@mmerterden/multi-agent-pipeline 14.2.2 → 15.1.0

package/CHANGELOG.md

@@ -16,6 +16,186 @@ Internal file-layout changes that don't affect the slash-command surface are sti
 
 ## [Unreleased]
 
+## [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)
+
+- **Claude Code stack skills are plugin-only** (ADR-0009). The installer no longer
+  copies `shared/core` + `shared/external` into `~/.claude/skills`; the
+  `multi-agent-plugins` marketplace is Claude Code's only stack-skill source,
+  namespaced (`ai-ios-toolkit:<skill>`). Exactly two pipeline-owned compliance
+  catalogs stay local (`PIPELINE_LOCAL_SKILLS`). Old installs are migrated
+  manifest-scoped (`.external-skills-manifest.json`); user-authored dirs survive.
+- **Marketplace plugin names lose the `engineering` infix**:
+  `ai-<stack>-engineering-toolkit` -> `ai-<stack>-toolkit`. `enabledPlugins`
+  keys must migrate; `/multi-agent:stack` deletes the retired keys.
+- **`/multi-agent:ship` -> `/multi-agent:resume-local`** (the tail command opens a
+  PR but merges nothing, so "ship" oversold it). Prefs `global.ship` ->
+  `global.resumeLocal` via schema 2.6.0 (step migration + monolith, autoFix value
+  carried across the finish -> ship -> resume-local chain).
+
+### Added
+
+- `/multi-agent:stack` **multi-select**: several stacks per call (`ios backend`),
+  a native multi-select picker with no args, `web` alias, always-on
+  `ai-common-toolkit`, legacy-key cleanup, and a Copilot/Codex refresh offer.
+- Every marketplace plugin ships **`ai-<stack>-toolkit:help`**: a language-aware
+  catalog rendered live from `plugin.json` (drift-proof by construction).
+- `pipeline/scripts/_stack-routing.mjs`: the single routing table shared by
+  `build-stack-plugins.mjs`, the installers and the skills index.
+- Skills index entries carry `plugin` + `invokeAs`; `match-skills.mjs` returns
+  plugin-namespaced names. `skill-conformance.mjs` probes the marketplace
+  checkout and version-named plugin cache as skills roots.
+
+### Changed
+
+- Copilot CLI and Codex CLI local copies are **filtered to the enabled stacks**
+  (`pluginsToDeliver` + `partitionExternalSkillsByPlugins`); Codex previously
+  received the full catalog unconditionally and now also writes a delivery
+  manifest. One `/multi-agent:stack` selection governs all three hosts.
+- Prompt-context skill tables (phase 1/2/4), `humanizer` invocations,
+  `build-optimize` dispatches and the store-review references are
+  plugin-namespaced.
+- `DESC_CEILING` 82000 -> 82600 and phase-doc total 52750 -> 53100: the
+  namespaced tables and the new command descriptions did not fit ceilings that
+  were already at (or 193 bytes past) their limit; the always-on surface itself
+  shrank with the local copy gone.
+
+
+### Added
+
+- **`/multi-agent:complaint-analysis`** — customer-complaint / customer-reported-error
+  triage as a new one-shot ops command (51st command). Ingests complaints from
+  free-text paste, csv/xlsx/txt/json exports (`pipeline/lib/parse-complaints.sh`,
+  with built-in PII redaction: email / phone / card / national-id / PNR shapes),
+  Jira issues, or Confluence URLs; fetches Graylog evidence per
+  trxId/conversationId via the existing `fetch-graylog.sh`; correlates read-only
+  against the selected client + BFF repos (user-confirmed layer tagging:
+  ios / android / web / mobile-bff / web-bff); and classifies each complaint as
+  `client:<layer>` / `bff:<layer>` (root cause + citations + a fix plan grounded
+  in the existing architecture + a ready-to-run dev prompt), `core` (routing
+  recommendation to the backend core team, never a fix analysis), or
+  `insufficient-evidence`. Report dispatches to Local (default) / Confluence /
+  Jira behind a deterministic gate (`scripts/validate-complaint-doc.mjs`:
+  sections, verdict tokens, per-core routing entries, humanizer punctuation,
+  redaction-leak scan; smoke: `smoke-validate-complaint-doc.sh`). State contract:
+  `schemas/complaint-analysis-spec.schema.json`. Graylog-as-primary-evidence is a
+  documented, command-scoped exception to the advisory-only rule in
+  `features/external-context-injection.md`. `DESC_CEILING` raised 81000 -> 82000
+  (gate + pinned test together): the two new ~430-byte descriptions did not fit
+  in the ~25 bytes of headroom the surface had left; the average stays at 319
+  against the 420 ceiling.
+
 ## [14.2.2] - 2026-08-04
 
 ### Added
@@ -1911,7 +2091,7 @@ Single-source skill management, an upgraded `refactor` command, and two new Phas
 - **Component/Figma work is plugin-only.** The pipeline no longer bundles the
   `figma-ios` / `figma-android` / `figma-common` skill trees. Phase 3 dispatches
   component and Figma-to-code work to the per-stack marketplace plugins
-  (`ai-ios-engineering-toolkit` / `ai-android-engineering-toolkit`) via the Skill
+  (`ai-ios-toolkit` / `ai-android-toolkit`) via the Skill
   tool, so component skills live in one place. The 3-tier Figma design-access
   fallback still governs the analysis phase.
 - **Command layout migrated to `<name>/SKILL.md`.** Each subcommand is now its own
@@ -1952,7 +2132,7 @@ Skill mining + an install-safety fix.
   write-if-missing: new baseline rules are added, existing local rules are
   preserved untouched. New `copyDir({ skipExisting })` option backs this.
 - **Two skills mined from the corporate iOS toolkit and genericized into
-  `ai-common-engineering-toolkit` (v0.1.2):**
+  `ai-common-toolkit` (v0.1.2):**
   - `skill-creator` — the house rules for authoring skills (description-first
     discovery, lean SKILL.md as an index, progressive disclosure, reference vs
     workflow vs tool layers, no-prefix naming, grow-from-failure), with a
@@ -1987,7 +2167,7 @@ operating systems, all additive and opt-in.
   no-progress stall, an identical repeated failure, a rework storm, cost drift
   past the `costBudget` ceiling, or a merge/rebase conflict. Continuing
   unattended off the happy path is the less safe choice.
-- **Three technique skills** added to `ai-common-engineering-toolkit`
+- **Three technique skills** added to `ai-common-toolkit`
   (v0.1.1): `council` (multi-voice adversarial decision), `search-first`
   (research-before-coding with an adopt/extend/compose/build matrix), and
   `agent-introspection-debugging` (capture -> diagnose -> contained-recovery ->
@@ -2343,7 +2523,7 @@ Fable 5 restored as the top model tier; `stack-swap` fully removed; setup gains
   setup detects the project stack from markers (`.xcodeproj`/`Package.swift` → iOS,
   `build.gradle` → Android, `package.json`+react → Frontend, `requirements.txt`/
   `pyproject.toml` → Backend) and enables the matching marketplace plugin plus the
-  always-on `ai-common-engineering-toolkit`. **No clear marker → default iOS.** So a
+  always-on `ai-common-toolkit`. **No clear marker → default iOS.** So a
   fresh install works out of the box and a repo at any org gets its correct stack.
 
 ### Changed
@@ -2377,7 +2557,7 @@ Stack skills move from the local `stack-swap` mechanic to versioned marketplace
   `plugin.json` `skills[]`, and **bumps the patch version of any plugin whose
   skill set changed**. Idempotent (`--dry-run` supported); a no-op run bumps
   nothing. Cross-stack skills (accessibility audit, humanizer, Firebase) route
-  to `ai-common-engineering-toolkit`; Apple/Xcode-only skills stay in the iOS
+  to `ai-common-toolkit`; Apple/Xcode-only skills stay in the iOS
   plugin. This is the version-based-management backbone: the pipeline is the
   single authoring source, the marketplace is a derived, versioned artifact.
 - **`multi-agent:sync` Step 3c (PLUGINS)** — runs the generator, then commits +
@@ -2387,7 +2567,7 @@ Stack skills move from the local `stack-swap` mechanic to versioned marketplace
 
 - **`/multi-agent:stack`** — selecting a stack no longer moves skill directories
   via `stack-swap.sh`. It now enables the matching marketplace plugin(s) (stack
-  toolkit + `ai-common-engineering-toolkit`) in the current repo's
+  toolkit + `ai-common-toolkit`) in the current repo's
   `.claude/settings.json` `enabledPlugins`, disabling the stack toolkits that
   don't apply. Declarative, per-repo, versioned. No SessionStart hook.
 - **`/multi-agent:update`** — added a step that refreshes the plugin marketplace

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)
 
@@ -17,13 +17,18 @@ Runs natively on Claude Code, Copilot CLI and Codex CLI. macOS / Linux / Windows
 ## Quick Start
 
 ```bash
-# from the public registry (no auth)
-npx @mmerterden/multi-agent-pipeline install --all   # Claude Code + Copilot CLI + Codex CLI
+# from the public registry (no auth) - pick the CLIs you actually use
+npx @mmerterden/multi-agent-pipeline install --claude    # Claude Code only (default)
+npx @mmerterden/multi-agent-pipeline install --copilot   # Copilot CLI only
+npx @mmerterden/multi-agent-pipeline install --codex     # Codex CLI only
+npx @mmerterden/multi-agent-pipeline install --all       # all three
 
 # then, once:
 /multi-agent:setup          # keychain token scan + git identity + default stack
 ```
 
+Tool flags combine (`--claude --codex`). With no tool flag at all, the installer targets Claude Code only. Other flags: `--dry-run` (show what would be written, write nothing), `--platform=ios|android|all` (skip the stack skills you do not need), `--link` (symlink instead of copy, for local development).
+
 Run a task - the input type is auto-detected:
 
 ```bash
@@ -41,6 +46,8 @@ Add `autopilot` to skip confirmations, `--dev` for the fast dev-only path, or `-
 
 Update later with `/multi-agent:update`. Uninstall (tokens preserved) with `npx @mmerterden/multi-agent-pipeline uninstall`.
 
+**Stack skills are marketplace plugins.** On Claude Code the `ai-<stack>-toolkit` plugins (`multi-agent-plugins` marketplace) are the only stack-skill source - nothing is copied into `~/.claude/skills`. Pick the active stack(s) per repo with `/multi-agent:stack` (multi-select: `ios backend`, or a native picker with no args); each plugin ships a language-aware catalog at `ai-<stack>-toolkit:help`. Copilot CLI and Codex CLI have no plugin loader, so they receive a local copy filtered to the same enabled stacks.
+
 ## How it works
 
 One command runs 8 phases, with a gate between the risky ones:
@@ -63,14 +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) |
-| Ship | `/multi-agent:ship` | Run the review→test→commit→report tail over local work |
+| 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`. 49 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
 
@@ -84,17 +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 49 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 + 49 sub-command skills + scripts |
-| Codex CLI | `--codex` | one router skill + 49 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 49.** 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
@@ -128,7 +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)
 
@@ -17,13 +17,18 @@ Claude Code, Copilot CLI ve Codex CLI üzerinde native çalışır. macOS / Linu
 ## Hızlı Başlangıç
 
 ```bash
-# public registry'den (auth gerekmez)
-npx @mmerterden/multi-agent-pipeline install --all   # Claude Code + Copilot CLI + Codex CLI
+# public registry'den (auth gerekmez) - sadece kullandığın CLI'ları seç
+npx @mmerterden/multi-agent-pipeline install --claude    # sadece Claude Code (varsayılan)
+npx @mmerterden/multi-agent-pipeline install --copilot   # sadece Copilot CLI
+npx @mmerterden/multi-agent-pipeline install --codex     # sadece Codex CLI
+npx @mmerterden/multi-agent-pipeline install --all       # üçü birden
 
 # sonra, bir kere:
 /multi-agent:setup          # keychain token taraması + git kimliği + varsayılan stack
 ```
 
+Tool flag'leri birleştirilebilir (`--claude --codex`). Hiç tool flag'i verilmezse installer sadece Claude Code'u hedefler. Diğer flag'ler: `--dry-run` (ne yazılacağını gösterir, hiçbir şey yazmaz), `--platform=ios|android|all` (ihtiyacın olmayan stack skill'lerini atlar), `--link` (kopyalamak yerine symlink, lokal geliştirme için).
+
 Bir görev çalıştır - girdi tipi otomatik algılanır:
 
 ```bash
@@ -41,6 +46,8 @@ Onayları atlamak için `autopilot`, hızlı dev-only yol için `--dev`, ya da w
 
 Sonra `/multi-agent:update` ile güncelle. Kaldırmak için (tokenlar korunur) `npx @mmerterden/multi-agent-pipeline uninstall`.
 
+**Stack skill'leri marketplace plugin'leridir.** Claude Code'da `ai-<stack>-toolkit` plugin'leri (`multi-agent-plugins` marketplace) tek stack-skill kaynağıdır - `~/.claude/skills` altına kopya konmaz. Repo başına aktif stack'leri `/multi-agent:stack` ile seç (çoklu seçim: `ios backend`, ya da argümansız native picker); her plugin `ai-<stack>-toolkit:help` ile dilinde katalog sunar. Copilot CLI ve Codex CLI'da plugin loader olmadığından onlara aynı enabled stack'lere filtreli lokal kopya iner.
+
 ## Nasıl çalışır
 
 Tek komut 8 fazı çalıştırır, riskli olanlar arasında bir kapı ile:
@@ -63,14 +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) |
-| Ship | `/multi-agent:ship` | Lokal iş üzerinde review→test→commit→report kuyruğunu çalıştır |
+| 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 49 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
 
@@ -84,17 +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 49 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 + 49 alt-komut skill'i + script'ler |
-| Codex CLI | `--codex` | bir router skill + ref olarak 49 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 49 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
@@ -129,7 +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/FIGMA_PIPELINE.md

@@ -2,7 +2,7 @@
 
 End-to-end guide for generating production-ready UI components from Figma designs through the multi-agent pipeline. Covers iOS (SwiftUI) and Android (Jetpack Compose) with the same workflow shape.
 
-> Note: Component and Figma-to-code skills are no longer bundled in this repo. Phase 3 dispatches component work to the per-stack marketplace plugins (`ai-ios-engineering-toolkit` / `ai-android-engineering-toolkit` in the `multi-agent-plugins` marketplace) via the Skill tool. The workflow, subphases, and skill names described below are what those plugin skills run internally, not pipeline-bundled code. The 3-tier Figma design-access fallback still governs the analysis phase in this repo.
+> Note: Component and Figma-to-code skills are no longer bundled in this repo. Phase 3 dispatches component work to the per-stack marketplace plugins (`ai-ios-toolkit` / `ai-android-toolkit` in the `multi-agent-plugins` marketplace) via the Skill tool. The workflow, subphases, and skill names described below are what those plugin skills run internally, not pipeline-bundled code. The 3-tier Figma design-access fallback still governs the analysis phase in this repo.
 
 ## What you get
 
@@ -15,7 +15,7 @@ End-to-end guide for generating production-ready UI components from Figma design
 
 ## How it runs
 
-When multi-agent Phase 0 classifies a task as `component` (Figma URL in description, or figma-driven instruction path), Phase 3 delegates the entire phase to the enabled `ai-<platform>-engineering-toolkit` marketplace plugin's component skill (`create-component`, fallback `create-ui-component`) via the Skill tool. Component skills live in the plugin marketplace, not the pipeline. The dispatch layer records a coarse component-build row in `state.phases["3"].subphases[]` - multi-agent's phase-tracker reads that array with no special case. The subphase list below describes the flow the plugin skill runs internally.
+When multi-agent Phase 0 classifies a task as `component` (Figma URL in description, or figma-driven instruction path), Phase 3 delegates the entire phase to the enabled `ai-<platform>-toolkit` marketplace plugin's component skill (`create-component`, fallback `create-ui-component`) via the Skill tool. Component skills live in the plugin marketplace, not the pipeline. The dispatch layer records a coarse component-build row in `state.phases["3"].subphases[]` - multi-agent's phase-tracker reads that array with no special case. The subphase list below describes the flow the plugin skill runs internally.
 
 ### Internal phase order
 
@@ -122,7 +122,7 @@ Global settings that affect the figma pipeline:
 
 | Symptom | Likely cause | Fix |
 |---|---|---|
-| Phase 3 halts with "plugin not enabled" | The `ai-<platform>-engineering-toolkit` plugin is not enabled in this repo | Enable it in the repo's `.claude/settings.local.json` (`"ai-ios-engineering-toolkit@<marketplace>": true`) and reload the session |
+| Phase 3 halts with "plugin not enabled" | The `ai-<platform>-toolkit` plugin is not enabled in this repo | Enable it in the repo's `.claude/settings.local.json` (`"ai-ios-toolkit@<marketplace>": true`) and reload the session |
 | `multi-agent:create-component` not found | Marketplace not installed / plugin disabled | Install the marketplace and enable the platform toolkit; dispatch tries `create-component` then `create-ui-component` |
 | Wiki adapter failure | Remote unreachable (separate-repo mode) | Adapter caches pending output; next run retries. Non-blocking - Phase 7 continues. |
 | Jira auto-create hits 5xx | Transient Jira outage | Non-blocking - pipeline continues without link. User can run `/multi-agent:channels` post-hoc to add it. |

package/docs/adr/0006-skills-core-external-split.md

@@ -1,6 +1,6 @@
 # 6. `shared/core/` vs `shared/external/` source organization
 
-**Status:** Accepted · 2026-04 (v5.3.3)
+**Status:** Accepted · 2026-04 (v5.3.3) · The "install destination is unchanged" clause is superseded by [ADR-0009](./0009-claude-stack-skills-plugin-only.md) (v15.0.0): Claude Code no longer receives the external tree; Copilot/Codex receive a stack-filtered subset.
 
 ## Context
 

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/adr/0009-claude-stack-skills-plugin-only.md

@@ -0,0 +1,31 @@
+# 9. Claude Code stack skills are plugin-only; the local copy is retired
+
+**Status:** Accepted · 2026-08 (v15.0.0) · Supersedes the "install destination is unchanged" clause of ADR-0006
+
+## Context
+
+ADR-0006 split the source tree into `shared/core/` + `shared/external/` but kept the install unchanged: both trees flattened into `~/.claude/skills/`. Since then the same external catalog also became the authoring source for the `multi-agent-plugins` marketplace (`build-stack-plugins.mjs` derives each plugin's `knowledge/` layer from it), and Claude Code loads those plugins natively, namespaced (`ai-ios-toolkit:swiftui-pro`).
+
+That left Claude Code receiving every stack skill **twice**:
+
+- 110 of 157 local skill dirs duplicated the enabled plugins byte-for-byte - ~10k tokens of duplicate descriptions per session, 4.4 MB on disk.
+- The local copy shadowed the plugin the moment it went stale, and it *was* stale in practice: the plugin cache and the local copy advanced on different schedules.
+- The duplication hid real bugs: `skill-conformance.mjs` and `match-skills.mjs` only knew the local root, so they kept working by accident - against the stale copy.
+
+## Decision
+
+1. **Claude Code receives no local copy of the stack skills.** The marketplace plugins (`ai-<stack>-toolkit`, enablement managed by `/multi-agent:stack`, multi-select) are its only stack-skill source. Prompt tables, `Skill` invocations and the skills index all use the plugin-namespaced name.
+2. **Exactly two skills stay local on Claude Code**: `apple-archive-compliance` and `google-play-compliance` (`PIPELINE_LOCAL_SKILLS` in `install/claude.mjs`). They are pipeline-owned compliance catalogs, kept out of the public marketplace by policy (they may carry audit rules not meant for it), and `uninstall.mjs` already treats exactly this pair as pipeline-owned.
+3. **`shared/external/` stays in the repo as the authoring source.** It feeds `build-stack-plugins.mjs` and the Copilot/Codex copies; it is simply never copied to `~/.claude/skills` again. Installs migrate old machines by removing the dirs named in `.external-skills-manifest.json` (manifest-scoped - user-authored dirs survive).
+4. **Copilot CLI and Codex CLI keep local copies** (no plugin loader / silently truncating skill list), now **filtered to the enabled stacks**: `pluginsToDeliver` reads `enabledPlugins` from `~/.claude/settings.json` (fallback `--platform`), `partitionExternalSkillsByPlugins` routes each skill through the same `_stack-routing.mjs` table the marketplace is built with. One stack selection governs all three hosts.
+5. **Scripts that resolve skills know the plugin roots**: `skill-conformance.mjs` probes the marketplace checkout and version-named plugin cache (newest first) alongside the install roots; `build-skills-index.mjs` stamps `plugin` + `invokeAs` per entry so `match-skills.mjs` returns namespaced names.
+
+## Consequences
+
+Positive: one source of truth per skill at runtime; ~13.5k tokens/session and ~5.9 MB reclaimed on Claude Code; a disabled stack is genuinely absent instead of half-present; the smoke suite now asserts the compliance-only contract (`smoke-install-layout.sh` 5b2b) and the filter's both directions (5b2).
+
+Negative / accepted:
+
+- A stack not enabled in `enabledPlugins` is invisible to Claude Code until `/multi-agent:stack` enables it. This is the intended behavior, not a regression.
+- `dynamicSkillLoading`'s index now names skills the local tree does not hold; consumers must use `invokeAs`, not a filesystem path.
+- Copilot/Codex copies go stale when the stack selection changes until `install --copilot --codex` is re-run; `/multi-agent:stack` offers that refresh after every change.

package/docs/adr/README.md

@@ -18,6 +18,7 @@ Format: lightly adapted from [Michael Nygard's ADR template](https://cognitect.c
 | [0006](./0006-skills-core-external-split.md) | `shared/core/` vs `shared/external/` source org    | Accepted |
 | [0007](./0007-multi-tool-adapter-framework.md) | Multi-tool adapter framework + token-preserving uninstall | Superseded by v10.7.0 (adapters removed; Claude Code + Copilot CLI only) |
 | [0008](./0008-installer-modularization-and-secret-leak-defense.md) | Installer modularization + secret-leak defense | Accepted (amended v10.7.0: adapter module removed) |
+| [0009](./0009-claude-stack-skills-plugin-only.md) | Claude Code stack skills are plugin-only; local copy retired | Accepted (supersedes ADR-0006 install-destination clause) |
 
 ## Writing a New ADR
 

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)"]
@@ -71,7 +71,7 @@ graph TD
 
 ## Figma SubPhase Integration (Phase 3)
 
-When a task is classified `component`, Phase 3 dispatches to the marketplace component plugin (`ai-<platform>-engineering-toolkit`) via the Skill tool. Component skills are not bundled in this repo; the subphases below describe the flow the plugin skill runs internally:
+When a task is classified `component`, Phase 3 dispatches to the marketplace component plugin (`ai-<platform>-toolkit`) via the Skill tool. Component skills are not bundled in this repo; the subphases below describe the flow the plugin skill runs internally:
 
 ```mermaid
 graph TD
@@ -117,17 +117,17 @@ graph TB
     end
 
     subgraph "Pipeline Specs"
-        CMD[commands/<br/>49 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
 
@@ -163,14 +163,14 @@ User Input → Phase 0 (Init)
 ## Ecosystem Sync Targets
 
 `/multi-agent:sync` actually walks **five** targets, not the three shown in earlier
-revisions of this diagram — Codex CLI and the two independently-shipped repos
+revisions of this diagram - Codex CLI and the two independently-shipped repos
 (`multi-agent-plugins`, `dev-toolkit-mcp`) are real sync targets too:
 
 ```mermaid
 graph TD
     CC["Claude Code<br/>(source of truth)"]
-    COP["Copilot CLI<br/>(instructions + 49 skills)"]
-    COD["Codex CLI<br/>(1 router skill + 49 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)"]
@@ -183,12 +183,12 @@ 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 —
+Full detail on how these three repos compose at install time and at run time -
 including the Phase 3 → plugin dispatch contract and the Phase 5 → dev-toolkit MCP
-contract — lives in [`docs/ecosystem.md`](./ecosystem.md).
+contract - lives in [`docs/ecosystem.md`](./ecosystem.md).