active pack only, not a 500-artefact dump.
-- **Portability guard** — works in any project; source confidentiality is CI-enforced.
+
+**What it deliberately is *not*** — a content + governance layer, not a runtime: **no background daemon, no separate state database, no self-rewriting memory, no auto-build pipeline.** The host agent runs the loop; every learned change is human-reviewed; the same layer stays portable across tools. Capability without a process to babysit.
 
 See exactly [what works on which host](docs/capability-matrix.md), or jump to [things you can do in a minute](docs/cookbook.md).
 
@@ -85,13 +90,7 @@ is platform operation, not a user-work flow.)
 
 > **Legal Pack — not legal advice.** The EU/DE legal pack (contract/NDA/DPA review, triage) is a **research-and-drafting aid only** — it does not provide legal advice, does not replace a qualified lawyer, and must not be relied on for any concrete matter. It produces general information and general templates, never individual-case examination. Read [`LEGAL_NOTICE.md`](LEGAL_NOTICE.md) before use.
 
-<details>
-<summary><b>Catalog at a glance</b> — raw artefact counts (maintainer reference)</summary>
-
-[![Skills](https://img.shields.io/badge/Skills-257-orange?style=flat-square)](dist/agent-src/skills/) [![Rules](https://img.shields.io/badge/Rules-91-orange?style=flat-square)](dist/agent-src/rules/) [![Commands](https://img.shields.io/badge/Commands-162-orange?style=flat-square)](dist/agent-src/commands/) [![Guidelines](https://img.shields.io/badge/Guidelines-84-orange?style=flat-square)](docs/guidelines/) [![Personas](https://img.shields.io/badge/Personas-26-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/)
-
-The headline is the **experience** (profile + packs), not the raw counts. Full catalog: [`docs/catalog.md`](docs/catalog.md).
-</details>
+> Full catalog — every skill, rule, command, guideline: [`docs/catalog.md`](docs/catalog.md). The headline is the **experience** (profile + packs) **and** the depth behind it.
 
 ## Use it in your project
 

package/dist/agent-src/rules/brand-source-of-truth.md

@@ -51,7 +51,17 @@ corpus from quietly replacing a value the brand already defines.
   marked as corpus-sourced, until `brand-identity` defines real tokens.
 - Non-brand surfaces.
 
+## Design register note
+
+When a consumer brand profile is present, the brand register ("the impression IS
+the product") is active — use `brand-identity`, `iconography`, and
+`design-intelligence` as the primary skill cluster. For product/dashboard/admin
+surfaces within the same brand, the product register ("design serves the task")
+may apply per-surface. See [`docs/guidelines/design-modes.md`](../docs/guidelines/design-modes.md)
+for the full Brand-mode vs Product-mode discriminator.
+
 ## See also
 
 - [`brand-consistency`](brand-consistency.md) — validates emitted artifacts against the authoritative brand profile this rule establishes.
 - [`brand`](../skills/brand/SKILL.md) — the gap-fill corpus this rule subordinates to consumer brand.
+- [`docs/guidelines/design-modes.md`](../docs/guidelines/design-modes.md) — brand vs product register discriminator and routing.

package/dist/agent-src/rules/delegation-policy.md

@@ -80,5 +80,6 @@ primitive → run in-session (clean no-op).
 ## See also
 
 - [`subagent-orchestration`](../skills/subagent-orchestration/SKILL.md) — the 7 modes this selects.
+- [`subagent-boundary`](../docs/contracts/subagent-boundary.md) — what a subagent owns vs never owns (task-meaning, memory, pack-surface, safety-floor bypass).
 - [`auto-orchestration-activation`](../contexts/execution/auto-orchestration-activation.md) — the gate.
 - [`reasoning-orchestrator`](../skills/reasoning-orchestrator/SKILL.md) — RDP dispatch, now gated here.

package/dist/agent-src/rules/legal-safety-floor.md

@@ -24,9 +24,9 @@ routes_to:
   - "skill:dpa-review"
   - "skill:legal-intake-triage"
 workspaces:
-  - legal
+  - legal-review-prep
 packs:
-  - legal
+  - legal-review-prep
 trust:
   level: advisory
   human_review_required: true
@@ -36,7 +36,7 @@ trust:
 
 # Legal Safety Floor
 
-Domain safety floor for legal-pack artefacts (contract/NDA/DPA review, legal triage). Auto-activates when `pack-legal` is installed. Sibling to `finance-safety-floor` / `strategy-safety-floor`. Every output is a **draft for attorney review**, never legal advice.
+Domain safety floor for the `legal-review-prep` pack (contract/NDA/DPA review, legal triage). Auto-activates when `pack-legal-review-prep` is installed. Sibling to `finance-safety-floor` / `strategy-safety-floor`. Every output is a **draft to PREPARE for attorney review**, never legal advice.
 
 ## Iron Law — no final legal call
 
@@ -56,6 +56,29 @@ THEY DO NOT REPLACE A LICENSED ATTORNEY. NO ONE MAY RELY ON THEM AS DEFINITIVE.
 
 Every output is a **draft / research aid for a human attorney to verify** — for first-pass review, issue-spotting, and drafts only. It is **not** legal advice, **not** a legal opinion, and **not** a substitute for a qualified lawyer in the relevant jurisdiction. Nobody should rely on it for a binding decision; treat it as a tool that makes attorney review faster, never as the review itself. This disclaimer is non-removable from the pack. See [`LEGAL_NOTICE.md`](../../LEGAL_NOTICE.md).
 
+## Consent gate — refuse until acknowledged
+
+```
+NO legal-review-prep SKILL RUNS UNTIL legal_review_prep.acknowledged: true.
+FAIL-CLOSED: NO ACKNOWLEDGMENT → REFUSE, POINT TO THE SETUP WIZARD.
+```
+
+Before any legal-review-prep skill produces output, read `legal_review_prep.acknowledged` from `.agent-settings.yml`. Missing / `false` → refuse and surface: *"The legal-review-prep pack is inactive until you acknowledge it is not legal advice. Run the setup wizard's legal-consent step, or set `legal_review_prep.acknowledged: true` in `.agent-settings.yml`."* This is active consent (set via the wizard checkbox), not a passive disclaimer — it manages reliance/expectation and host-ToS exposure; it does **not** cure RDG.
+
+## Iron Law — legal work-product is council / deep-research gated
+
+```
+WHEN legal_review_prep.require_council IS TRUE (DEFAULT), A LEGAL WORK-PRODUCT
+IS PRODUCED VIA A MULTI-MODEL COUNCIL / research:deep PASS — NEVER SINGLE-MODEL.
+FAIL-CLOSED: NO COUNCIL CONFIGURED → REFUSE. NO INFRA → NO OUTPUT, NOT BAD OUTPUT.
+```
+
+A **work-product** = a review, redline, gap-frame, or demand draft (not a one-line definition or a general-concept explanation). Every legal-review-prep skill carries `council_depth: deep`; when consulted it routes through the AI council (`--depth deep`) or `research:deep`. Single-model legal work-product is refused while `require_council: true`. When no council is configured, **fail closed** — refuse and say so; an unreviewed single-model legal draft is the worse outcome for a high-risk pack.
+
+**Honest enforcement boundary.** This is advisory + settings + lint enforcement, not a hard runtime hook — skills are prose the host reads; the floor, the `require_council` flag, and the `lint_legal_pack` `council_depth` check are the teeth, the host is *asked* to route through the council. The deep council (2026-06-24) found this defense-in-depth substantive (documented multi-stage review + reliance-bounding friction + audit trail), **not** an RDG cure: it improves quality and creates a record; it does **not** make the output reliable legal advice.
+
+**Audit pointer.** When a council / deep-research pass runs for a legal work-product, persist its pointer (timestamp · members · artefact hash) under `agents/runtime/council/responses/` so the "documented multi-stage review" claim is real, not asserted. No pass, no work-product.
+
 ## Iron Law — general information only, never individual-case examination
 
 ```
@@ -69,7 +92,22 @@ The line (German RDG § 2(1); a disclaimer does **not** cure crossing it): a reg
 - **Definitive individual application** — "this violates GDPR in your case", "you must terminate within 30 days".
 - **Dispute-specific drafting** — "draft the warning letter for *my* dispute with X", "write my response to this cease-and-desist".
 
-On a refusal, respond in shape: *"I can explain [general concept] and provide a general template, but I cannot determine how it applies to your specific situation — that requires individual legal examination by a qualified lawyer. Jurisdiction: [EU/DE]. Attorney review required."* Err toward refusal when more than ~3 case-specific facts are needed to answer.
+This is a hard **STOP**, not a hedge — do not continue the individual-case analysis. When the request crosses into individual-case territory (specific facts about *your* situation, outcome prediction, deadline-driven or definitive-action questions — "may I terminate?", "will I win?", "is this enforceable in my case?"), emit the STOP block and end the individual-case answer:
+
+```
+🛑 I must stop here — this needs a lawyer.
+
+Your request involves individual legal examination, which I cannot provide.
+This is a regulatory boundary (German RDG § 2(1)), not a gap in knowledge.
+Find a qualified lawyer:
+- Rechtsanwaltskammer (German bar) attorney search — https://www.rechtsanwaltskammer.de
+- Beratungshilfe (legal aid) — https://www.bmj.de
+
+I can still explain the general concept and provide a general template —
+just not how it applies to your specific situation.
+```
+
+Err toward the STOP when more than ~3 case-specific facts are needed to answer. The general-information path (concept + template) stays available; the STOP only terminates the *individual-case* branch, never the whole interaction.
 
 ## No definitive legal language
 

package/dist/agent-src/rules/output-discipline.md

@@ -0,0 +1,85 @@
+---
+type: "auto"
+tier: "2a"
+description: "Prohibits placeholder-prose output in generated code and UI — no truncation shorthands; on budget overflow emit a clean PAUSED breakpoint instead"
+triggers:
+  - intent: "generating code or multi-section output"
+  - keyword: "// rest of component"
+  - keyword: "for brevity"
+  - keyword: "rest follows the same pattern"
+  - phrase: "similar pattern"
+workspaces:
+  - engineering
+packs:
+  - engineering-base
+---
+
+# Output Discipline
+
+## Iron Law — no placeholder prose in emitted code
+
+```
+NEVER EMIT PLACEHOLDER PROSE IN GENERATED CODE OR UI.
+PLACEHOLDER PROSE IS INCOMPLETE OUTPUT, NOT A STYLE CHOICE.
+ON BUDGET OVERFLOW: EMIT A CLEAN PAUSED MARKER. NEVER TRUNCATE SILENTLY.
+```
+
+## Banned placeholder patterns
+
+The following patterns are **absolutely banned** in generated code, components,
+templates, and UI markup. They signal "I gave up midway" and leave the codebase
+in a broken state:
+
+| Banned pattern | What to do instead |
+|---|---|
+| `// rest of component` | Write the rest of the component. If budget runs out, emit `[PAUSED]` marker |
+| `// ... (unchanged)` | Emit the unchanged code or omit it from the diff with a clean explanation of what was NOT changed |
+| `// TODO: implement` | Implement it. If genuinely deferred, name the deferral explicitly in the brief, not in the code |
+| `/* similar pattern */` | Write the similar pattern in full |
+| `"for brevity"` in code comments | There is no brevity in broken code |
+| `// rest follows same pattern` | Follow the same pattern — write it |
+| `...` / `…` as an ellipsis replacing code content | Write the content |
+| `[Your component here]` / `<YourComponentName>` | Use the actual component name or write the component |
+| `Lorem ipsum` / `dolor sit amet` in UI output intended for review | Use realistic placeholder content or ask for content |
+
+The banned patterns above are also detected by `lint_output_slop.ts` (see
+`src/scripts/lint_output_slop.ts`) — violations cause a CI exit-code-2.
+
+## On budget overflow — PAUSED protocol
+
+When output genuinely reaches a context budget limit mid-generation:
+
+1. Complete the current logical unit (function body, component, section).
+2. Emit a clean breakpoint marker on its own line:
+   ```
+   [PAUSED — section X of Y complete. Continue prompt: "continue from <last-completed-unit>"]
+   ```
+3. Stop. Do **not** truncate with `// rest follows...` or `...`.
+
+The user will prompt "continue" and the next turn resumes cleanly from the
+named unit.
+
+## Interaction with `verify-before-complete`
+
+`verify-before-complete` requires fresh verification before claiming work is
+done. `output-discipline` adds the pre-condition: **there must be nothing to
+verify that was never written**. A component with `// rest of component` is
+not a complete artifact — it cannot be verified, it cannot be committed.
+
+## Inline-ignore escape (for legitimate edge cases)
+
+In the rare case where a pattern above is intentional (e.g., a documentation
+example showing what NOT to do), use the inline-ignore escape:
+
+```javascript
+// lint-output-slop-disable-next-line impl-placeholder -- showing a negative example in documentation
+// rest of component
+```
+
+Or for a whole file: `// lint-output-slop-disable-file impl-placeholder -- test fixture`
+
+## See also
+
+- `verify-before-complete` — no completion claim without evidence
+- `downstream-changes` — every edit is incomplete until all callers are updated
+- `src/scripts/lint_output_slop.ts` — the CI linter enforcing this rule

package/dist/agent-src/rules/telegraph-speak.md

@@ -59,7 +59,7 @@ Post-rewrite validator runs on every reply when `speak_scope != off`:
 The rule documents the algorithm; agents apply it inline before
 sending. The mechanism is the rule, not a hidden script.
 
-Optional CI-side regression lock: [`scripts/validate_telegraph_carveouts.py`](../../scripts/validate_telegraph_carveouts.py) takes pre/post reply pair and asserts byte-identical preservation across all seven carve-out categories — runtime mechanism stays algorithmic; script is offline check.
+- Optional CI-side regression lock: [`scripts/validate_telegraph_carveouts.py`](../../scripts/validate_telegraph_carveouts.py) — pre/post reply pair, byte-identical preservation across all seven carve-out categories; runtime mechanism stays algorithmic, script is the offline check.
 
 ## Telegraph grammar
 
@@ -80,4 +80,7 @@ Example: *"I will now check the file and see if it exists"* →
 | `telegraph.speak` | `true` | Compile-time include in `dist/router.json`. |
 | `telegraph.speak_scope` | `prose_only` | Runtime scope of telegraph grammar. |
 
+- Input-side memory condensation (shrinking always-loaded memory files like `AGENTS.md` / `CLAUDE.md` / `.cursorrules` rather than the reply stream) runs independently of `speak_scope` — see [`condense-memory`](../skills/condense-memory/SKILL.md) for the script wrapper, sensitive-path refusal contract, and `.original.md` round-trip.
+- Skills marked `token_budget_class: rich` are **exempt** from telegraph condensation + thin-projector trimming (gated by `tokens.rich_skills`, default `on`) — full model in [`token-budget-discipline`](token-budget-discipline.md).
+
 Cross-rule index: [`frugality-charter § cross-references`](../contexts/contracts/frugality-charter.md#cross-references--frugality-canon-rules).

package/dist/agent-src/rules/token-budget-discipline.md

@@ -0,0 +1,94 @@
+---
+type: "auto"
+tier: "2a"
+description: "Governs token_budget_class: rich skills — exempt them from telegraph-speak + thin-projector trimming; enforce the 15% cap + justification requirement"
+triggers:
+  - keyword: "token_budget_class"
+  - keyword: "rich skill"
+  - intent: "editing a rich-tagged skill"
+workspaces:
+  - agent-config-maintainer
+packs:
+  - meta
+---
+
+# Token Budget Discipline
+
+## Iron Law — rich skills load in full, lean skills compress
+
+```
+SKILLS MARKED token_budget_class: rich ARE INTENTIONALLY DETAILED.
+LOAD THEM FULLY. DO NOT CONDENSE, SUMMARIZE, OR TRIM THEM.
+THEIR LENGTH IS A DELIBERATE QUALITY INVESTMENT, NOT BLOAT.
+SKILLS WITHOUT THE KEY, OR MARKED lean/standard, REMAIN SUBJECT
+TO THE FULL FRUGALITY CANON (telegraph-speak, thin-projector).
+```
+
+## The three classes
+
+| Class | Default? | Telegraph-speak | Thin-projector trimming | Target size |
+|---|---|---|---|---|
+| `lean` | No explicit key = lean | Full condensation | May be trimmed | < 500 tokens |
+| `standard` | — | Balanced condensation | Not trimmed if priority ≥ 60 | 500–2000 tokens |
+| `rich` | Must be declared + justified | **Exempt** | **Never trimmed** | 2000–5000 tokens |
+
+Read `tokens.rich_skills` from `.agent-settings.yml` (default `on`) to determine
+whether rich skills may load in full. If `off`, treat them as
+`standard`. If `ask`, surface the estimated token delta (≈ skill file size in
+chars / 4) and wait for user confirmation; cache the answer for the session.
+
+## Requirements for `token_budget_class: rich`
+
+A skill claiming `rich` MUST satisfy ALL three:
+
+1. **`## Why this skill is rich` section** — explains in 2-5 sentences the
+   irreducible complexity that makes condensation harmful (e.g. "agents need to
+   see 6 worked examples to pattern-match the modular scale; condensing to the
+   rule alone produces agents that invent arbitrary sizes"). The linter
+   (`lint_token_budget_discipline.ts`) fails the skill if this section is absent.
+
+2. **Not already coverable by a reference link** — if the richness is entirely
+   in an external document the agent can fetch, the skill should load lean and
+   carry a `load_context` pointer instead.
+
+3. **≤ 15 % of the suite's skills may claim `rich`** — the CI linter counts
+   rich-tagged skills and hard-fails if the ratio is exceeded. With ~230 skills, the
+   cap is ~35. Do not claim `rich` for convenience; claim it only for
+   irreducible-complexity skills.
+
+## Telegraph-speak amendment
+
+The `telegraph-speak` rule (Tier 1, always-on) **exempts** skills marked
+`token_budget_class: rich`. When such a skill is active:
+
+- Do not apply telegraph-speak condensation to its guidance prose
+- Do not drop articles, linking auxiliaries, or extended examples
+- Do not compress multi-paragraph explanations into fragments
+- Preserve all worked examples, decision tables, and code blocks verbatim
+
+This exemption is limited to the skill's guidance content; reply prose from the
+*agent* (not from the skill body) remains subject to telegraph-speak unless the
+user has set `telegraph.speak_scope: off`.
+
+## Candidate rich skills (justified, not exhaustive)
+
+These skills are approved `rich` by this roadmap's council:
+
+| Skill | Justification summary |
+|---|---|
+| `design-intelligence` | 11 corpus CSVs + 16 design-language prose specs + a 10-category checklist; grounded selection needs the full reference to avoid random corpus subsets |
+| `typography-system` | Modular-scale math + 6 worked example type systems; condensing to "use 1.25 ratio" produces agents that invent arbitrary px values |
+| `accessibility-auditor` | WCAG criteria are non-negotiable detail; every criterion has a testable condition + failure mode; compression loses the test procedures |
+| `design-system-capture` (Phase 6) | Writes + maintains DESIGN.md + PRODUCT.md; needs full templates + worked examples to generate useful artifacts |
+
+## Governed by
+
+- `tokens.rich_skills` setting in `.agent-settings.yml` (consumer override)
+- `lint_token_budget_discipline.ts` (cap + justification CI check)
+- `telegraph-speak.md` (amended to except rich-tagged skills)
+
+## See also
+
+- `token_budget_class` key in `src/scripts/schemas/skill.schema.json`
+- `tokens.rich_skills` in `src/config/agent-settings.template.yml`
+- `telegraph-speak` rule — the frugality canon this rule amends

package/dist/agent-src/skills/accessibility-auditor/SKILL.md

@@ -9,6 +9,7 @@ workspaces:
   - engineering
 packs:
   - engineering-base
+token_budget_class: rich
 ---
 
 # accessibility-auditor
@@ -53,11 +54,12 @@ gets a verdict in step 5; missing one is a coverage failure.
 **Perceivable** — text alternatives for non-text (`alt`, `aria-label`),
 contrast ≥ 4.5:1 for body / 3:1 for large or UI components, no
 colour-only state ("error in red" must also be iconic or text).
-Grounded reference for palette + chart verdicts: corpus WCAG-adjusted
-token sets (`--domain color`), chart a11y grades + colorblind fallbacks
-(`--domain chart`), mobile touch/a11y rules (`--domain web`, 44pt) via
-[`design-intelligence`](../design-intelligence/SKILL.md) — cite the corpus
-row; WCAG 2.2 AA *method* stays this skill's checklists.
+Grounded reference for palette + chart verdicts: the adopted corpus's
+WCAG-adjusted token sets (`--domain color`), chart a11y grades +
+colorblind fallbacks (`--domain chart`), and mobile touch/a11y rules
+(`--domain web`, 44pt targets) via
+[`design-intelligence`](../design-intelligence/SKILL.md) — cite the
+corpus row; the WCAG 2.2 AA *method* stays this skill's own checklists.
 Widget-pattern selection (dialog, combobox, tabs, toast, table, form
 errors, drag-reorder …) grounds in the ARIA-APG corpus:
 `ground.py search --manifest
@@ -145,3 +147,16 @@ Top 3 fixes:  <ordered by user impact>
   jurisdictions.
 - Do NOT close a finding by adjusting the test instead of the UI;
   the user's experience is the ground truth, not the test report.
+
+## Why this skill is rich
+
+WCAG 2.2 AA compliance is non-negotiable detail — each success criterion
+has a specific testable condition, failure mode, and remediation path.
+The skill carries the full WCAG criterion matrix with concrete test
+procedures (not just "check contrast"), keyboard-navigation patterns
+(roving tabindex, trap management, escape-key handling), ARIA role/
+property/state tables, and screen-reader-specific edge cases per
+assistive technology. Condensing to "check contrast and add aria-labels"
+loses the test procedures that turn a vague finding into a reproducible
+failure with a specific remedy. Accessibility bugs that are described
+vaguely cannot be verified as fixed.

package/dist/agent-src/skills/blade-ui/SKILL.md

@@ -133,6 +133,15 @@ current state on the next polish round.
 - Do NOT put business logic in Blade templates — use Livewire or view composers.
 - Do NOT use inline styles — use Tailwind utility classes.
 
+## Anti-slop
+
+Before shipping a Blade view, pull
+[`docs/guidelines/design-antipatterns.md`](../../../docs/guidelines/design-antipatterns.md)
+and scan Visual / Typography / Layout — the Blade markup is where side-stripe
+accents (V1), icon-tile feature cards (T3), and the centered-hero + 3-column
+template (L1/L2) concretely land. Stack-specific Tailwind class/hex bans live in
+[`tailwind-engineer`](../tailwind-engineer/SKILL.md).
+
 ## Auto-trigger keywords
 
 - Blade template

package/dist/agent-src/skills/bug-analyzer/evals/evals.json

@@ -0,0 +1,13 @@
+{
+  "skill": "bug-analyzer",
+  "_calibration": "Starter behavioral fixtures (roadmap road-to-operator-runtime-harvest, Phase 1, line 182). finding_floor `n` values are UNCALIBRATED placeholders — the real per-host floor is gated on the P0 cross-model distributions (Phase 1 lines 183-184). Do not wire these as an enforcing CI gate until calibrated.",
+  "scenarios": [
+    {
+      "id": "stacktrace-root-cause-findings",
+      "prompt": "Analyze this failure and list each candidate cause as its own bullet point:\n```\nTypeError: Cannot read properties of undefined (reading 'id')\n  at resolveUser (auth.ts:42)\n  at middleware (auth.ts:11)\n```\nContext: intermittent; only on requests without a session cookie.",
+      "assertions": [
+        { "kind": "finding_floor", "n": 2, "pattern": "(?m)^\\s*[-*+]\\s+" }
+      ]
+    }
+  ]
+}

package/dist/agent-src/skills/code-review/evals/evals.json

@@ -0,0 +1,21 @@
+{
+  "skill": "code-review",
+  "_calibration": "Starter behavioral fixtures (roadmap road-to-operator-runtime-harvest, Phase 1, line 182). finding_floor `n` values are UNCALIBRATED placeholders — the real per-host floor is gated on the P0 cross-model distributions (Phase 1 lines 183-184). Do not wire these as an enforcing CI gate until calibrated.",
+  "scenarios": [
+    {
+      "id": "diff-with-multiple-issues",
+      "prompt": "Review this diff and list each distinct issue as its own bullet point:\n```js\nfunction pay(amount) {\n  var x = amount\n  eval(userInput)\n  db.query('SELECT * FROM users WHERE id = ' + req.params.id)\n  return x\n}\n```",
+      "assertions": [
+        { "kind": "finding_floor", "n": 2 },
+        { "kind": "contains", "value": "eval" }
+      ]
+    },
+    {
+      "id": "clean-diff-few-findings",
+      "prompt": "Review this diff and list each distinct issue as its own bullet point:\n```js\nexport function add(a: number, b: number): number {\n  return a + b\n}\n```",
+      "assertions": [
+        { "kind": "finding_floor", "n": 0 }
+      ]
+    }
+  ]
+}

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

@@ -4,12 +4,13 @@ name: contract-review
 description: "Use when reviewing a contract clause-by-clause from your party's side — buyer/seller/vendor/licensee. Triggers on 'review this contract', 'redline this MSA', 'is this clause a problem'."
 status: active
 tier: senior
+council_depth: deep
 domain: process
 recommended_for_user_types: [legal]
 workspaces:
-  - legal
+  - legal-review-prep
 packs:
-  - legal
+  - legal-review-prep
 trust:
   level: advisory
 install:

package/dist/agent-src/skills/dashboard-design/SKILL.md

@@ -23,11 +23,17 @@ Do NOT use when:
 
 ## Procedure: Design a dashboard
 
-Ground chart-type choice in the adopted data-viz corpus, not memory:
-`ground.py search --manifest <skills-root>/design-intelligence/data/manifest.json
---domain chart "<data shape>"` → best chart type, when-NOT-to-use, volume
-threshold, a11y grade + colorblind fallback, library recommendation
-([`design-intelligence`](../design-intelligence/SKILL.md)).
+1. **Inspect the data sources** — Identify which signals already exist (logs, metrics, app queries) and where they live (Grafana / Loki / app DB) before designing a new panel.
+2. **Pick the surface** — Use the decision tables below to choose Grafana, app dashboard, or embed; document audience and refresh cadence.
+3. **Draft the layout** — Sketch panels, choose visualization per signal (RED / USE / Golden Signals), define filters and thresholds.
+   **Ground the chart-type choice** in the adopted data-viz corpus instead
+   of memory: `ground.py search --manifest
+   <skills-root>/design-intelligence/data/manifest.json --domain chart
+   "<data shape>"` returns the best chart type, when-NOT-to-use, data-volume
+   threshold, a11y grade + colorblind fallback, and a library
+   recommendation per row (see
+   [`design-intelligence`](../design-intelligence/SKILL.md)).
+4. **Implement and verify** — Build the dashboard, load realistic data, and confirm every panel answers a named question for the named audience.
 
 | Domain | Technology | Purpose |
 |---|---|---|
@@ -120,6 +126,16 @@ Config required: `allow_embedding = true`, `cookie_samesite = none` (cross-origi
 - Do NOT mix ops metrics with business KPIs on the same dashboard.
 - Do NOT show admin data without tenant scoping.
 
+## Anti-slop
+
+Dashboards have their own signature tell: the **hero-metric template** (giant
+number + small label + a row of stats + gradient) is L1 in
+[`docs/guidelines/design-antipatterns.md`](../../../docs/guidelines/design-antipatterns.md).
+Pull the catalog and check L1–L3 (hero-metric, identical-card grids, monotonous
+spacing) before finalizing the layout — a dashboard is product-mode
+(`docs/guidelines/design-modes.md`): design serves the task, so favour data
+density and earned familiarity over decorative variance.
+
 ## Auto-trigger keywords
 
 - dashboard