@event4u/agent-config 7.0.2 → 7.2.0

package/dist/ui/index.html

@@ -5,7 +5,7 @@
         <meta name="viewport" content="width=device-width, initial-scale=1" />
         <meta name="robots" content="noindex" />
         <title>agent-config</title>
-      <script type="module" crossorigin src="/assets/index-CoQo90sz.js"></script>
+      <script type="module" crossorigin src="/assets/index-UjcTG_9O.js"></script>
       <link rel="stylesheet" crossorigin href="/assets/index-BbWWuFrF.css">
     </head>
     <body>

package/docs/RELEASE_STORY_TEMPLATE.md

@@ -0,0 +1,37 @@
+# Release Story — `<version>`
+
+A curated, human-readable "what changed and **why it matters**" — distinct from
+the raw `CHANGELOG`. The changelog lists commits; the release story tells a
+maintainer or consumer, in plain language, what they get and what to watch.
+
+Copy this template per release; keep it short (a screen or less).
+
+## Headline
+
+One sentence: the single most important thing this release delivers.
+
+## What changed (and why it matters)
+
+- **<change>** — what it is · why a consumer cares · what they should do (if anything).
+- **<change>** — …
+
+## Safety / behaviour changes
+
+Anything that changes agent behaviour, gates, or defaults — call it out explicitly
+(new floors, new consent gates, renamed packs, changed risk postures). Consumers
+read this section first.
+
+## Upgrade notes
+
+- Breaking? Migration steps. Non-breaking? Say so.
+- New opt-in surfaces (packs, settings) — how to enable.
+
+## Deferred / known limitations
+
+What was intentionally left for a future release, and the pointer (roadmap /
+ADR). Honesty here prevents "is this missing or coming?" questions.
+
+---
+
+> Fill every section. An empty section is a signal the release is not understood
+> well enough to ship its story. (road-to-product-clarity Phase 4a.)

package/docs/architecture.md

@@ -146,10 +146,10 @@ note, package-internal path-swap, description budget, and the
 
 | Layer | Count | Purpose |
 |---|---|---|
-| **Skills** | 251 | On-demand expertise — stack analysis (Laravel · Symfony · Zend / Laminas · Next.js · React · Node), testing, Docker, API design, security, observability, … |
-| **Rules** | 88 | Always-active constraints — coding standards, scope control, verification, language-and-tone, agent-authority |
-| **Commands** | 161 | Slash-command workflows — `/commit`, `/create-pr`, `/fix ci`, `/optimize skills`, `/feature plan`, `/work`, `/implement-ticket`, `/condense`, … |
-| **Guidelines** | 82 | Reference material cited by skills — PHP patterns, Eloquent, Playwright, agent-infra, … |
+| **Skills** | 258 | On-demand expertise — stack analysis (Laravel · Symfony · Zend / Laminas · Next.js · React · Node), testing, Docker, API design, security, observability, … |
+| **Rules** | 93 | Always-active constraints — coding standards, scope control, verification, language-and-tone, agent-authority |
+| **Commands** | 162 | Slash-command workflows — `/commit`, `/create-pr`, `/fix ci`, `/optimize skills`, `/feature plan`, `/work`, `/implement-ticket`, `/condense`, … |
+| **Guidelines** | 86 | Reference material cited by skills — PHP patterns, Eloquent, Playwright, agent-infra, … |
 | **Templates** | 7 | Scaffolds for features, roadmaps, contexts, skills, overrides |
 | **Contexts** | 5 | Shared knowledge about the system itself |
 

package/docs/benchmark.md

@@ -73,3 +73,49 @@
 - Arms: vanilla (plugin off) · package (real plugin) · package-rdp (plugin + RDP rules) · placebo (plugin off + equal-length inert prose).
 - Corpus: `internal/bench/corpora/ab-trackb-v2.yaml` (5 trap archetypes). Scoring: `bench_ab_scoring_v2.py` (deterministic, no LLM judge).
 - Roadmap: `agents/roadmaps/road-to-discipline-axis-benchmark.md`.
+
+## Recursive self-verification (ADR-106) — HONEST-NULL
+
+> **Verdict: recursion is redundant with the always-on rules. `verification.recursive`
+> stays `off`. No model got "closer to Fable" — exactly what ADR-106's gate was built to
+> disconfirm.** The one retraining-free Sakana-Fugu mechanism (a depth-bounded
+> `attempt → critic verdict → re-attempt` loop) was built, shipped behind a gate, and
+> measured — and adds nothing over the rules.
+
+Measured the `package-recursive` arm (D₂ = rules + recursion, deterministic scorer-as-critic,
+`max_depth=1`) against `package` (D₁ = rules only) on a weak host (`claude-haiku-4-5`),
+`capH-debug` archetype × 6 seeds (n=54 paired):
+
+| axis | D₁ (rules) | D₂ (rules + recursion) | Δ (D₂ − D₁) | test |
+|---|---|---|---|---|
+| capability (pass-rate) | 87% | 87% | 0 | McNemar p=1.0, h=0.0 |
+| discipline (0–1) | 0.852 | 0.861 | +0.009 | Wilcoxon p=0.79, rb=0.33, n≠0=3 |
+
+**ADR-106 gate: FALSIFIED** — neither a capability lift (p=1.0) nor a *significant* novel
+discipline lift (p=0.79; only 3 discordant pairs, below the ≥6 the gate requires).
+
+**Why, despite a passing human pre-test.** Recursion fired on only **8/29** corpus tasks
+(~28%) and produced a differentiated output on **4/29** — with the rules active, the host's
+*first* attempt already passes the critic 72% of the time, so recursion is a no-op. A blind
+human pre-test on the 4 differentiated pairs preferred the recursion output **4/4**, but those
+cases are too rare and the aggregate marginal lift too small (n≠0=3) to register as
+significant. The pre-test looked positive on N=4; the paired benchmark falsified it — which is
+exactly why ADR-106 required the benchmark, not just the pre-test.
+
+**Honesty scope.** Weak host, `capH-debug` family, deterministic scorer-as-critic, `max_depth=1`.
+A model-based critic (Phase 4) was not pursued — gated on this result passing, which it did not.
+Cost axis: each recursion run is up to 2× the host calls of a single pass, for a null lift.
+
+- Roadmap: `agents/roadmaps/archive/road-to-recursive-verification.md` (closed honest-null).
+- Gate logic: `recursiveGateVerdict` / `resolveRecursiveDefault` (`orchestration_gate.ts`); on a
+  falsified gate `resolveRecursiveDefault` resolves `off` — no shipped-default flip.
+
+**Follow-up disposition — TERMINAL** (AI council, anthropic/claude-sonnet-4-5 +
+openai/gpt-4o, 2026-06-24, deep tier). Both members converged: do **not** pursue a
+model-critic / cross-vendor variant. The 72% first-pass rate shows recursion solves the
+wrong problem — cost scales with *all* tasks, benefit only on the ~28% tail (best-case
+~4–6% lift, would need n≥200 to detect); a model-critic would mostly fire more often and
+produce more null-lift re-attempts at higher cost. The real lever is **refining the rules
+on the 28% failure tail** (applies to 100% of tasks at zero marginal cost), not recursion.
+Recursion-as-a-class is closed; the model-critic's contextual-quality angle, if ever
+wanted, is a *different* (quality-review) product, not a recursion follow-up.

package/docs/catalog.md

@@ -1,13 +1,13 @@
 # agent-config — Public Catalog
 
-Consumer-facing catalog of all **581 public artefacts** shipped by
+Consumer-facing catalog of all **593 public artefacts** shipped by
 this package. Internal package-maintenance rules and deprecation shims
 are excluded.
 
-> **Regenerate:** `python3 scripts/generate_index.py`
+> **Regenerate:** `./scripts-run src/scripts/generate_index`
 > Auto-generated — do not edit manually.
 
-## Skills (251)
+## Skills (257)
 
 | kind | name | extra | description |
 |---|---|---|---|
@@ -57,6 +57,7 @@ are excluded.
 | skill | [`content-funnel-design`](../dist/agent-src/skills/content-funnel-design/SKILL.md) |  | Use when mapping funnel-stage to content shape — conversion-pathway, content-as-system, leverage-point selection. Triggers on 'design our content funnel', 'why does mid-funnel leak'. |
 | skill | [`context-authoring`](../dist/agent-src/skills/context-authoring/SKILL.md) |  | Use when filling in knowledge-layer context files — auth-model, tenant-boundaries, data-sensitivity, deployment-order, observability — interactive walkthrough that turns templates into reviewer fuel. |
 | skill | [`context-document`](../dist/agent-src/skills/context-document/SKILL.md) |  | Use when the user says \"create context\", \"document this area\", or wants a structured snapshot of a codebase area for agent orientation. |
+| skill | [`contract-review`](../dist/agent-src/skills/contract-review/SKILL.md) |  | 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'. |
 | skill | [`contracts-cognition`](../dist/agent-src/skills/contracts-cognition/SKILL.md) |  | Use when reading a contract for risk and constraint — clause shape, redline priority, what the contract actually binds. Triggers on 'review this contract', 'what does this MSA constrain'. |
 | skill | [`conventional-commits-writing`](../dist/agent-src/skills/conventional-commits-writing/SKILL.md) |  | Use when writing commit messages or squash-merge titles — `feat:`, `fix:`, `chore:`, scopes, breaking changes — even when the user just says 'commit this' without naming Conventional Commits. |
 | skill | [`copilot-agents-optimization`](../dist/agent-src/skills/copilot-agents-optimization/SKILL.md) |  | Use when optimizing AGENTS.md or copilot-instructions.md — deduplicates against .augment/ content, enforces line budgets, and focuses each file on its audience. |
@@ -83,6 +84,7 @@ are excluded.
 | skill | [`discovery-interview`](../dist/agent-src/skills/discovery-interview/SKILL.md) |  | Use when running discovery interviews — question-bank build, bias audit, insight extraction. Triggers on 'audit my guide', 'extract insights from transcript', 'is my hypothesis falsifiable'. |
 | skill | [`doc-coauthoring`](../dist/agent-src/skills/doc-coauthoring/SKILL.md) |  | Use when co-authoring a PRD, design doc, RFC, decision doc, or technical spec — 3-stage flow (context → section-by-section → reader-test) — even if the user just says 'help me write this spec'. |
 | skill | [`docker`](../dist/agent-src/skills/docker/SKILL.md) |  | Use when working with Docker — Dockerfile edits, docker-compose services, containers, or the dual-container (fast + Xdebug) setup — even when the user just says 'my container won't start'. |
+| skill | [`dpa-review`](../dist/agent-src/skills/dpa-review/SKILL.md) |  | Use when reviewing a DPA as controller or processor against GDPR Art. 28 — GREEN/YELLOW/RED gap frame, never a final call. Triggers on \"review this DPA\", \"check this DPA\". |
 | skill | [`editorial-calendar`](../dist/agent-src/skills/editorial-calendar/SKILL.md) |  | Use when shaping cadence — evergreen / campaign / reactive split, beat-mapping across channel stages, content-debt management. Triggers on 'plan our content cadence', 'what should we publish'. |
 | skill | [`eloquent`](../dist/agent-src/skills/eloquent/SKILL.md) |  | Use when writing Eloquent models, relationships, scopes, or queries via Model:: — 'fetch users with their orders'. NOT for PHPStan output, non-Eloquent services, or raw SQL questions. |
 | skill | [`emit-tickets`](../dist/agent-src/skills/emit-tickets/SKILL.md) |  | Use when materialising a roadmap into a ticket bundle — 'turn this roadmap into tickets', 'materialise tickets', 'mach Tickets aus der Roadmap', 'emit tickets for this plan'. |
@@ -135,6 +137,8 @@ are excluded.
 | skill | [`laravel-websocket`](../dist/agent-src/skills/laravel-websocket/SKILL.md) |  | Use when building Laravel real-time features — Broadcasting events, ShouldBroadcast, private/presence channels, Echo client. For non-Laravel WebSockets, use the stack-native skill. |
 | skill | [`launch-readiness`](../dist/agent-src/skills/launch-readiness/SKILL.md) |  | Use before merging a release-shaped PR — pre-merge checklist, rollout plan, rollback criteria, ops handoff. Triggers on 'ready to ship', 'launch checklist', 'rollout plan for X'. |
 | skill | [`learning-to-rule-or-skill`](../dist/agent-src/skills/learning-to-rule-or-skill/SKILL.md) |  | Use when a repeated learning, mistake, or successful pattern should be turned into a new rule or skill. Also use after completing a task to capture learnings from the work. |
+| skill | [`legal-intake-triage`](../dist/agent-src/skills/legal-intake-triage/SKILL.md) |  | Use when triaging the quick legal-question channel + intake; classifies and ROUTES, never reviews. Triggers on 'is this a legal problem', 'do we need a lawyer for this', 'quick legal question'. |
+| skill | [`legal-practice-profile`](../dist/agent-src/skills/legal-practice-profile/SKILL.md) |  | Use when setting up the legal pack — captures jurisdiction, role, escalation, and playbook into a plain-prose profile every legal skill reads. Triggers on \"set up legal\", \"legal profile\". |
 | skill | [`lint-skills`](../dist/agent-src/skills/lint-skills/SKILL.md) |  | Use when running the package's skill linter against all skills and rules to validate frontmatter, required sections, and execution metadata. |
 | skill | [`livewire`](../dist/agent-src/skills/livewire/SKILL.md) |  | Use when the project's frontend stack is Livewire — dispatched by `directives/ui/{apply,review,polish}.py`. Covers reactive state, events, lifecycle hooks, and component/view separation. |
 | skill | [`livewire-architect`](../dist/agent-src/skills/livewire-architect/SKILL.md) |  | Use when shaping a Livewire component before code — full-page vs partial, parent/child split, event flow, state-vs-props boundary, hydration cost — even on 'add this Livewire component'. |
@@ -154,6 +158,7 @@ are excluded.
 | skill | [`module-management`](../dist/agent-src/skills/module-management/SKILL.md) |  | Use when working within any module under `modules.root_paths` from `.agent-project-settings.yml` — Laravel HMVC, Symfony DDD-lite, Node monorepo, Python src/, Go internal/, or a custom path. |
 | skill | [`motion-choreographer`](../dist/agent-src/skills/motion-choreographer/SKILL.md) |  | Use when turning a locked still + blueprint into a provider-tuned motion prompt — camera, primary + secondary motion, physics, native-audio sync. Triggers 'motion prompt for Veo/Kling/Sora'. |
 | skill | [`multi-tenancy`](../dist/agent-src/skills/multi-tenancy/SKILL.md) |  | Use when working with the multi-tenant architecture — customer DB switching, FQDN routing, tenant isolation, or cross-tenant operations. |
+| skill | [`nda-triage`](../dist/agent-src/skills/nda-triage/SKILL.md) |  | Use when triaging an inbound NDA fast — GREEN/YELLOW/RED so only the hard ones reach a lawyer. Triggers on 'check this NDA', 'can we sign this NDA', 'is this NDA standard'. |
 | skill | [`nextjs-patterns`](../dist/agent-src/skills/nextjs-patterns/SKILL.md) |  | Writes Next.js App Router code — Server Components, Server Actions, RSC boundaries, route handlers, caching, and streaming — matching framework conventions and project architecture. |
 | skill | [`okr-tree-modeling`](../dist/agent-src/skills/okr-tree-modeling/SKILL.md) |  | Use when decomposing a company objective into team OKRs, auditing a draft OKR tree, or stress-testing an existing one for measurability and laddering. |
 | skill | [`onboarding-design`](../dist/agent-src/skills/onboarding-design/SKILL.md) |  | Use when designing customer onboarding — time-to-first-value, milestone design, friction audit, drop-off diagnosis. Triggers on 'fix onboarding', 'why do new accounts churn fast'. |
@@ -201,6 +206,7 @@ are excluded.
 | skill | [`readme-writing-package`](../dist/agent-src/skills/readme-writing-package/SKILL.md) |  | Use when creating or rewriting a README for a reusable package or library. Focus on installability, minimal usage example, compatibility, and developer onboarding. |
 | skill | [`reasoning-orchestrator`](../dist/agent-src/skills/reasoning-orchestrator/SKILL.md) |  | Use for multi-step / ambiguous / end-to-end work — refactor a whole module, drive a vague ticket to a verified result, plan+build+verify a migration; coordinates the reasoning chain across skills. |
 | skill | [`receiving-code-review`](../dist/agent-src/skills/receiving-code-review/SKILL.md) |  | Use when processing code review feedback (bot or human) before changing anything — triages, verifies, and pushes back with technical reasoning — even when the user just says 'fix the comments'. |
+| skill | [`recursive-verification`](../dist/agent-src/skills/recursive-verification/SKILL.md) |  | Use to run a depth-bounded self-correction loop (attempt → critic verdict → re-attempt) as a tunable test-time compute knob — a do-and-judge specialisation, default off, capability-gated. |
 | skill | [`refine-prompt`](../dist/agent-src/skills/refine-prompt/SKILL.md) |  | Reconstruct a free-form prompt into actionable AC + assumptions + confidence band before the engine plans — '/work \"…\"', 'baue X', 'ist der Prompt klar genug für die Engine?'. |
 | skill | [`refine-ticket`](../dist/agent-src/skills/refine-ticket/SKILL.md) |  | Refine a Jira/Linear ticket before planning — 'refine ticket', 'tighten AC on PROJ-123', 'ist das Ticket klar?' — rewritten ticket, Top-5 risks, persona voices, sub-skills orchestrated, close-prompt. |
 | skill | [`release-comms`](../dist/agent-src/skills/release-comms/SKILL.md) |  | Use when turning a shipped changelog into a release narrative — value-not-feature framing, audience-segmented surfaces, one source of truth. Triggers on 'announce the release', 'write changelog post'. |
@@ -263,7 +269,7 @@ 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'. |
 
-## Rules (87)
+## Rules (90)
 
 | kind | name | type | description |
 |---|---|---|---|
@@ -283,6 +289,8 @@ are excluded.
 | 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 |
 | rule | [`context-hygiene`](../dist/agent-src/rules/context-hygiene.md) | auto | Debugging, fixing errors, or long conversations — 3-failure stop rule, tool-loop detection, fresh-chat triggers |
 | rule | [`copilot-routing`](../dist/agent-src/rules/copilot-routing.md) | auto | Configuring GitHub Copilot — copilot-instructions.md, PR-review patterns, suggestion behavior — route to copilot-config |
+| rule | [`delegation-policy`](../dist/agent-src/rules/delegation-policy.md) | auto | Delegable multi-part work + auto-orchestration enabled — decompose, tier-size each slice, dispatch to subagents instead of doing it all in-session |
+| rule | [`design-fidelity`](../dist/agent-src/rules/design-fidelity.md) | auto | A provided prototype / mockup / design system is the run's spec — build it 1:1; never swap fonts, controls, components, or layout without confirmation. Strictness: design.fidelity_mode. |
 | rule | [`devcontainer-routing`](../dist/agent-src/rules/devcontainer-routing.md) | auto | Wiring DevContainers/Codespaces — devcontainer.json, images, VS Code features, port forwarding — route to the devcontainer skill |
 | rule | [`direct-answers`](../dist/agent-src/rules/direct-answers.md) | always | Always — direct, unembellished answers. No flattery, no invented facts (verify load-bearing claims, otherwise ask). Emojis only as functional markers. Brevity is the default. |
 | rule | [`docker-commands`](../dist/agent-src/rules/docker-commands.md) | auto | Running PHP inside Docker — artisan, composer, phpstan, rector, ecs, phpunit, tests, migrations, any CLI tool |
@@ -305,6 +313,7 @@ are excluded.
 | rule | [`language-and-tone`](../dist/agent-src/rules/language-and-tone.md) | always | Language and tone — informal German Du, English code comments, .md files always English |
 | rule | [`laravel-routing`](../dist/agent-src/rules/laravel-routing.md) | auto | Writing/reviewing Laravel code — controllers, Eloquent, Artisan, jobs, events, policies — route to laravel skill |
 | rule | [`laravel-translations`](../dist/agent-src/rules/laravel-translations.md) | auto | Laravel language files, translations, i18n, lang/de, lang/en, __() helper, localization |
+| rule | [`legal-safety-floor`](../dist/agent-src/rules/legal-safety-floor.md) | auto | Legal-pack output (contract/NDA/DPA review, triage) — never a final legal call; role-conditional header + attorney-review line; EU/DE-only hard refusal; machine-checkable Jurisdiction tag |
 | rule | [`lethal-trifecta-guard`](../dist/agent-src/rules/lethal-trifecta-guard.md) | auto | Authoring a skill/command/tool that mixes private-data access + untrusted-content ingestion + external comms — break one leg of the lethal trifecta before shipping |
 | rule | [`linked-projects-onboarding-gate`](../dist/agent-src/rules/linked-projects-onboarding-gate.md) | auto | IDE-attached sibling repo detected — prompt once to opt it into proactive cross-repo awareness, persist local-only, then surface cross-repo impact on relevant changes |
 | rule | [`low-impact-corpus-privacy-floor`](../dist/agent-src/rules/low-impact-corpus-privacy-floor.md) | auto | Writing/editing/upstreaming entries in agents/decisions/low-impact-decisions.md — non-bypassable privacy floor for the learning corpus |
@@ -355,7 +364,7 @@ are excluded.
 | rule | [`user-interrupt-priority`](../dist/agent-src/rules/user-interrupt-priority.md) | always | User interrupts override the current task — STOP, complete new task in full, then ASK before resuming; never silently return to prior work |
 | rule | [`verify-before-complete`](../dist/agent-src/rules/verify-before-complete.md) | always | Verify before completion — run tests and quality tools before claiming done |
 
-## Commands (161)
+## Commands (162)
 
 | kind | name | cluster | description |
 |---|---|---|---|
@@ -420,6 +429,7 @@ are excluded.
 | command | [`feature-roadmap`](../dist/agent-src/commands/feature/roadmap.md) | cluster: feature | Generate implementation roadmap(s) from a feature plan and link them |
 | command | [`fix`](../dist/agent-src/commands/fix.md) | cluster: fix | Fix orchestrator — routes to ci, references, portability, seeder, pr-comments |
 | command | [`fix-ci`](../dist/agent-src/commands/fix/ci.md) | cluster: fix | Fetch CI errors from GitHub Actions and fix them |
+| command | [`fix-comments`](../dist/agent-src/commands/fix/comments.md) | cluster: fix | Review the code comments touched by the current branch and simplify, shorten, or remove each one |
 | command | [`fix-portability`](../dist/agent-src/commands/fix/portability.md) | cluster: fix | Find and fix project-specific references in shared .augment/ package files |
 | command | [`fix-pr-comments`](../dist/agent-src/commands/fix/pr-comments.md) | cluster: fix | Fix and reply to all open review comments (bots + human reviewers) on a GitHub PR |
 | command | [`fix-refs`](../dist/agent-src/commands/fix/refs.md) | cluster: fix | Find and fix broken cross-references in .augment/ and agents/ files |
@@ -521,7 +531,7 @@ are excluded.
 | command | [`video-storyboard`](../dist/agent-src/commands/video/storyboard.md) | cluster: video | Image-only storyboard — script → scenes → blueprint → image render → contact-sheet PNG via ffmpeg montage. No video calls. |
 | command | [`work`](../dist/agent-src/commands/work.md) |  | Drive a free-form prompt end-to-end through refine → score → plan → implement → test → verify → report — Option-A loop over the `work_engine` Python engine, confidence-band gated, no auto-git. |
 
-## Guidelines (82)
+## Guidelines (84)
 
 | kind | name | category | description |
 |---|---|---|---|
@@ -536,6 +546,8 @@ are excluded.
 | guideline | [`critical-thinking`](../docs/guidelines/agent-infra/critical-thinking.md) | agent-infra |  |
 | guideline | [`developer-judgment`](../docs/guidelines/agent-infra/developer-judgment.md) | agent-infra |  |
 | guideline | [`direct-answers-demos`](../docs/guidelines/agent-infra/direct-answers-demos.md) | agent-infra |  |
+| guideline | [`domain-eval-anti-pattern`](../docs/guidelines/agent-infra/domain-eval-anti-pattern.md) | agent-infra |  |
+| guideline | [`domain-pack-architecture`](../docs/guidelines/agent-infra/domain-pack-architecture.md) | agent-infra |  |
 | guideline | [`engineering-memory-data-format`](../docs/guidelines/agent-infra/engineering-memory-data-format.md) | agent-infra |  |
 | guideline | [`failure-signatures`](../docs/guidelines/agent-infra/failure-signatures.md) | agent-infra |  |
 | guideline | [`first-principles`](../docs/guidelines/agent-infra/first-principles.md) | agent-infra |  |

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`.
 
-**148 commands** across **10 surfaces** (4 user-work flows + 6 platform/domain surfaces).
+**154 commands** across **10 surfaces** (4 user-work flows + 6 platform/domain surfaces).
 
 ## User-work flows
 
@@ -205,6 +205,12 @@ _AI image + video pipeline._
 
 _Ghostwriter + post-as voice pipeline._
 
+- `brand` — Brand-as-UX orchestrator — strategy, identity, tokens, review, voice. Routes to the brand-grounding skills…
+- `brand-identity` — Define the brand identity — logo direction, colour story, type story, imagery direction — and the token con…
+- `brand-review` — Audit emitted UI, copy, and assets against the active brand tokens and voice profile — flag any value not t…
+- `brand-strategy` — Define brand positioning, archetype, voice, tone, and messaging over the brand-grounding corpus — the strat…
+- `brand-tokens` — Derive a DTCG .tokens.json source of truth from brand decisions, then emit CSS vars + Tailwind via the no-N…
+- `brand-voice` — Define the brand voice-and-tone profile — register, do/don't lexicon, and tone shifts by context — the prof…
 - `ghostwriter` — Ghostwriter cluster — fetch, write, list, show, and delete public-figure voice profiles (the third voice pr…
 - `ghostwriter-delete` — Hard-delete a ghostwriter profile at agents/reference/ghostwriter/<slug>.md after a two-step confirmation.…
 - `ghostwriter-fetch` — Build or refresh a public-figure voice profile under agents/reference/ghostwriter/ from a URL or bare name;…

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

@@ -33,23 +33,30 @@ fallback during the v2.4 namespace transition). This is where a single
 developer enables members, pins models, and sets caps once — and the
 council then works in **every** project they open, with no per-project
 file to check in or accidentally commit. See
-[ADR-093](../decisions/ADR-093-ai-council-config-user-global.md).
+[ADR-093](../decisions/ADR-093-ai-council-config-user-global.md) and
+[ADR-104](../decisions/ADR-104-ai-council-config-global-only.md).
 
-`scripts/ai_council/config.py:resolve_config_path` resolves the active
-file with this precedence (first match wins):
+**The council config is ALWAYS user-global. The project tree is NEVER
+searched for it.** `scripts/ai_council/config.ts:resolve_config_path`
+resolves the active file with this precedence (first match wins):
 
 1. **`$AI_COUNCIL_CONFIG`** — an explicit absolute path. Honoured even
    when the target is absent (so a typo surfaces as "create it here"
    rather than silently falling back). Primarily for tests / power users.
-2. **Project-local** `<project_root>/agents/settings/.ai-council.yml` —
-   only when a consumer project deliberately checks in its own council
-   config. This **overrides** the user-global file for that project.
-3. **User-global** `~/.event4u/agent-config/settings/.ai-council.yml` — the
+   This is an explicit path, not a project search.
+2. **User-global** `~/.event4u/agent-config/settings/.ai-council.yml` — the
    canonical default described above.
 
-When none exists, the loader reports the user-global path as the place to
-create it. `agents/templates/.ai-council.yml.example` ships the documented
-shape to copy from. The legacy `ai_council.*` block under
+There is **no project-local lookup.** A `<project_root>/agents/settings/.ai-council.yml`
+in any project (including this package's own tree) is ignored — the
+council never reads it (ADR-104, superseding the project-local override
+ADR-093 had kept). The absence of a council file *in a project* therefore
+says **nothing** about whether the council is configured; only the
+user-global file (or the `$AI_COUNCIL_CONFIG` override) decides that.
+
+When neither exists, the loader reports the user-global path as the place
+to create it. `agents/templates/.ai-council.yml.example` ships the
+documented shape to copy from. The legacy `ai_council.*` block under
 `.agent-settings.yml` remains removed (Phase 0 Step 5); a one-line
 breadcrumb there points at this contract.
 

package/docs/contracts/audit-log-v1.md

@@ -87,6 +87,13 @@ Single-line. The pretty-printed reference shape:
 Unknown trailing fields are forward-compat extensions; readers MUST
 NOT raise on them.
 
+A line MAY carry an optional `orchestration` object when the run was
+produced by the auto-dispatch orchestration layer. It is additive and
+non-breaking — `schema_version` is unchanged, no existing field is
+removed or renamed, and readers that do not understand it ignore it per
+the forward-compat rule above. Its shape lives in
+[`orchestration-telemetry.md`](../../src/agent-src/contexts/execution/orchestration-telemetry.md).
+
 ## Privacy floor
 
 Lines MUST NOT contain:

package/docs/contracts/auto-orchestration-v1.md

@@ -0,0 +1,70 @@
+---
+stability: beta
+keep-beta-until: 2026-09-23
+---
+
+# Auto-Orchestration v1
+
+**Purpose.** Pin the data shapes the automatic subagent-orchestration layer
+depends on — the host-capability manifest, the spawn brief, and the
+orchestration telemetry object — so producers and consumers agree without
+re-deriving them. Behaviour (when to dispatch, how to route, how to verify)
+lives in the context docs; this contract pins the **shapes**.
+
+**Scope.** The three JSON shapes below + the activation precondition. Does not
+define classification rules, routing policy, or the verification budget — those
+are the cited context docs.
+
+Last refreshed: 2026-06-23. Decided in
+[ADR-105](../decisions/ADR-105-automatic-subagent-orchestration.md).
+
+## Host-capability manifest
+
+Resolved once per session, cached. Safe default = all-false.
+
+```json
+{ "schema_version": 1, "subagent_spawn": false, "parallel_spawn": false, "status_polling": false, "separate_quota_pool": false }
+```
+
+Full semantics: [`host-capability-manifest`](../../src/agent-src/contexts/execution/host-capability-manifest.md).
+
+## Spawn brief
+
+Composed per delegated sub-task; knowledge is references only, capped.
+
+```json
+{ "task": "<sub-task>", "role_mode": "reviewer|null", "profile": "<id|null>", "personas": ["<id>"], "knowledge_refs": ["<id-or-path>"] }
+```
+
+Full semantics: [`subagent-spawn-contract`](../../src/agent-src/contexts/execution/subagent-spawn-contract.md).
+
+## Orchestration telemetry
+
+Optional `orchestration` object on an [`audit-log-v1`](audit-log-v1.md) line —
+additive, non-breaking, counts + ids only.
+
+```json
+{ "task_size_estimate": 0, "spawn_count": 0, "tiers": [], "token_delta": 0, "wall_clock_ms": 0, "outcome": "DONE", "verify_mode": "deterministic" }
+```
+
+Full semantics: [`orchestration-telemetry`](../../src/agent-src/contexts/execution/orchestration-telemetry.md).
+
+## Activation precondition
+
+Auto-dispatch is attempted only when:
+
+```
+subagents.enabled AND subagents.auto != off AND manifest.subagent_spawn AND task-is-delegable
+```
+
+Any failing → in-session. Full gate:
+[`auto-orchestration-activation`](../../src/agent-src/contexts/execution/auto-orchestration-activation.md).
+
+## Cross-references
+
+- [ADR-105](../decisions/ADR-105-automatic-subagent-orchestration.md) — the decisions.
+- [`subagent-routing`](../../src/agent-src/contexts/execution/subagent-routing.md) — model downshift + quota bonus.
+- [`auto-dispatch-classification`](../../src/agent-src/contexts/execution/auto-dispatch-classification.md) — delegability rules.
+- [`verify-budget`](../../src/agent-src/contexts/execution/verify-budget.md) — verification budget.
+- [`subagent-steering`](../../src/agent-src/contexts/execution/subagent-steering.md) — guardrails + kill-switch.
+- [`orchestration-benchmark-gate`](../../src/agent-src/contexts/execution/orchestration-benchmark-gate.md) — the default-flip gate.

package/docs/contracts/capability-boundary.md

@@ -0,0 +1,64 @@
+# Capability Boundary Matrix
+
+The per-pack safety posture at a glance: is a pack on by default, does it need
+consent, a council pass, a disclaimer, an eval — and how risky is it. The matrix
+makes the invisible visible; the **enforcement** lives in the per-pack safety
+floors + gates (this doc is the map, not the engine).
+
+> Source of truth: `src/config/discovery/packs.yml` (`surface_tier`,
+> `trust_level_default`, `domain`, and the legal-review-prep gate fields) + the
+> domain safety-floor rules. Built in `road-to-capability-governance` Phase 1;
+> `risk_class` becomes a real pack field in Phase 2.
+
+## Policy by risk class
+
+| `risk_class` | default install | consent | council / deep-research | disclaimer | eval expectation | surface_tier |
+|---|---|---|---|---|---|---|
+| **low** | per profile | no | no | no | optional | `core` |
+| **medium** (advisory) | per profile | no | no | **yes** (domain safety floor) | recommended | `core` |
+| **high** | **no** (opt-in) | **yes** | **yes** (fail-closed) | **yes** | **yes** | `lab` |
+
+- **low** — engineering, product, meta, and tooling packs. Normal capability; no domain liability surface.
+- **medium (advisory)** — packs that emit advisory-shaped output (finance, strategy). They carry a **domain safety floor** that mandates a not-X-advice disclaimer + structural elements (assumptions / counter-case / confidence). Not off-by-default, but never a final call.
+- **high** — regulated-advice-adjacent. Off by default, consent-gated, council-gated (fail-closed), disclaimer-bound, eval-backed, lab-tier, and promotion-gated behind a professional review.
+
+## Per-pack assignment (non-low)
+
+| Pack | `risk_class` | Floor | Gates |
+|---|---|---|---|
+| `legal-review-prep` | **high** | `legal-safety-floor` | consent (`legal_review_prep.acknowledged`) · council (`require_council`, fail-closed) · hard individual-case STOP · attorney-review line + `Jurisdiction:` tag · attorney-framing-review promotion tripwire · `default_install: false` · `surface_tier: lab` |
+| `finance-basic` | medium | `finance-safety-floor` | not-financial-advice disclaimer · assumptions + sensitivity + confidence + counter-case · no final invest/raise call |
+| `finance-advanced` | medium | `finance-safety-floor` | as finance-basic (DCF / scenario depth) |
+| `founder-strategy` | medium | `strategy-safety-floor` | not-a-strategic-decision footer · bet + counter-case + residual risk + decision owner |
+
+Every other pack in `packs.yml` is **low** by default. A pack moves to medium the
+moment it ships advisory-shaped output behind a domain safety floor, and to high
+only through the high-risk checklist (consent + council + disclaimer + eval +
+lab + promotion gate) — see `road-to-legal-review-prep` for the worked example.
+
+## Capability lifecycle (a view, not a new axis)
+
+Reviewers wanted one lifecycle vocabulary for promoting / retiring capabilities.
+This is a **derived view** over the metadata that already exists
+(`trust_level_default` + `surface_tier` + eval presence) — **not** a new field.
+Nothing to set; it is read off what is already there.
+
+| Lifecycle | Derived from | Promotion criterion (to reach it) |
+|---|---|---|
+| **experimental** | `surface_tier: lab` **or** `trust_level_default: experimental` | default for any new pack/skill |
+| **validated** | `surface_tier: core` **and** has an `evals/` (or regression harness) | a real eval exists + the pack left lab |
+| **recommended** | validated **and** in a default profile / ≥1 real consumer | adoption evidence, not just existence |
+| **deprecated** | a `deprecated`/`superseded_by` marker in frontmatter | a successor named (per the persona/skill deprecation discipline) |
+
+Read the lifecycle column off the matrix above: a `lab` + `experimental` pack
+(e.g. `legal-review-prep`, `ai-video`) is **experimental**; a `core` pack with an
+eval is **validated**; a `core` pack a profile ships is **recommended**.
+Promotion stays a human/maintainer decision (criteria-documented, never
+automated — see `road-to-capability-governance` Phase 6).
+
+## See also
+
+- [`legal-safety-floor`](../../src/rules/legal-safety-floor.md) — the high-risk exemplar.
+- `finance-safety-floor` · `strategy-safety-floor` — the medium-risk advisory floors.
+- [`domain-pack-architecture`](../guidelines/agent-infra/domain-pack-architecture.md) — the pack build sequence.
+- `road-to-capability-governance` Phase 2 — `risk_class` as a validated pack field.

package/docs/contracts/command-clusters.md

@@ -28,7 +28,7 @@ column 1 of this table.
 
 | Cluster | Phase | Sub-commands | Replaces |
 |---|:-:|---|---|
-| `fix` | 1 | `ci` · `pr-comments` · `pr-bot-comments` · `pr-developer-comments` · `portability` · `refs` · `seeder` | `fix-ci` · `fix-pr-comments` · `fix-pr-bot-comments` · `fix-pr-developer-comments` · `fix-portability` · `fix-references` · `fix-seeder` |
+| `fix` | 1 | `ci` · `pr-comments` · `pr-bot-comments` · `pr-developer-comments` · `portability` · `refs` · `seeder` · `comments` | `fix-ci` · `fix-pr-comments` · `fix-pr-bot-comments` · `fix-pr-developer-comments` · `fix-portability` · `fix-references` · `fix-seeder`; `comments` added 2026-06-22 — audits the **code comments** in the current branch's diff (simplify / shorten / remove), distinct from the PR-review-thread `pr-comments` sub |
 | `optimize` | 1 | `agents-dir` · `augmentignore` · `rtk` · `skills` | `optimize-augmentignore` · `optimize-rtk-filters` · `optimize-skills` · former `/optimize agents` and `/optimize agents-md` moved to the `/agents` file-family cluster 2026-05-09; `/agents prepare/audit/cleanup` collapsed into the single `/optimize agents-dir` (flags or wizard) per the agent-doc consolidation |
 | `feature` | 1 | `explore` · `plan` · `refactor` · `roadmap` · `dev` | `feature-explore` · `feature-plan` · `feature-refactor` · `feature-roadmap` · `feature-dev` |
 | `chat-history` | 2 | `show` · `import` · `learn` | `chat-history` (legacy status) — `resume` / `clear` / `checkpoint` removed in `road-to-chat-history-hook-only` (auto-adopt + structural hooks); `import` (verbatim cross-session render) and `learn` (project-improving learning extraction) added in the v4 stateless schema |

package/docs/contracts/discovery-manifest.schema.json

@@ -74,7 +74,7 @@
     },
     "workspace_id": {
       "type": "string",
-      "enum": ["engineering", "product", "finance", "founder", "gtm", "ops", "small-business", "construction", "agent-config-maintainer"]
+      "enum": ["engineering", "product", "finance", "founder", "gtm", "ops", "small-business", "construction", "legal-review-prep", "agent-config-maintainer"]
     },
     "pack_id": {
       "type": "string",
@@ -84,7 +84,7 @@
         "finance-basic", "finance-advanced",
         "gtm-sales", "gtm-marketing",
         "ops-people", "founder-strategy", "small-business", "construction", "ai-video", "ai-image", "fun", "meta", "git", "frontend-design", "brand",
-        "memory", "analytics", "product-reasoning", "analysis-workbench"
+        "memory", "analytics", "product-reasoning", "analysis-workbench", "legal-review-prep"
       ]
     },
     "lifecycle": {

package/docs/contracts/package-self-orientation.md

@@ -156,5 +156,8 @@ layout + cloud-bundle pipeline:
 3. Commit in logical chunks with Conventional Commits.
 4. Open a PR against `main`.
 
+Per-pack safety posture (default-install / consent / council / disclaimer /
+risk_class): [`capability-boundary.md`](capability-boundary.md).
+
 User-facing story: [`README.md`](../../README.md). Architecture
 deep-dive: [`docs/architecture.md`](../architecture.md).

package/docs/contracts/subagent-boundary.md

@@ -0,0 +1,54 @@
+# Subagent Boundary Contract
+
+What a subagent **owns** and what it must **never** own. As delegation spreads
+(the `subagent-orchestration` modes, the `delegation-policy` auto-trigger,
+workflow fan-out), the failure mode is scope drift: a subagent quietly
+redefining the task, expanding scope, or bypassing a floor. This contract draws
+the line.
+
+## The ownership line
+
+A subagent **executes one scoped, named task and returns a conclusion.** That is
+the whole of its authority.
+
+### A subagent OWNS
+
+- **Its scoped task** — the single, well-specified slice it was dispatched with.
+- **Its method** — how it searches, reads, reasons, or drafts within that slice.
+- **Its return** — a conclusion + evidence, sized to what the orchestrator asked for (structured output when a schema was given).
+
+> **Explainability is durable, not host-ephemeral.** The return must carry a brief
+> *why + evidence* (which sources/steps led to the conclusion) **in the artefact /
+> output itself**, not only in the host's session reasoning. A user opening the
+> result later — possibly across sessions — must be able to trace the *why* without
+> reassembling provider chat logs. This is the reasoning-in-notes discipline applied
+> to delegation: conclusions + evidence travel with the output, raw chain-of-thought
+> does not.
+
+### A subagent must NEVER own
+
+- **Task meaning** — it does not redefine, broaden, or reinterpret the parent task. An ambiguous slice returns "ambiguous + why", it does not guess a bigger task.
+- **Cross-task memory / state** — it does not write durable memory, mutate shared roadmaps, or persist decisions for other tasks; its output is its only channel.
+- **Pack / surface decisions** — it does not decide what ships, what installs, or what a pack contains; those are orchestrator + human calls.
+- **Safety-floor bypass** — every floor applies *inside* the subagent. The Hard Floor ([`non-destructive-by-default`](../../src/rules/non-destructive-by-default.md)), the domain safety floors, [`scope-control`](../../src/rules/scope-control.md), and [`commit-policy`](../../src/rules/commit-policy.md) are not lifted by being one level down. A subagent cannot do what its parent may not.
+- **Silent scope expansion** — touching files / systems beyond its slice is a contract violation, surfaced, not absorbed.
+
+## Orchestrator obligations (the other side)
+
+- **Verify, never adopt blind** — a subagent return is evidence, not truth; the orchestrator verifies per [`delegation-policy`](../../src/rules/delegation-policy.md)'s Iron Law before adopting it.
+- **Tier-size the slice, not the agent** — dispatch at the slice's complexity, not the session's.
+- **Own the safety decision** — a Hard-Floor or egress action surfaced by a subagent is decided by the orchestrator + human, never executed by the subagent.
+
+## Failure modes
+
+- A research subagent that, finding the task underspecified, invents a broader task and "helpfully" does it.
+- A subagent that writes to shared memory / a roadmap dashboard as a side effect.
+- A subagent that commits, pushes, or deletes because "the task implied it".
+- An orchestrator that pastes a subagent's claim into the answer without verifying it.
+
+## See also
+
+- [`subagent-orchestration`](../../src/skills/subagent-orchestration/SKILL.md) — the dispatch modes this contract bounds.
+- [`delegation-policy`](../../src/rules/delegation-policy.md) — the delegate-by-default trigger + verify-every-return Iron Law.
+- [`capability-boundary`](capability-boundary.md) — the pack-level companion (this is the agent-level one).
+- [`non-destructive-by-default`](../../src/rules/non-destructive-by-default.md) — the Hard Floor that applies inside subagents too.

package/docs/decisions/ADR-013-discovery-frontmatter-contract.md

@@ -93,6 +93,7 @@ install:
 | `ops` | Operations | Hiring, comp, perf, org design, runbooks. |
 | `small-business` | Small Business | Self-employed / SMB-shaped owner workflows. |
 | `construction` | Construction | Trade-business workflows (planning, quotes). |
+| `legal` | Legal | In-house legal — contract/NDA/DPA review, privacy, legal triage (EU/DE scope). |
 | `agent-config-maintainer` | Maintainer | Skills/rules/commands that maintain *this* package. |
 
 Amendments to the workspace list require an ADR-013 amendment.
@@ -120,6 +121,7 @@ Amendments to the workspace list require an ADR-013 amendment.
 | `founder-strategy` | Vision, fundraising narrative, competitive moat. (Renamed from `founder` to honour the non-overlap rule against `profile.id: founder`.) |
 | `small-business` | SMB-shaped owner workflows. |
 | `construction` | Trade-business workflows. |
+| `legal` | In-house legal — EU/DE-scoped contract/NDA/DPA review and legal triage; procedure-only, attorney-review draft output. |
 | `ai-video` | AI video pipeline (per ADR-011, the only heavyweight domain). |
 | `fun` | Non-essential social/fun workflows (prediction-pool tips, etc.). Optional under the `small-business` workspace; `experimental` trust. |
 | `meta` | Artefacts that maintain *this* package (`agent-config` itself). |
@@ -295,6 +297,36 @@ consistency governance that constrains UI). Mirrored in
 2026-06-13 (road-to-image-brand-typography Phase B). Additive, no rename;
 non-overlap with cost-profile and `profile.id` reservations holds.
 
+### 2026-06-24 — New `legal` workspace + `legal` pack
+
+Added workspace id `legal` and pack id `legal` to the closed vocabularies
+(in-house legal — EU/DE-scoped contract/NDA/DPA review and legal triage;
+procedure-only, no default legal positions; every output a draft for attorney
+review). Mirrored in
+[`src/config/discovery/workspaces.yml`](../../src/config/discovery/workspaces.yml),
+[`src/config/discovery/packs.yml`](../../src/config/discovery/packs.yml), and the
+`ADR_WORKSPACES` + `ADR_PACKS` sets in
+[`src/scripts/lint_discovery_vocabulary.ts`](../../src/scripts/lint_discovery_vocabulary.ts).
+`workspaces: [legal]`, `domain: legal`, `size_class: medium`,
+`trust_level_default: experimental`, `surface_tier: lab` (gated lab-tier until the
+Gate-2 maintenance owner + external qualification is confirmed —
+road-to-legal-pack Phase 0.2). Council-resolved across three rounds 2026-06-24
+(road-to-legal-pack). Additive, no rename; non-overlap with cost-profile and
+`profile.id` reservations holds.
+
+### 2026-06-24 — Rename `legal` → `legal-review-prep` (workspace + pack)
+
+Renamed the workspace id and pack id `legal` → `legal-review-prep` in both
+closed vocabularies, the schema enums, and all artefacts (`src/domains/legal/`
+→ `src/domains/legal-review-prep/`, the five skill frontmatters, the
+`legal-safety-floor` rule). Driven by a deep AI-council (3 rounds,
+anthropic/claude-sonnet-4-5 + openai/gpt-4o, 2026-06-24) + ~8 external
+7.1.0 reviewers: the name `legal` reads as "legal advice" and undermines the
+not-legal-advice positioning; `legal-review-prep` names the actual capability
+(prepare for attorney review). The `domain: legal` classifier and the `legal`
+user-type are a different axis and are unchanged. Rename, not additive;
+non-overlap reservations still hold. See `road-to-legal-review-prep` Phase 0.
+
 ## Cross-references
 
 - [ADR-007 — Agent Discovery Scopes](ADR-007-agent-discovery-scopes.md):