@event4u/agent-config 9.13.0 → 9.14.0

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": "9.13.0",
+    "version": "9.14.0",
     "keywords": [
       "agent-config",
       "skills",

package/CHANGELOG.md

@@ -253,6 +253,54 @@ Entry-shape contract: [`docs/contracts/CHANGELOG-conventions.md`](docs/contracts
 > that forces a new era split (`# Era: 9.14.x`, etc.) — see
 > [`docs/contracts/CHANGELOG-conventions.md § Era splits`](docs/contracts/CHANGELOG-conventions.md).
 
+## [9.14.0](https://github.com/event4u-app/agent-config/compare/9.13.0...9.14.0) (2026-08-02)
+
+### Release highlights
+
+<!-- Curated head: fill before merge, keep it under 10 lines, and leave `_none_` where it is genuinely the answer. The generated log below is unchanged. -->
+- **Behaviour changes:** _none_
+- **Default changes + migration:** _none_
+- **Security and correctness:** _none_
+- **Honest nulls:** _none_
+- **Known limitations:** _none_
+
+### Features
+
+* **gates:** fail on any count position the generator cannot rewrite ([71c8761](https://github.com/event4u-app/agent-config/commit/71c8761e1a7ba5a7d89e234c30b22daa41f2ee3f))
+* **counts:** generate the scoped-projection and active-command figures ([0a69bad](https://github.com/event4u-app/agent-config/commit/0a69bad08a166295fbe0cf5be018742600f02450))
+* **commands:** /optimize:deep — autonomous deep-refactoring loop ([a34efa9](https://github.com/event4u-app/agent-config/commit/a34efa9a78ecd45fbf1a3549c58bdd4b685b9ad8))
+* **roadmaps:** package-renewal central roadmap + three sub-roadmaps ([1802712](https://github.com/event4u-app/agent-config/commit/1802712bc0e9dc161830ee8f714c9a81e1feab33))
+
+### Bug Fixes
+
+* **ci:** discriminate dead scope from verified-empty release in corpus gates ([caa35e7](https://github.com/event4u-app/agent-config/commit/caa35e7b6f46900c987c3d12010f5db73fbec843))
+* **ci:** probe only the canonical projection root in the liveness check ([11cbaa7](https://github.com/event4u-app/agent-config/commit/11cbaa7cda5b104f1b0aa5b6d4beb174659586bf))
+* **commands:** shorten optimize-deep description below the 200-char cap ([2501034](https://github.com/event4u-app/agent-config/commit/250103476f6b362946475240f1087179fa38a236))
+
+### Documentation
+
+* **roadmap:** close and archive road-to-reproducible-artefact-counts ([2599fc4](https://github.com/event4u-app/agent-config/commit/2599fc470e8390bc7f03dbc3787f74933e5cd5a7))
+* **claims:** bind the default-install claim to the emitter, date the snapshot ([222c83c](https://github.com/event4u-app/agent-config/commit/222c83c0fb64105ff4819add5220c27182020cb6))
+* **roadmaps:** close the refinement-loop step — set converged at N=3 ([9b50deb](https://github.com/event4u-app/agent-config/commit/9b50deb8a2f6cf7e048fc605170b04f05c170e2b))
+
+### Refactoring
+
+* **install:** extract the scoped-projection predicate into _lib ([59be75f](https://github.com/event4u-app/agent-config/commit/59be75f3d7d9105a29e110424acce4bfeae1950e))
+* **roadmaps:** apply maintainer-review fixes (win path, ci baseline, loop verification gate) ([62a0c72](https://github.com/event4u-app/agent-config/commit/62a0c72e7e7850197df1f0b4c2ed7ac9f331d93c))
+* **roadmaps:** apply loop-3 convergence deltas ([d2dfd7d](https://github.com/event4u-app/agent-config/commit/d2dfd7df824d1a0f1b31ed975673bbe8c71e5119))
+* **roadmaps:** apply loop-2 review deltas ([19f5bc2](https://github.com/event4u-app/agent-config/commit/19f5bc279dea4407d844199550a04cf46954709f))
+* **roadmaps:** apply loop-1 adversarial-review deltas ([ba8e641](https://github.com/event4u-app/agent-config/commit/ba8e6414cf10eeab218e9aecf18d571946a6501f))
+
+### Tests
+
+* **counts:** witness that the two gates now move together ([14ac65b](https://github.com/event4u-app/agent-config/commit/14ac65b73355363204784585d76640a23b98e3c9))
+
+### Build
+
+* **install:** rebuild the install bundle for the extracted predicate ([00cc359](https://github.com/event4u-app/agent-config/commit/00cc359ce6a0582857b62f662b19e4cfd809b0b9))
+
+Tests: 10056 (+14 since 9.13.0)
+
 ## [9.13.0](https://github.com/event4u-app/agent-config/compare/9.12.0...9.13.0) (2026-08-02)
 
 ### Release highlights

package/README.md

@@ -4,7 +4,7 @@
 
 [![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) [![MCP Toplist](https://mcptoplist.com/badge/glama%2Fevent4u-app%2Fagent-config.svg)](https://mcptoplist.com/server/glama%2Fevent4u-app%2Fagent-config)
 
-[![Skills](https://img.shields.io/badge/Skills-288-orange?style=flat-square)](dist/agent-src/skills/) [![Rules](https://img.shields.io/badge/Rules-111-orange?style=flat-square)](dist/agent-src/rules/) [![Commands](https://img.shields.io/badge/Commands-191-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-288-orange?style=flat-square)](dist/agent-src/skills/) [![Rules](https://img.shields.io/badge/Rules-111-orange?style=flat-square)](dist/agent-src/rules/) [![Commands](https://img.shields.io/badge/Commands-193-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/)
 
 **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/)**.
 

package/dist/agent-src/commands/optimize/deep.md

@@ -0,0 +1,147 @@
+---
+model_tier: high
+name: optimize-deep
+pack: meta
+tier: 2
+visibility: internal
+sub: deep
+cluster: optimize
+skills: [ai-council, roadmap-writing, subagent-orchestration, decision-review]
+description: "Autonomous deep-refactoring loop — subagent analysis, verified findings, council, central + sub-roadmaps, PR, then N refinement loops (default 3). E.g. 'run a deep optimization pass'."
+argument-hint: "[--loops=N] [--scope=<path>] [--no-external]"
+suggestion:
+  eligible: false
+  rationale: "Cluster sub-command — reached via its cluster head's routing or its explicit /cluster:sub name; not independently suggested (surface-consolidation)."
+workspaces:
+  - agent-config-maintainer
+  - engineering
+packs:
+  - meta
+---
+
+# /optimize-deep
+
+Autonomous deep-improvement loop: **analyze → verify → council → roadmaps →
+PR → refine ×N**. The autonomous sibling of [`/optimize project`](project.md)
+(which is interview-driven and asks the user); this command answers its own
+questions in the AI council and ends with a pull request plus a
+council-refined roadmap set.
+
+This is a **coordinator** over existing primitives — it composes, never
+reimplements: subagent fan-out analysis, `/analyze:decision`-style decision
+challenge, `ai-council` resolution, `/roadmap:create` output shape,
+`/create-pr` mechanics.
+
+## When to invoke
+
+- "Deep-analyze this package and build the improvement roadmap" /
+  "geh in die Tiefe und erstelle die Refactoring-Roadmap".
+- Periodic renewal: question standing decisions after the environment
+  changed (new host capabilities, model generation, ecosystem shift).
+- A refactoring mandate that should end in a reviewed PR, not a chat answer.
+
+Do NOT invoke for: a single named bug, an interview-style sweep with the
+user in the loop (route to `/optimize project`), a code-only analysis
+(`/project-analyze`), or agent-layer file tooling (`/optimize` siblings).
+
+## Loop budget
+
+`--loops=N` caps the refinement loops. **Default: 3** (council-locked
+2026-08-02: autonomous loops without a fast, trustworthy CI oracle are
+compounding-error machines; 3 with a tripwire beats 5 on cost/benefit).
+Hard ceiling: 5 — above that, re-invoke deliberately with fresh context.
+
+**Halt-on-spin tripwire (checked after every loop, overrides the budget):**
+
+- A loop ends with no material roadmap delta (no step added, removed,
+  re-scoped, or re-ordered) → STOP, the set has converged.
+- The council splits on the same question twice → STOP, escalate that
+  question to the user instead of burning a third loop on it.
+- Any validation target fails 3 consecutive refinement attempts → STOP
+  (N=3 budget, `autonomous-execution`).
+
+## Steps
+
+### Step 0 — Preflight (read-only)
+
+1. Live remote state first (`direct-answers` live-state law): fetch,
+   open PRs, recently merged work overlapping the scope — never from memory.
+2. Create or enter an isolated worktree on a fresh branch off the trunk
+   (branch/worktree creation is authorized by invoking this command; every
+   Hard-Floor action below stays gated).
+3. Honor any repo worktree-seeding convention when seeding the worktree;
+   never copy `.agent-settings.yml` into a worktree.
+4. Read the lock inventory: honest nulls, DR memories, `later/` resume
+   conditions, standing ADRs. These are constraints for Step 4, surfaced —
+   never silently relitigated (`decision-revisit-gate`).
+
+### Step 1 — Deep analysis (parallel subagents)
+
+Fan out read-only analysis subagents over the repo's load-bearing surfaces
+(token/context cost, execution flows, CI/PR pipeline, routing/activation,
+decision debt, archived intelligence) plus — unless `--no-external` —
+tree-level deep-dives of named external references (`external-reference-deep-dive`:
+file trees + raw files, never README summaries). Each agent returns
+structured findings with file:line evidence and an effort estimate.
+
+### Step 2 — Verification gate (non-negotiable)
+
+Hand-verify every damning finding before it may steer the roadmap
+(`plausible-mechanism-is-not-evidence`): re-run the grep/measurement the
+finding rests on, in this checkout, at this SHA. A finding that fails
+verification is dropped with a note. Findings colliding with a recorded
+lock are marked and routed to Step 3 only if the mechanism differs
+(mechanism-match test) — otherwise honored as locked.
+
+### Step 3 — Council pass
+
+Run the AI council (`council:estimate` → `council:run --confirm`) on the
+contested decisions only: priority order, roadmap topology, lock collisions
+that pass the mechanism-match test, and the loop count when the user gave
+none. Surface the fast-path marker verbatim where the low-impact path
+resolves something. High-impact and user-required classes still reach the
+user per `ai-council-config` — autonomy never rewires that floor.
+
+### Step 4 — Roadmap set
+
+Author ONE central roadmap (goal, verified findings, locks honored,
+sub-roadmap management table, pre-registered success criteria, provenance —
+external sources anonymized + `ENC1:`-encrypted per `source-confidentiality`)
+plus sub-roadmaps cut along the council's topology. Foundation-class
+work (whatever must be true for the rest to be verifiable — typically the
+CI oracle) gates the leverage-class work explicitly. Regenerate the
+dashboard (`roadmap:progress`) in the same response as any roadmap write.
+
+### Step 5 — Pull request
+
+Push the branch and open the PR per [`/create-pr`](../pr/create.md) — its
+mechanics and the always-active PR-surface rules govern the body and reply
+shape; do not restate them here.
+
+### Step 6 — Refinement loops (×N, autonomous)
+
+Each loop: (a) re-read the roadmap set with fresh subagent reviewers
+(adversarial: hunt over-building, missing evidence, lock violations,
+sequencing errors); (b) resolve contested deltas in the council; (c) any
+delta resting on a NEW factual claim re-enters the Step-2 verification gate
+before application — reviewer assertions are findings, not facts; (d) apply
+the surviving deltas to the roadmaps; (e) push to the same PR; (f) evaluate
+the tripwire. Loop output is a delta summary in the PR description's
+changelog section, not a comment (`no-pr-progress-comments`).
+
+## Output
+
+- The PR URL (literal last line of the closing reply).
+- Central + sub-roadmaps on the branch, dashboard regenerated.
+- Council artifacts under `agents/runtime/council/` (local-only, auto-pruned).
+- A one-paragraph verdict per refinement loop: what changed, what converged.
+
+## Gotchas
+
+- Merge/deploy is where autonomy ends — Step 6 loop pushes go to the
+  already-open PR under the invocation's authorization; merging it,
+  deploying, or any irreversible external action stays this-turn gated.
+- Council spend: estimate first; abort and surface if the configured budget
+  guard trips mid-run.
+- Subagent cwd pins to the launch dir, not the worktree — pass absolute
+  paths into every subagent prompt.

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

@@ -2,19 +2,19 @@
 model_tier: medium
 name: optimize
 disable-model-invocation: true
-argument-hint: "[skills|agents-dir|augmentignore|rtk|project|prompt] [args]"
+argument-hint: "[skills|agents-dir|augmentignore|rtk|project|prompt|deep] [args]"
 pack: meta
-intent: "Optimization dispatcher — skills, rtk, augmentignore, agents-dir, project sweep, prompt"
-routes_to: [optimize-skills, optimize-rtk, optimize-augmentignore, optimize-agents-dir, optimize-project, optimize-prompt]
+intent: "Optimization dispatcher — skills, rtk, augmentignore, agents-dir, project sweep, prompt, deep autonomous loop"
+routes_to: [optimize-skills, optimize-rtk, optimize-augmentignore, optimize-agents-dir, optimize-project, optimize-prompt, optimize-deep]
 replaces: []
 tier: 1
 visibility: advanced
-description: Optimize orchestrator — routes to skills, agents-dir, augmentignore, rtk-filters, project (project-wide sweep), prompt (AI-prompt polish)
+description: Optimize orchestrator — routes to skills, agents-dir, augmentignore, rtk-filters, project (project-wide sweep), prompt (AI-prompt polish), deep (autonomous deep-refactoring loop)
 cluster: optimize
 type: orchestrator
 suggestion:
   eligible: true
-  trigger_description: "optimize my skills, manage agents directory, tune augmentignore, optimize rtk filters, optimize this project, optimize this prompt"
+  trigger_description: "optimize my skills, manage agents directory, tune augmentignore, optimize rtk filters, optimize this project, optimize this prompt, run a deep optimization pass"
   trigger_context: "maintainer auditing/trimming the agent layer, running a project-wide optimization sweep, or polishing an AI prompt (NOT AGENTS.md — that's /agents)"
 workspaces:
   - agent-config-maintainer
@@ -42,6 +42,7 @@ the **agent layer** (skills, agents-dir, augmentignore, rtk), the **project**
 | `/optimize rtk` | `commands/optimize/rtk.md` | Create or refine project-local rtk filters |
 | `/optimize project` | `commands/optimize/project.md` | Project-wide optimization sweep — inventory roadmaps/ADRs/agent folders, challenge stale decisions, emit new roadmap(s) |
 | `/optimize prompt` | `commands/optimize/prompt.md` | Optimize a raw prompt for ChatGPT/Claude/Gemini via the 4-D methodology |
+| `/optimize deep` | `commands/optimize/deep.md` | Autonomous deep-refactoring loop — subagent analysis, council, central + sub-roadmaps, PR, N refinement loops (default 3) |
 
 Sub-command names match the locked contract in
 [`docs/contracts/command-clusters.md`](../docs/contracts/command-clusters.md).
@@ -60,14 +61,19 @@ Sub-command names match the locked contract in
    > 4. rtk — create or refine project-local rtk filters
    > 5. project — project-wide sweep (roadmaps, ADRs, decisions → new roadmaps)
    > 6. prompt — polish a raw AI prompt (4-D methodology)
+   > 7. deep — autonomous deep-refactoring loop (analysis → council → roadmaps → PR → refine ×N)
 
 ## Rules
 
 - **Suggest only — never auto-apply.** All `/optimize` sub-commands are
   audit-grade: they report and propose, but the user approves every change.
+  Exception: `deep` is the explicitly autonomous variant — invoking it IS the
+  approval for its worktree/branch/roadmap/PR flow; the Hard Floor
+  (merge/deploy/prod/bulk-delete) still gates inside it.
 - **Scope check before routing.** Agent-layer subs (1–4) never touch project
   code or roadmaps; `project` never rewrites the agent layer; `prompt` only
-  returns a rewritten prompt.
+  returns a rewritten prompt; `deep` writes roadmaps + a PR branch but never
+  merges.
 - **Do NOT chain sub-commands.** One `/optimize <sub>` per turn.
 - If the user invokes `/optimize` with no argument, **show the menu** — do
   not guess which sub-command they meant.

package/dist/agent-src/templates/agents/agent-project-settings.example.yml

@@ -39,7 +39,7 @@ schema_version: 1
 # CI guard: a release bump of `package.json` must update this value
 # in lockstep — see scripts/check_template_pin_drift.ts (road-to-
 # portable-runtime-and-update-check P3.3).
-agent_config_version: "9.13.0"
+agent_config_version: "9.14.0"
 
 # --- Project identity ---
 project: