@mmerterden/multi-agent-pipeline 15.0.0 → 15.2.0

package/CHANGELOG.md

@@ -16,6 +16,133 @@ Internal file-layout changes that don't affect the slash-command surface are sti
 
 ## [Unreleased]
 
+## [15.2.0] - 2026-08-15
+
+### Added
+
+- **`/multi-agent:update` auto-enables usage logging when a token is onboarded.**
+  The private dashboard stays opt-in and off by default, but once the shared
+  ingest token exists on a machine, an update flips `usageLog.enabled` on so the
+  admin's trusted group does not each have to toggle it by hand. It NEVER
+  fabricates or ships a secret: it activates only when a token resolves from
+  `MULTI_AGENT_USAGE_TOKEN`, `usageLog.token`, or the Keychain item named by the
+  new generic `keychainMapping.usage_ingest` slot - a machine that was never
+  given the token stays silent.
+- **`usage-report.mjs` reads the ingest token from the Keychain** (via
+  `credential-store.sh`, resolved through `keychainMapping.usage_ingest`) as a
+  fallback after env and `usageLog.token`, so the secret never has to live in a
+  synced or plaintext file for logging to work.
+
+## [15.1.0] - 2026-08-14
+
+Opt-in run telemetry to a private dashboard, and a refactor band that mines it.
+
+### Added
+
+- **Opt-in usage telemetry (`usageLog`).** When `prefs.global.usageLog.enabled`
+  is set with an ingest token, each run emits one activity event, keyed by task
+  id and refreshed live at every phase boundary via `phase-tracker.sh`, so one
+  record always shows the last phase a run reached — including runs that halt
+  before Phase 7. Wired at Phase 7 report and the halt path; detached and
+  best-effort, never blocking a run. The event carries activity metadata only
+  (who, command, mode, input type, repo, phase, outcome, halt cause, review
+  iterations, duration, token spend, cost, per-phase breakdown, OS, CLI, models,
+  stack, plugins, integrations, credential health, invoked skills, error tags,
+  version) — never prompts, code, diffs, token values or absolute paths. New
+  `pipeline/scripts/usage-report.mjs`; prefs schema + template gain the
+  `usageLog` block. Off by default; the emitter no-ops unless enabled and a
+  token resolves.
+- **`/multi-agent:refactor` Step 0d (band F).** Reads the local run-error ledger
+  (`errors-ledger.jsonl`, written by the telemetry emitter on terminal runs) and
+  ranks recurring failures as prioritized improvement areas — lived evidence,
+  offline, and without auth.
+
+### Changed
+
+- Reconciled the Copilot shared-core `multi-agent-refactor` skill with the Claude
+  command version, ending the prose drift that had accumulated between the two.
+
+## [15.0.1] - 2026-08-13
+
+Post-15.0.0 audit release: three blocking defects in the 15.0.0 surface, two
+data-loss paths, and the doc drift that let a command count go stale in 17
+places at once.
+
+### Fixed
+
+- **The 15.0.0 plugin-only migration never ran on an upgrade.** Its prune was
+  gated on `.external-skills-manifest.json`, which no released version wrote on
+  Claude Code, so every machine upgrading from 14.x kept the whole ~151-dir
+  external catalog (the duplicated per-session descriptions and plugin-shadowing
+  copies ADR-0009 exists to remove), and `uninstall --claude` refused to clean it
+  for the same reason. Pre-manifest installs are now migrated by proof rather
+  than by name: a skill dir byte-identical to the shipped catalog is provably
+  pipeline-delivered and is removed, a dir that differs is kept and reported,
+  and the new `install --prune-external` flag removes those too (still never a
+  dir carrying `local-only: true`). Gate: `smoke-claude-external-migration.sh`.
+- **The cross-host stack filter read a file nothing writes.** `pluginsToDeliver`
+  looked only at `~/.claude/settings.json` while `/multi-agent:stack` writes the
+  invoking repo's `.claude/settings.json`, so a stack selection either delivered
+  the entire catalog to Copilot/Codex (logged as if a filter had run) or, worse,
+  delivered a different stack than the repo asked for. Repo settings are now read
+  first, user-global second, `--platform` last.
+- **Copilot's skipped-stack prune could delete user-authored skills.** The prune
+  was derived from catalog *names*, so a user's own `~/.copilot/skills/<name>/`
+  sharing a catalog name was removed with no prompt. It is now scoped to the
+  previous delivery manifest (or, pre-manifest, to dirs byte-identical to the
+  catalog) - the same contract `uninstall` already used.
+- **Manifest-driven removal had no path containment.** A name carrying `..` or a
+  path separator in `.external-skills-manifest.json` resolved outside the skills
+  directory before reaching a recursive delete.
+- **`validate-complaint-doc.mjs` rejected reports that follow the template.**
+  Section 1's coverage table cites `C-NN` ids in its last column and was read as
+  verdict-less triage rows, and verdict matching was positional-substring, so a
+  summary cell mentioning `core-data` classified the row as `core`. Triage rows
+  are now scoped to the Triage section with the id in the first cell, and verdict
+  tokens match cell-exact. The smoke fixture carries both Section 1 tables so the
+  gate is exercised against real template output.
+- **`/multi-agent:stack` with no arguments wiped the repo's stack selection.**
+  The implementation block resolved an empty arg list to "common only" and then
+  applied the write rule that sets every other stack toolkit to `false`. Zero
+  args now exits into status mode, and the picker's `frontend (web)` label maps
+  back to its canonical arg.
+- `parse-complaints.sh` returns the documented exit 4 when `--file` / `--format`
+  is passed without a value instead of dying on `set -u`, and redacts all-letter
+  PNRs that follow a PNR-ish keyword.
+- `migrate-prefs.mjs`: the schema-unreadable fallback set now includes `2.5.0`,
+  so a 14.x prefs file no longer throws `unknown schemaVersion` on an install
+  tree whose `schemas/` cannot be read.
+- `check-derived-drift.mjs`: an acknowledged drift pin no longer silences a
+  cache-only resolution, which had let the gate exit 0 while nothing
+  authoritative was consulted.
+- `match-skills.mjs` gains the `~/.codex/multi-agent-refs/skills` index
+  candidate, so dynamic skill loading works on Codex instead of exiting 1.
+
+### Changed
+
+- `smoke-command-inventory.sh` now derives the command count for `README.md`,
+  `README.tr.md`, `docs/architecture.md` and `docs/ecosystem.md` as well. Those
+  four files held 17 of the 20 "50 commands" sites and none was gated, so adding
+  `complaint-analysis` desynced all of them at once.
+- Doc corrections: autopilot / local modes document 7 phases, not 8 (the
+  interactive Phase 5 test gate is dropped in every autopilot and local variant,
+  per `gen-mode-dispatch.mjs`) - README EN+TR and `tracker-contract.md`; the
+  Node badge matches `engines` (20.11+); the publish diagrams say public npm
+  rather than GitHub Packages; skill / schema / fixture counts match the tree;
+  `ecosystem.md` drops the retracted "frozen `figma-*` fallback" claim; ROADMAP
+  catches up four majors; ADR-0007 records Codex's return as a native target.
+- `SECURITY.md` ships in the package, so the README link resolves on npmjs and
+  in an installed tree. Install help documents `--dry-run`, `--index-only` and
+  `--prune-external`.
+
+### Removed
+
+- Dead pre-v15 code: `copyExternalSkillsFiltered`, `classifyExternalSkill` and
+  its prefix tables (superseded by the routing table), `existingSkillNames`
+  (superseded by `pipelineOwnedSkillNames`, and a hazard if called), and an
+  unconsumed `MCP_SERVER_NAME` re-export. Six internals no longer export a
+  surface nothing imports.
+
 ## [15.0.0] - 2026-08-13
 
 ### Changed (BREAKING)

package/README.md

@@ -2,7 +2,7 @@
 
 [![GitHub Release](https://img.shields.io/github/v/release/mmerterden/multi-agent-pipeline?color=blue)](https://github.com/mmerterden/multi-agent-pipeline/releases)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![Node.js](https://img.shields.io/badge/Node.js-18%20%7C%2020%20%7C%2022-green)](https://nodejs.org)
+[![Node.js](https://img.shields.io/badge/Node.js-20%20%7C%2022-green)](https://nodejs.org)
 [![Zero Dependencies](https://img.shields.io/badge/dependencies-0-brightgreen)](https://github.com/mmerterden/multi-agent-pipeline/blob/main/package.json)
 [![OpenSSF Scorecard](https://api.scorecard.dev/projects/github.com/mmerterden/multi-agent-pipeline/badge)](https://scorecard.dev/viewer/?uri=github.com/mmerterden/multi-agent-pipeline)
 
@@ -70,14 +70,14 @@ The discipline behind all of this - bounded loops, evidence gates, token-budgete
 | Mode | Command | Flow |
 |---|---|---|
 | Full | `/multi-agent "task"` | All 8 phases, interactive |
-| Autopilot | `/multi-agent:autopilot "task"` | All 8 phases, no confirmations |
+| Autopilot | `/multi-agent:autopilot "task"` | 7 phases (interactive Test gate dropped), no confirmations |
 | Dev | `/multi-agent:dev "task"` | Init → Dev → Review → Test → Commit → Report |
-| Local | `/multi-agent:local "task"` | Full pipeline, current branch (no worktree) |
+| Local | `/multi-agent:local "task"` | Full pipeline minus the interactive Test gate, current branch (no worktree) |
 | Ship | `/multi-agent:resume-local` | Run the review→test→commit→report tail over local work |
 | Audit | `/multi-agent:design-check` | Mock-mode vs Figma conformance, local-only |
 | Audit | `/multi-agent:testflight-validation` | Pre-submission gates for a TestFlight build: static archive audit → Apple's `altool --validate-app` → Review-Guidelines check. Validates only, never uploads |
 
-Helpers: `setup`, `status`, `resume #N`, `kill #N`, `garbage-collect`, `prune-logs`, `purge`, `review`, `test`, `channels`, `stack`, `update`, `sync`, `refactor`, `jira`, `issue`, `analysis`, `create-jira`, `save`, `routines`, `forget`. 50 commands in all  -  full list: `/multi-agent:help`.
+Helpers: `setup`, `status`, `resume #N`, `kill #N`, `garbage-collect`, `prune-logs`, `purge`, `review`, `test`, `channels`, `stack`, `update`, `sync`, `refactor`, `jira`, `issue`, `analysis`, `create-jira`, `save`, `routines`, `forget`. 51 commands in all  -  full list: `/multi-agent:help`.
 
 ## Stacks
 
@@ -91,17 +91,17 @@ This enables the matching plugin (+ the shared `ai-common` plugin) in the repo's
 
 ## Tool support
 
-The pipeline runs natively on **Claude Code**, **Copilot CLI** and **Codex CLI** - all three install from the same `pipeline/` source and get the same 50 commands.
+The pipeline runs natively on **Claude Code**, **Copilot CLI** and **Codex CLI** - all three install from the same `pipeline/` source and get the same 51 commands.
 
 | Tool | Flag | What it installs |
 |---|---|---|
 | Claude Code | `--claude` (default) | slash commands + skills + agents + `PreToolUse` secret-scan hook |
-| Copilot CLI | `--copilot` | instructions + 50 sub-command skills + scripts |
-| Codex CLI | `--codex` | one router skill + 50 specs as refs + 8 agent TOML + `AGENTS.md` block + `codex mcp add` |
+| Copilot CLI | `--copilot` | instructions + 51 sub-command skills + scripts |
+| Codex CLI | `--codex` | one router skill + 51 specs as refs + 8 agent TOML + `AGENTS.md` block + `codex mcp add` |
 
 Filter skills by stack with `--platform=ios\|android\|all`.
 
-**Why Codex gets one skill and not 50.** Codex assembles every discovered skill's name
+**Why Codex gets one skill and not 51.** Codex assembles every discovered skill's name
 and description into a single prompt block and drops entries when it overflows, with no
 error. Measured on 0.145: installing one plugin that declares 142 skills surfaced only
 75 of them and evicted an unrelated user skill. So on Codex the pipeline ships a single
@@ -135,7 +135,7 @@ The **secret scan** runs as a `PreToolUse` hook on Claude Code (hard-blocks a co
 
 ## Platform support
 
-Runs on **macOS**, **Linux**, and **Windows** (Git Bash / WSL). Shell and credential access go through a platform-agnostic layer - the keychain resolves automatically to **macOS Keychain**, **Linux libsecret** (`secret-tool`), or **Windows Credential Manager**, and scripts fall back between BSD and GNU tool variants. Node.js 18 / 20 / 22.
+Runs on **macOS**, **Linux**, and **Windows** (Git Bash / WSL). Shell and credential access go through a platform-agnostic layer - the keychain resolves automatically to **macOS Keychain**, **Linux libsecret** (`secret-tool`), or **Windows Credential Manager**, and scripts fall back between BSD and GNU tool variants. Node.js 20.11+ (tested on 20 and 22).
 
 ## Companion repos
 

package/README.tr.md

@@ -2,7 +2,7 @@
 
 [![GitHub Release](https://img.shields.io/github/v/release/mmerterden/multi-agent-pipeline?color=blue)](https://github.com/mmerterden/multi-agent-pipeline/releases)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![Node.js](https://img.shields.io/badge/Node.js-18%20%7C%2020%20%7C%2022-green)](https://nodejs.org)
+[![Node.js](https://img.shields.io/badge/Node.js-20%20%7C%2022-green)](https://nodejs.org)
 [![Zero Dependencies](https://img.shields.io/badge/dependencies-0-brightgreen)](https://github.com/mmerterden/multi-agent-pipeline/blob/main/package.json)
 [![OpenSSF Scorecard](https://api.scorecard.dev/projects/github.com/mmerterden/multi-agent-pipeline/badge)](https://scorecard.dev/viewer/?uri=github.com/mmerterden/multi-agent-pipeline)
 
@@ -70,14 +70,14 @@ Bunun arkasındaki disiplin - sınırlı loop'lar, kanıt kapıları, token-büt
 | Mod | Komut | Akış |
 |---|---|---|
 | Full | `/multi-agent "task"` | Tüm 8 faz, interaktif |
-| Autopilot | `/multi-agent:autopilot "task"` | Tüm 8 faz, onaysız |
+| Autopilot | `/multi-agent:autopilot "task"` | 7 faz (interaktif Test kapısı atlanır), onaysız |
 | Dev | `/multi-agent:dev "task"` | Init → Dev → Review → Test → Commit → Report |
-| Local | `/multi-agent:local "task"` | Tam pipeline, mevcut branch (worktree yok) |
+| Local | `/multi-agent:local "task"` | İnteraktif Test kapısı hariç tam pipeline, mevcut branch (worktree yok) |
 | Ship | `/multi-agent:resume-local` | Lokal iş üzerinde review→test→commit→report kuyruğunu çalıştır |
 | Audit | `/multi-agent:design-check` | Mock-mode vs Figma uygunluğu, yalnızca lokal |
 | Audit | `/multi-agent:testflight-validation` | TestFlight build için pre-submission kapıları: statik archive denetimi → Apple'ın `altool --validate-app`'i → Review-Guidelines kontrolü. Yalnızca doğrular, asla yüklemez |
 
-Yardımcılar: `setup`, `status`, `resume #N`, `kill #N`, `garbage-collect`, `prune-logs`, `purge`, `review`, `test`, `channels`, `stack`, `update`, `sync`, `refactor`, `jira`, `issue`, `analysis`, `create-jira`, `save`, `routines`, `forget`. Toplam 50 komut - tam liste: `/multi-agent:help`.
+Yardımcılar: `setup`, `status`, `resume #N`, `kill #N`, `garbage-collect`, `prune-logs`, `purge`, `review`, `test`, `channels`, `stack`, `update`, `sync`, `refactor`, `jira`, `issue`, `analysis`, `create-jira`, `save`, `routines`, `forget`. Toplam 51 komut - tam liste: `/multi-agent:help`.
 
 ## Stack'ler
 
@@ -91,17 +91,17 @@ Bu, ilgili plugin'i (+ ortak `ai-common` plugin'ini) repo'nun `.claude/settings.
 
 ## Araç desteği
 
-Pipeline **Claude Code**, **Copilot CLI** ve **Codex CLI** üzerinde native çalışır - üçü de aynı `pipeline/` kaynağından kurulur ve aynı 50 komutu alır.
+Pipeline **Claude Code**, **Copilot CLI** ve **Codex CLI** üzerinde native çalışır - üçü de aynı `pipeline/` kaynağından kurulur ve aynı 51 komutu alır.
 
 | Araç | Bayrak | Ne kurar |
 |---|---|---|
 | Claude Code | `--claude` (varsayılan) | slash komutları + skill'ler + agent'lar + `PreToolUse` secret-scan hook'u |
-| Copilot CLI | `--copilot` | talimatlar + 50 alt-komut skill'i + script'ler |
-| Codex CLI | `--codex` | bir router skill + ref olarak 50 spec + 8 agent TOML + `AGENTS.md` bloğu + `codex mcp add` |
+| Copilot CLI | `--copilot` | talimatlar + 51 alt-komut skill'i + script'ler |
+| Codex CLI | `--codex` | bir router skill + ref olarak 51 spec + 8 agent TOML + `AGENTS.md` bloğu + `codex mcp add` |
 
 Skill'leri stack'e göre filtrele: `--platform=ios\|android\|all`.
 
-**Codex neden 50 değil de tek bir skill alıyor.** Codex, keşfettiği her skill'in adını
+**Codex neden 51 değil de tek bir skill alıyor.** Codex, keşfettiği her skill'in adını
 ve açıklamasını tek bir prompt bloğuna toplar ve blok taştığında girdileri hatasızca
 düşürür. 0.145 üzerinde ölçüldü: 142 skill deklare eden bir plugin kurulduğunda sadece
 75'i yüzeye çıktı ve alakasız bir kullanıcı skill'i tahliye edildi. Bu yüzden Codex'te
@@ -136,7 +136,7 @@ triage notu bunu belirtir.
 
 ## Platform desteği
 
-**macOS**, **Linux** ve **Windows** (Git Bash / WSL) üzerinde çalışır. Shell ve credential erişimi platform-agnostik bir katmandan geçer - keychain otomatik olarak **macOS Keychain**, **Linux libsecret** (`secret-tool`) veya **Windows Credential Manager**'a çözülür, ve script'ler BSD ile GNU araç varyantları arasında fallback yapar. Node.js 18 / 20 / 22.
+**macOS**, **Linux** ve **Windows** (Git Bash / WSL) üzerinde çalışır. Shell ve credential erişimi platform-agnostik bir katmandan geçer - keychain otomatik olarak **macOS Keychain**, **Linux libsecret** (`secret-tool`) veya **Windows Credential Manager**'a çözülür, ve script'ler BSD ile GNU araç varyantları arasında fallback yapar. Node.js 20.11+ (20 ve 22'de test edildi).
 
 ## Yan repolar
 

package/SECURITY.md

@@ -0,0 +1,43 @@
+# Security Policy
+
+## Supported Versions
+
+We provide security fixes for the latest minor of the current major. Older versions get fixes only for severity ≥ high.
+
+| Version | Supported              |
+| ------- | ---------------------- |
+| 12.x    | ✅ active              |
+| 11.x    | ⚠️ security fixes only |
+| ≤ 10.x  | ❌ end-of-life         |
+
+## Reporting a Vulnerability
+
+**Do not open a public GitHub issue for security reports.**
+
+Please report vulnerabilities privately via GitHub's [Security Advisory](https://github.com/mmerterden/multi-agent-pipeline/security/advisories/new) flow. If GitHub Advisories are unavailable to you, email the package owner (see `package.json` → `author`) with:
+
+- A clear description of the issue and its impact
+- Steps to reproduce (a minimal repro is most helpful)
+- Affected version(s) and platform
+- Optional: a suggested patch or mitigation
+
+You should receive an initial acknowledgement within **5 business days**. We'll keep you updated on progress and aim to release a patch within **30 days** for high/critical issues.
+
+## Scope
+
+This pipeline orchestrates external systems (Jira, Bitbucket, GitHub, Confluence, Figma) using user-supplied tokens. We consider the following in scope for security reports:
+
+- **Token leakage** - any code path that logs, echoes, or persists secrets outside macOS Keychain.
+- **Command injection** - bash invocations built from untrusted input (Jira summary, branch names, PR titles, etc.).
+- **Pre-commit bypass** - secret-detection hook silently failing or being skippable without `--no-verify`.
+- **Pipeline tampering** - agent-state.json or preferences manipulation that escalates an installed package's effective permissions.
+
+Out of scope:
+
+- Misconfigured user systems (broken Keychain, expired tokens, missing CLI tools).
+- Vulnerabilities in transitive dependencies that don't reach a code path we use (please report those upstream first).
+- Issues that require an attacker to already control the user's local machine.
+
+## Coordinated Disclosure
+
+We follow standard coordinated disclosure: researchers are credited (with permission) in the release notes once a fix is shipped. Public disclosure timelines are agreed with the reporter, defaulting to 90 days from initial report or 30 days after a patch is released - whichever is earlier.

package/docs/adr/0007-multi-tool-adapter-framework.md

@@ -1,6 +1,6 @@
 # 7. Multi-tool adapter framework + token-preserving uninstall
 
-**Status:** Superseded · 2026-07-02 (v10.7.0 removed all non-native adapters - the pipeline targets Claude Code + Copilot CLI only). Original acceptance: 2026-04-27 (v7.7.0 / v7.9.0). Kept as the historical record of why the adapter framework existed; install flags documented below no longer exist.
+**Status:** Superseded · 2026-07-02 (v10.7.0 removed all non-native adapters - the pipeline targets Claude Code + Copilot CLI only; Codex CLI was later added as a third NATIVE target in v13.0.0, not through this adapter framework). Original acceptance: 2026-04-27 (v7.7.0 / v7.9.0). Kept as the historical record of why the adapter framework existed; install flags documented below no longer exist.
 
 ## Context
 

package/docs/architecture.md

@@ -54,7 +54,7 @@ graph TD
     DIFF["Code Diff"]
 
     DIFF --> R1["Fable (Claude Code) / Opus (Copilot)<br/>Security + Architecture"]
-    DIFF --> GPT["GPT-5.4<br/>Quality + Edge Cases"]
+    DIFF --> GPT["GPT-5.4<br/>Quality + Edge Cases<br/>(Copilot CLI only)"]
     DIFF --> SON["Sonnet<br/>Correctness + Style"]
 
     R1 --> TRIAGE["Fable Triage<br/>(Opus on Copilot CLI)"]
@@ -117,17 +117,17 @@ graph TB
     end
 
     subgraph "Pipeline Specs"
-        CMD[commands/<br/>50 command files]
+        CMD[commands/<br/>51 command files]
         AGT[agents/<br/>8 agent personas]
         RUL[rules/<br/>12 domain rules]
         PHS[multi-agent-refs/phases/<br/>phase specs + contracts]
         CMP[skills/shared/core/<br/>orchestration skills<br/>incl. compliance]
-        EXT["skills/shared/external/<br/>150 curated skills<br/>(authoring source for the<br/>multi-agent-plugins marketplace)"]
+        EXT["skills/shared/external/<br/>151 curated skills<br/>(authoring source for the<br/>multi-agent-plugins marketplace)"]
     end
 
     subgraph "Quality Gates"
-        SCH[schemas/<br/>17 JSON schemas]
-        EVL[eval/triage/<br/>12 regression fixtures]
+        SCH[schemas/<br/>19 JSON schemas]
+        EVL[eval/triage/<br/>11 regression fixtures]
         SMK[scripts/smoke-*<br/>100+ smoke suites]
     end
 
@@ -169,8 +169,8 @@ revisions of this diagram - Codex CLI and the two independently-shipped repos
 ```mermaid
 graph TD
     CC["Claude Code<br/>(source of truth)"]
-    COP["Copilot CLI<br/>(instructions + 50 skills)"]
-    COD["Codex CLI<br/>(1 router skill + 50 refs)"]
+    COP["Copilot CLI<br/>(instructions + 51 skills)"]
+    COD["Codex CLI<br/>(1 router skill + 51 refs)"]
     REPO["Pipeline Repo<br/>(npm package)"]
     WEB["Website"]
     PLUGREPO["multi-agent-plugins<br/>(5 stack plugins, own repo)"]
@@ -183,10 +183,10 @@ graph TD
     REPO -->|build-stack-plugins.mjs| PLUGREPO
     DTK -.->|sync only detects + ships, never authors| CC
 
-    REPO -->|npm publish| NPM["GitHub Packages"]
+    REPO -->|npm publish| NPM["npm registry (public)"]
     WEB -->|auto-deploy| VERCEL["Vercel"]
     PLUGREPO -->|git push| MKT["Claude marketplace"]
-    DTK -->|npm publish| NPM2["GitHub Packages (private)"]
+    DTK -->|npm publish| NPM2["npm registry (public)"]
 ```
 
 Full detail on how these three repos compose at install time and at run time -

package/docs/ecosystem.md

@@ -5,7 +5,7 @@ separately, wired together at install time and at run time:
 
 | Repo | What it owns | Ships as |
 |---|---|---|
-| **`multi-agent-pipeline`** (this repo) | Orchestration: the 8-phase flow, the 50 slash commands, quality gates, review/triage, cross-CLI parity | npm package (`@mmerterden/multi-agent-pipeline`), installs itself onto Claude Code / Copilot CLI / Codex CLI |
+| **`multi-agent-pipeline`** (this repo) | Orchestration: the 8-phase flow, the 51 slash commands, quality gates, review/triage, cross-CLI parity | npm package (`@mmerterden/multi-agent-pipeline`), installs itself onto Claude Code / Copilot CLI / Codex CLI |
 | **`multi-agent-plugins`** | Stack knowledge: per-platform component/lifecycle skills (iOS, Android, Frontend, Backend) + shared knowledge | Claude Code marketplace, 5 independently-versioned plugins |
 | **`dev-toolkit-mcp`** | The pipeline's hands on devices and browsers: 80 MCP tools across 6 categories (simulator/emulator control, accessibility audit, store compliance, web automation, Figma-vs-mock design audit, an agent-DSL batch runner) | npm package, registered as a standard stdio MCP server on every host |
 
@@ -18,7 +18,7 @@ Either can be swapped or removed without touching the other two's source.
 graph LR
     subgraph PIPE ["multi-agent-pipeline (orchestrator)"]
         direction TB
-        PHASES["8 phases · 50 commands"]
+        PHASES["8 phases · 51 commands"]
         GATES["deterministic gates + review triage"]
     end
 
@@ -63,8 +63,8 @@ only those:
 graph TD
     CC["Claude Code<br/>~/.claude/commands/multi-agent/<br/>(source of truth)"]
 
-    CC -->|"Step 2: copy + reformat<br/>50 sub-command skills"| COP["Copilot CLI<br/>~/.copilot/skills/"]
-    CC -->|"Step 2b: transform<br/>(install.js --codex)"| COD["Codex CLI<br/>1 router skill + 50 refs<br/>+ 8 agent TOML"]
+    CC -->|"Step 2: copy + reformat<br/>51 sub-command skills"| COP["Copilot CLI<br/>~/.copilot/skills/"]
+    CC -->|"Step 2b: transform<br/>(install.js --codex)"| COD["Codex CLI<br/>1 router skill + 51 refs<br/>+ 8 agent TOML"]
     CC -->|"Step 3: genericize<br/>(strip personal data)"| REPO["multi-agent-pipeline repo<br/>pipeline/"]
     CC -->|"Step 4: version + feature sync"| WEB["Website<br/>projects.ts / i18n.tsx"]
 
@@ -75,10 +75,10 @@ graph TD
     CC -.->|"sync only SHIPS this,<br/>never authors it"| SYNC3D
     SYNC3D -.-> DTK2
 
-    REPO -->|"npm publish"| NPM["GitHub Packages"]
+    REPO -->|"npm publish"| NPM["npm registry (public)"]
     WEB -->|"git push → auto-deploy"| VERCEL["Vercel"]
     PLUGREPO -->|"git push"| MKT["Claude Code marketplace"]
-    DTK2 -->|"npm publish"| NPM2["GitHub Packages<br/>(private)"]
+    DTK2 -->|"npm publish"| NPM2["npm registry<br/>(public)"]
 
     style CC fill:#f9f,stroke:#333
     style DTK2 fill:#dff,stroke:#333,stroke-dasharray: 5 5
@@ -105,7 +105,7 @@ hand-authored *inside* `multi-agent-plugins` and are never touched by sync.
 
 ```mermaid
 graph TD
-    EXT["pipeline/skills/shared/external/<br/>150 skills - single authoring source<br/>(the pipeline's own phases read these too)"]
+    EXT["pipeline/skills/shared/external/<br/>151 skills - single authoring source<br/>(the pipeline's own phases read these too)"]
 
     EXT -->|"cross-stack skills"| COMMONP["ai-common-toolkit<br/>10 skills · v0.2.3"]
     EXT -->|"Apple/Xcode-only"| IOSP["ai-ios-toolkit<br/>145 skills · v0.6.0"]
@@ -128,7 +128,7 @@ graph TD
 
 A skill counted in more than one platform plugin (a cross-stack knowledge skill
 plus, say, an iOS-specific one) is why the plugins' skill counts sum to more than
-the 150-skill source: `ai-common` skills are vendored into every stack plugin's
+the 151-skill source: `ai-common` skills are vendored into every stack plugin's
 `knowledge/`, not deduplicated across them. Versioning is per-plugin and
 patch-only from this generator - a repo enabling only `ai-ios-toolkit`
 never pulls an Android-only change.
@@ -150,9 +150,9 @@ measurements behind this table):
 
 | | Claude Code | Copilot CLI | Codex CLI |
 |---|---|---|---|
-| **Pipeline commands** | 50 slash-command skills, native | 50 skills, `multi-agent-{cmd}` naming, copied in | 1 router skill (`multi-agent`) + 50 command specs as reference files - Codex silently truncates its skills block past a few dozen entries, so sub-commands are not peer skills here |
+| **Pipeline commands** | 51 slash-command skills, native | 51 skills, `multi-agent-{cmd}` naming, copied in | 1 router skill (`multi-agent`) + 51 command specs as reference files - Codex silently truncates its skills block past a few dozen entries, so sub-commands are not peer skills here |
 | **Stack plugins** | Marketplace plugin, loaded natively, resolved by `.claude/settings.json` enabled-list | Enabled plugin's authored skills copied flat into `~/.copilot/skills/`; `knowledge/` **not** re-copied (already delivered via `shared/external`) | Copied as reference files under `~/.codex/multi-agent-refs/skills/`, plugin-prefixed on name clash (e.g. `architecture` → `ai-ios-toolkit-architecture`) |
-| **Component dispatch (Phase 3)** | Marketplace plugin's `create-component`/`create-screen` skill via the Skill tool | No plugin loader - falls back to local frozen `figma-*` skill copies | Not part of the enforced parity axis; classification + state-shape must match, skill *inventory* does not |
+| **Component dispatch (Phase 3)** | Marketplace plugin's `create-component`/`create-screen` skill via the Skill tool | No plugin loader - the enabled stack plugin's authored skills (incl. `create-component`) are copied flat into `~/.copilot/skills/` at install time (the old frozen `figma-*` copies are pruned, they were never a fallback) | Not part of the enforced parity axis; classification + state-shape must match, skill *inventory* does not |
 | **dev-toolkit-mcp** | `claude mcp add dev-toolkit -- npx -y @mmerterden/dev-toolkit-mcp` | `copilot mcp add dev-toolkit -- npx -y @mmerterden/dev-toolkit-mcp` | `codex mcp add dev-toolkit -- npx -y @mmerterden/dev-toolkit-mcp` (skipped with a warning if `codex` isn't on `PATH`) |
 
 `smoke-cross-cli-behavior.sh` and `smoke-codex-install.sh` gate the axes that **do**

package/index.js

@@ -53,6 +53,9 @@ if (command === "--version" || command === "-v" || command === "version") {
     npx @mmerterden/multi-agent-pipeline install --codex      Install for Codex CLI
     npx @mmerterden/multi-agent-pipeline install --all        Claude + Copilot + Codex
     npx @mmerterden/multi-agent-pipeline install --link       Use symlinks (saves tokens, dev mode)
+    npx @mmerterden/multi-agent-pipeline install --dry-run    Preview what would be written, write nothing
+    npx @mmerterden/multi-agent-pipeline install --index-only Ship only the skills index (dynamic skill loading)
+    npx @mmerterden/multi-agent-pipeline install --prune-external  Also remove pre-v15 catalog copies that differ from the shipped catalog
 
   Uninstall (token-preserving - Keychain/Credential Manager untouched):
     npx @mmerterden/multi-agent-pipeline uninstall            Interactive: remove from all installed targets
@@ -70,7 +73,7 @@ if (command === "--version" || command === "-v" || command === "version") {
 
   Options:
     --no-color           Disable colored output
-    --target=<path>      Target dir for legacy adapter cleanup on uninstall (defaults to cwd)
+    --target=<path>      Target dir override (install and legacy-adapter cleanup on uninstall; defaults to cwd)
     --platform=ios|android|all   Filter external skills by platform (default: all)
 
   After installation:

package/install/_common.mjs

@@ -15,6 +15,7 @@ import {
   existsSync,
   lstatSync,
   mkdirSync,
+  readFileSync,
   readdirSync,
   realpathSync,
   renameSync,
@@ -90,7 +91,7 @@ export function ensureRealDir(dir) {
  * @param {string} agentsSrc - pipeline/agents source directory
  * @returns {Set<string>}
  */
-export function pipelineAgentFileNames(agentsSrc) {
+function pipelineAgentFileNames(agentsSrc) {
   const names = new Set();
   if (existsSync(agentsSrc)) {
     for (const entry of readdirSync(agentsSrc, { withFileTypes: true })) {
@@ -269,7 +270,7 @@ export function pruneLegacyMultiAgentSkills(skillsDir) {
  *
  * @type {ReadonlyArray<{dir: string, root?: "claude"|"home", reason: string}>}
  */
-export const ABANDONED_TREES = Object.freeze([
+const ABANDONED_TREES = Object.freeze([
   {
     dir: "eval",
     reason: "eval corpora; the harnesses that read them are maintainer-only and no longer ship",
@@ -521,3 +522,44 @@ export function wipeDir(dir) {
     /* non-fatal */
   }
 }
+
+
+/**
+ * @param {string} a
+ * @param {string} b
+ * @returns {boolean} true when both trees have identical entries and file bytes
+ */
+export function dirsIdentical(a, b) {
+  const namesA = readdirSync(a).sort();
+  const namesB = readdirSync(b).sort();
+  if (namesA.length !== namesB.length || namesA.some((n, i) => n !== namesB[i])) return false;
+  for (const name of namesA) {
+    const pa = join(a, name);
+    const pb = join(b, name);
+    const sa = statSync(pa);
+    const sb = statSync(pb);
+    if (sa.isDirectory() !== sb.isDirectory()) return false;
+    if (sa.isDirectory()) {
+      if (!dirsIdentical(pa, pb)) return false;
+    } else if (!readFileSync(pa).equals(readFileSync(pb))) {
+      return false;
+    }
+  }
+  return true;
+}
+
+/**
+ * Same `local-only: true` frontmatter convention the command wrappers use:
+ * a dir carrying it is the user's and no prune path may take it.
+ *
+ * @param {string} dir
+ * @returns {boolean}
+ */
+export function isLocalOnlySkill(dir) {
+  try {
+    const skill = join(dir, "SKILL.md");
+    return existsSync(skill) && /^local-only:\s*true\s*$/m.test(readFileSync(skill, "utf-8"));
+  } catch {
+    return true;
+  }
+}