@mmerterden/multi-agent-pipeline 14.2.2 → 15.1.0

package/pipeline/commands/multi-agent/help/SKILL.md

@@ -91,7 +91,7 @@ Dedicated commands (same as flags above):
   /multi-agent:local-autopilot "task"           = multi-agent "task" --local autopilot
   /multi-agent:dev-local "task"                 = multi-agent "task" --dev --local
   /multi-agent:dev-local-autopilot "task"       = multi-agent "task" --dev --local autopilot
-  /multi-agent:ship [jira-id] [autopilot]     Continue already-done LOCAL work: Review → Build+Test → PR → Jira analysis + test scenarios (no dev)
+  /multi-agent:resume-local [jira-id] [autopilot]     Continue already-done LOCAL work: Review → Build+Test → PR → Jira analysis + test scenarios (no dev)
 
 ------------------------------------------------------------
 
@@ -102,6 +102,7 @@ Status & Resume:
   /multi-agent:resume [#id]   Resume a paused or failed task from where it stopped
   /multi-agent:kill [#id]     Stop task + delete worktree (logs preserved)
   /multi-agent:prune-logs     Delete per-task project logs (audit + metrics kept; age/project/task filters, dry-run first)
+  /multi-agent:prune-prompts  Zero-base prompt review: measure always-on instruction footprint, propose keep/trial/delete per rule (report first, apply on approval)
   /multi-agent:garbage-collect  Sweep leftover /tmp scratch from past runs (dry-run first)
   /multi-agent:purge          Worktree + logs  -  full reset (double confirm)
 
@@ -113,6 +114,7 @@ Post-Hoc & Side-Channel:
   /multi-agent:review-issue   Grade a GitHub issue's pipeline-readiness -> comment the gaps on it
   /multi-agent:analysis ["analysis-name"]  Feature-spec analysis (Figma + Swagger + Confluence + repos) → per-platform v3 doc (23-section Full / 7-section Lite)
   /multi-agent:analysis-resolve [doc]      Resolve Section 20 open questions of an analysis doc, one at a time with source-labeled candidates
+  /multi-agent:complaint-analysis ["run-name"] [--file path]  Customer-complaint triage: Graylog evidence per trx/conv id + read-only repo correlation → client/bff root cause + fix plan + dev prompt, or core routing recommendation
   /multi-agent:build-optimize iOS-only Xcode build perf wrapper → benchmark + analyze + recommend-first .build-benchmark/optimization-plan.md
   /multi-agent:create-jira ["desc"] [figma-url] [swagger-url]  Create a Jira Task/Bug/Story matching team conventions (asks type + mining + active sprint + auto-sizing sections + preview & approval)
   /multi-agent:diff-explain   Map a Phase 4 triage finding back to specific diff lines
@@ -132,13 +134,18 @@ Setup & Maintenance:
 
   /multi-agent:setup          First-run wizard  -  Keychain tokens + Git identity + language
   /multi-agent:language [en|tr]   Show or set outputLanguage (promptLanguage stays English)
-  /multi-agent:stack <id>     Select stack by enabling the matching marketplace plugin(s) (ios / android / mobile / backend / frontend / fullstack / all)
+  /multi-agent:stack [ids...]  Enable stack plugin(s); multi-select: ids together (ios backend) or no arg -> native picker (common always on)
   /multi-agent:sync           Sync ecosystem (Claude Code + Copilot CLI + pipeline + website + dev-toolkit MCP)
   /multi-agent:update         Pull latest pipeline + reinstall + run migrations
   /multi-agent:uninstall      Uninstall pipeline from every CLI (--all-data also clears settings + logs; Keychain tokens always intact, double confirm)
 
 ------------------------------------------------------------
 
+Stack plugin skills: call directly as ai-<stack>-toolkit:<skill>. Catalog:
+  ai-<stack>-toolkit:help. Active plugins per repo: /multi-agent:stack.
+
+------------------------------------------------------------
+
 Routines (your own reusable jobs):
 
   /multi-agent:save [name]    Save a recurring job as a reusable /multi-agent:<name> command
@@ -353,7 +360,7 @@ Dedicated komutlar (yukarıdaki flag'lerin eşdeğeri):
   /multi-agent:local-autopilot "task"           = multi-agent "task" --local autopilot
   /multi-agent:dev-local "task"                 = multi-agent "task" --dev --local
   /multi-agent:dev-local-autopilot "task"       = multi-agent "task" --dev --local autopilot
-  /multi-agent:ship [jira-id] [autopilot]     Lokalde biten işi sürdür: Review → Build+Test → PR → Jira teknik analiz + test senaryoları (dev yok)
+  /multi-agent:resume-local [jira-id] [autopilot]     Lokalde biten işi sürdür: Review → Build+Test → PR → Jira teknik analiz + test senaryoları (dev yok)
 
 ------------------------------------------------------------
 
@@ -364,6 +371,7 @@ Status & Resume:
   /multi-agent:resume [#id]   Duraklamış / hata almış task'ı kaldığı yerden devam ettir
   /multi-agent:kill [#id]     Task'ı durdur + worktree'yi sil (log'lar korunur)
   /multi-agent:prune-logs     Task bazlı proje log'larını sil (audit + metrics korunur; yaş/proje/task filtresi, önce dry-run)
+  /multi-agent:prune-prompts  Sıfır-tabanlı prompt incelemesi: sürekli yüklü talimat yükünü ölç, kural başına tut/dene/sil öner (önce rapor, onayla uygula)
   /multi-agent:garbage-collect  Geçmiş koşumların /tmp artıklarını süpür (önce dry-run)
   /multi-agent:purge          Worktree + log'lar  -  tam reset (çift onay)
 
@@ -375,6 +383,7 @@ Post-Hoc & Side-Channel:
   /multi-agent:review-issue   GitHub issue'nun pipeline'a hazırlığını değerlendir -> eksikleri yorum olarak ekle
   /multi-agent:analysis ["analysis-name"]  Feature-spec analizi (Figma + Swagger + Confluence + repolar) → platform başına v3 doküman (23 bölüm Full / 7 bölüm Lite)
   /multi-agent:analysis-resolve [doc]      Analiz dokümanının Bölüm 20 açık sorularını kaynak etiketli adaylarla teker teker çözer
+  /multi-agent:complaint-analysis ["run-adı"] [--file yol]  Müşteri şikayeti triyajı: trx/conv id ile Graylog kanıtı + salt-okunur repo eşleştirme → client/bff kök neden + fix planı + dev prompt'u, veya core'a yönlendirme önerisi
   /multi-agent:build-optimize iOS-only Xcode build performance wrapper → benchmark + analiz + recommend-first .build-benchmark/optimization-plan.md
   /multi-agent:create-jira ["açıklama"] [figma-url] [swagger-url]  Takım standartlarına uygun Jira Task/Bug/Story oluştur (tip sorar + convention mining + aktif sprint + auto-sizing bölümler + önizleme & onay)
   /multi-agent:diff-explain   Phase 4 triage bulgusunu diff satırlarına eşle
@@ -394,13 +403,19 @@ Setup & Maintenance:
 
   /multi-agent:setup              İlk kurulum sihirbazı  -  Keychain token + Git kimliği + dil
   /multi-agent:language [en|tr]   outputLanguage'ı göster veya ayarla (promptLanguage İngilizce kalır)
-  /multi-agent:stack <id>         Stack'i eşleşen marketplace plugin'i etkinleştirerek seç (ios / android / mobile / backend / frontend / fullstack / all)
+  /multi-agent:stack [ids...]     Stack plugin'lerini etkinleştir; çoklu seçim: id'ler yan yana (ios backend) ya da argümansız -> native picker (common hep açık)
   /multi-agent:sync               Ekosistemi senkronize et (Claude Code + Copilot CLI + pipeline + website + dev-toolkit MCP)
   /multi-agent:update             En son pipeline'ı çek + reinstall + migration çalıştır
   /multi-agent:uninstall          Pipeline'ı tüm CLI'lerden kaldır (--all-data ayar + logları da siler; Keychain token her zaman dokunulmaz, çift onay)
 
 ------------------------------------------------------------
 
+Stack plugin skill'leri: doğrudan ai-<stack>-toolkit:<skill> olarak çağrılır
+  (örn. ai-ios-toolkit:create-component). Lokal kopya ve sarmalayıcı yok. Katalog:
+  ai-<stack>-toolkit:help. Aktif plugin'ler repo bazında: /multi-agent:stack.
+
+------------------------------------------------------------
+
 Rutinler (kendi tekrar eden işlerin):
 
   /multi-agent:save [ad]          Sık yaptığın bir işi yeniden kullanılabilir /multi-agent:<ad> komutu olarak kaydet

package/pipeline/commands/multi-agent/ios-coding-standard/SKILL.md

@@ -9,9 +9,9 @@ allowed-tools: Skill, Bash, Read, Edit, Write, AskUserQuestion
 
 **Input**: $ARGUMENTS  -  optionally a module name or path. When absent, Phase 1 discovers and asks.
 
-This routine is the **procedure**. The rules live in the `ios-coding-standard` skill, whose registry is
+This routine is the **procedure**. The rules live in the `ai-ios-toolkit:ios-coding-standard` skill, whose registry is
 `references/rules.yml` and whose teaching doc is `references/STANDARD.md`. Load that
-skill first; it is installed on every host and carried by the iOS stack plugin, so
+skill first; Claude Code loads it from the iOS stack plugin, Copilot/Codex from their local copy, so
 there is one registry rather than a copy per CLI. Never restate a rule here  -  cite its ID. A rule that is not in the
 registry is not a rule; if the audit needs one, propose it as `status: proposed` and say so.
 

package/pipeline/commands/multi-agent/jira/SKILL.md

@@ -79,7 +79,7 @@ After issue selection, inspect `maturity` from `~/.claude/lib/issue-fetcher.sh`:
 > **Empty description → parent candidate**: development sub-tasks are often filed with no description of their own, with the real requirements on the parent issue. Before scoring, `issue-fetcher.sh` fetches the issue's `parent` (single hop, no chasing the parent's parent). If the issue's own description is empty and the parent's isn't, it does **not** auto-substitute  -  it exposes `descriptor.parentKey` + `descriptor.parentDescription` as a candidate and adds `description_empty_parent_available` to `warnings` (not `blockers`) instead of the plain `description_empty` blocker. If the parent is also empty or unreachable, `description_empty` still blocks exactly as before.
 >
 > When `description_empty_parent_available` is present, ask a tailored question instead of the generic "Continue?" below:
-> - `question` (outputLanguage): "Bu issue'nun (`{KEY}`) açıklaması boş, ama parent'ın (`{parentKey}`) açıklaması var. Parent'ın açıklamasından devam edilsin mi?" / "This issue's (`{KEY}`) description is empty, but its parent (`{parentKey}`) has one. Continue using the parent's description?" — show a short excerpt of `parentDescription` for context.
+> - `question` (outputLanguage): "Bu issue'nun (`{KEY}`) açıklaması boş, ama parent'ın (`{parentKey}`) açıklaması var. Parent'ın açıklamasından devam edilsin mi?" / "This issue's (`{KEY}`) description is empty, but its parent (`{parentKey}`) has one. Continue using the parent's description?" - show a short excerpt of `parentDescription` for context.
 > - `header` (English, <=12 chars): `"Parent desc"`
 > - `options`: `{ label: "Use parent's description" (Recommended), description: "Continue with descriptor.parentDescription as the working description for this task." }` / `{ label: "No, halt", description: "Treat like description_empty  -  fix the issue's own description in Jira first." }`
 > - **Accept** → set the working `description` to `parentDescription` for every later phase (analysis/dev/review all read this one substituted value); log the substitution (source issue + parent key) to `agent-log.md`.

package/pipeline/commands/multi-agent/prune-prompts/SKILL.md

@@ -0,0 +1,81 @@
+---
+description: "Zero-base prompt review: measure the always-on instruction footprint, classify every rule block, propose keep/trial-removal/delete; applies only approved rows. Use when a new model ships or instructions have accumulated."
+description-tr: "Sıfır-tabanlı prompt incelemesi: sürekli yüklü talimat yükünü ölçer, her kural bloğunu sınıflar, tut/dene/sil önerir; yalnızca onaylananı uygular."
+argument-hint: "[--report-only]"
+---
+
+# multi-agent prune-prompts - Zero-Base Prompt Review
+
+Instruction files only grow. Every rule was added because some model once got
+something wrong, and nobody deletes a rule once a workaround ships. A newer
+model needs fewer of them; the ones it no longer needs are pure context tax on
+every session, and stale rules actively mislead.
+
+The discipline this command applies (after Boris Cherny's advice): on a model
+upgrade, assume ZERO instructions are needed, and let each line earn its way
+back. A line earns its way back only after the model gets the same thing wrong
+repeatedly (three strikes) WITHOUT it. Instructions are a cache of past model
+failures; a new model invalidates that cache.
+
+## Flow
+
+### 1. MEASURE - the always-on footprint
+
+Estimate tokens (chars/4) for each layer the model carries into every session:
+
+```bash
+wc -c "$HOME/.claude/CLAUDE.md" 2>/dev/null
+wc -c "$HOME"/.claude/rules/*.md 2>/dev/null
+find "$PWD" -maxdepth 2 -name "CLAUDE.md" -exec wc -c {} + 2>/dev/null
+```
+
+Report a table: layer, file, estimated tokens, share of total. Flag any single
+file above ~2,000 estimated tokens.
+
+### 2. CLASSIFY - what kind of line is each rule
+
+Walk CLAUDE.md + each rules/ file section by section. Classify every
+instruction block:
+
+| Class | Meaning | Default verdict |
+|---|---|---|
+| **Constraint** | Facts the model cannot infer (hosts, key names, branch formats, team conventions) | keep |
+| **Failure patch** | "Never do X" added after a model did X | trial removal - the current model may not need it |
+| **Restatement** | Something the model does correctly anyway (write tests, guard early) | delete |
+| **Stale** | References files, commands or workflows that no longer exist | delete |
+
+For failure patches, note WHEN the patch was added if git history shows it -
+a patch older than the current model's release is the strongest removal
+candidate.
+
+### 3. REPORT - the zero-base proposal
+
+One table, every block accounted for: file, section, class, verdict
+(keep / trial-removal / delete), and the one-line reason. Never a sample -
+if a section is not in the table, the review did not happen.
+
+With `--report-only`, stop here.
+
+### 4. APPLY - only what the user approves
+
+Present the table, ask which verdicts to apply (all deletes / all
+trial-removals too / pick rows). For approved rows, edit the files. Trial
+removals move the block into `~/.claude/rules/.pruned/<file>.md` with a
+dated header rather than deleting outright, so a strike-out can be reverted
+by moving the block back.
+
+### 5. THE THREE-STRIKE RULE going forward
+
+After a prune, when the model gets something wrong that a removed rule used
+to cover, do NOT restore it on the first miss. Record the miss (the
+`.pruned/` file has a `strikes:` line per block). Restore the line only on
+the third occurrence of the SAME failure. One line back at a time - never
+the whole file.
+
+## Boundaries
+
+- Never touches skill bodies or command files - those load on demand and are
+  not part of the always-on footprint. The lint gate (`lint-skills.mjs`)
+  owns their budgets.
+- Never touches `multi-agent-preferences.json` or anything under `logs/`.
+- Applies nothing without explicit approval on the report table.

package/pipeline/commands/multi-agent/refactor/SKILL.md

@@ -18,10 +18,11 @@ Deep-analyses the current project, extracts the global best-practices worth adop
 Step 0:  BEST-PRACTICES  Research the field, extract the best approaches, ADAPT them to our stack -> plan band A
 Step 0b: DRIFT           Check upstream-derived skills for updates we have not pulled -> plan band D
 Step 0c: DEV-TOOLKIT     Research current MCP practice + audit the companion dev-toolkit repo -> plan band E
+Step 0d: RUN-ERRORS      Read the local run-error ledger, rank recurring failures -> plan band F
 Step 1:  SCAN            Walk the project structure (files, LOC, dependencies, CI, tests)
 Step 2:  ANALYZE         10 categories + an explicit BUG HUNT (real defects, not just scores) -> plan bands B, C
 Step 3:  SCORE           Each category /10, overall /100
-Step 4:  PLAN            Merge bands A (best-practice) + B (bugs) + C (improvements) + D (drift) + E (dev-toolkit)
+Step 4:  PLAN            Merge bands A (best-practice) + B (bugs) + C (improvements) + D (drift) + E (dev-toolkit) + F (run-errors)
 Step 5:  ASK             "Start the work?"  -  wait for user approval
 Step 6:  IMPLEMENT       Apply approved items one by one (lint, test, commit)
 Step 7:  VERIFY          Confirm every test + lint passes
@@ -34,6 +35,7 @@ Plan bands (all five feed the single Step 4 table):
 - **C - Improvement**: quality/perf/DX gaps surfaced by the 10-category analysis.
 - **D - Drift**: upstream updates to skills we derived from an external source.
 - **E - Dev-toolkit**: current-practice gaps in the companion dev-toolkit MCP server (the pipeline's device and browser hands), applied in that repo.
+- **F - Run-errors**: recurring real failures the pipeline actually hit across past runs, read from the local run-error ledger. These are lived evidence, not speculation - a failure that recurs across users or tasks is a prioritized improvement area.
 
 ## Step 0: BEST-PRACTICES  -  research the field, adapt to us
 
@@ -178,6 +180,39 @@ Rules for this band:
 - A finding that changes the tool surface (new / renamed / removed tool) pairs with a pipeline-side item: bump the minimum toolkit version wherever a pipeline skill declares one.
 - If the current working directory IS the toolkit repo, skip band E and let bands A/B/C cover it  -  never report the same finding twice.
 
+## Step 0d: RUN-ERRORS  -  what the pipeline actually failed on
+
+Before speculating about improvements, read what real runs already failed on. When usage logging is enabled, every terminated run appends its errors to a local ledger:
+
+```bash
+LEDGER="$HOME/.claude/logs/multi-agent/errors-ledger.jsonl"
+[ -f "$LEDGER" ] || echo "no run-error ledger yet - skip band F"
+```
+
+Each line is one run: `{ t, id, u, c, rp, ph, v, errs[] }`. The `errs[]` entries are cause tags (`<phase>:<cause>` halt reasons, `phase-<id>-failed`, `run-failed`).
+
+1. Read the ledger (best-effort; a missing or unreadable file means skip band F, not a failure).
+2. Group by error tag. For each tag compute: occurrences, distinct users affected, distinct repos, the phase it usually strikes, first + last seen, and which pipeline versions it spans (a tag that persists across versions is unfixed; one that stopped at a version is already resolved  -  do not re-raise it).
+3. Rank by `occurrences x users-affected`. A failure that recurs across users or tasks is lived evidence, not a hypothesis  -  it outranks a speculative improvement.
+4. For each surviving tag, trace it to the phase doc / script that emits that cause and propose the concrete fix.
+
+This band mirrors the admin dashboard's "Gelişim alanları" panel, but reads the local ledger so it needs no auth and works offline. If `$ARGUMENTS` names a focus area, still read the ledger  -  a recurring run error in that area is the strongest possible signal.
+
+Output (plan band F):
+
+```
+| # | Error tag | Occurrences | Users | Usual phase | Versions | Root cause (file) | Fix | In plan? |
+|---|-----------|-------------|-------|-------------|----------|-------------------|-----|----------|
+| 1 | 4:reviewer-json-invalid | 12 | 3 | 4 | 14.x-15.x | reviewer prompt lets prose leak | tighten schema instruction in phase-4-review.md | Yes (P0) |
+| 2 | phase-3-failed | 5 | 2 | 3 | 15.0.x | build step misses a stack toolchain | add preflight in phase-3-dev.md | Yes (P1) |
+```
+
+Rules for this band:
+
+- The ledger is evidence of the past, not a spec. A tag that stopped recurring after a version bump is resolved  -  report it as resolved, do not add a plan item.
+- Never quote a user's identity as blame. The `u` field is for counting distinct affected users, not for naming anyone in the plan.
+- If the ledger is empty or absent, skip band F silently  -  it is additive signal, never a gate.
+
 ## Step 1: SCAN
 
 ```

package/pipeline/commands/multi-agent/resume/SKILL.md

@@ -10,7 +10,7 @@ argument-hint: "[#id]  -  optional: task ID (e.g. #2). If omitted, the most rece
 
 Resume a paused or failed task from the last successful phase.
 
-> **Not the same as `/multi-agent:ship`.** `resume` continues a **tracked pipeline task** (needs its `agent-state.json`/worktree) from where it stopped. `/multi-agent:ship` takes **ad-hoc local work** on the current branch (no prior task required) and runs the pipeline tail - Review → Build+Test → PR → Jira report - over it.
+> **Not the same as `/multi-agent:resume-local`.** `resume` continues a **tracked pipeline task** (needs its `agent-state.json`/worktree) from where it stopped. `/multi-agent:resume-local` takes **ad-hoc local work** on the current branch (no prior task required) and runs the pipeline tail - Review → Build+Test → PR → Jira report - over it.
 
 ## Steps
 

package/pipeline/commands/multi-agent/{ship → resume-local}/SKILL.md

@@ -4,11 +4,11 @@ description-tr: "Halihazırda bitmiş LOKAL işi pipeline kuyruğundan geçirir:
 allowed-tools: Agent, Bash, Read, Write, Edit, Glob, Grep, TaskCreate, TaskUpdate, TaskList, TaskGet, AskUserQuestion, WebFetch, WebSearch, Skill
 ---
 
-# multi-agent ship  -  Take Existing Branch Work Through the Pipeline Tail
+# multi-agent resume-local  -  Take Existing Branch Work Through the Pipeline Tail
 
 > **Language (read FIRST)**: Before any status output, read `prefs.global.outputLanguage` and render every conversational line in it. `AskUserQuestion` `label`/`header` stay English, but its `question` and option `description`s render in `outputLanguage`; external payload bodies follow `outputLanguage` too (identifiers, commit messages, branch names stay English). Full contract: `$HOME/.claude/multi-agent-refs/rules.md` "Language Application".
 
-You already did the work locally  -  wrote code on the current branch and maybe tested it by hand, or committed it outside the pipeline entirely. (As of v14.0.0 the `--dev` family reviews its own output, so this command is for work that had no pipeline run behind it, not a patch for a mode that skipped review.) `/multi-agent:ship` picks up from there and runs the **pipeline tail** over that existing local work in one command: parallel review, a build + test success gate, commit/push + PR, then the technical analysis and a **Jira comment with test scenarios**. It does NOT re-develop  -  Analysis / Planning / Dev (phases 1-3) are intentionally skipped; the diff already on the branch IS the input.
+You already did the work locally  -  wrote code on the current branch and maybe tested it by hand, or committed it outside the pipeline entirely. (As of v14.0.0 the `--dev` family reviews its own output, so this command is for work that had no pipeline run behind it, not a patch for a mode that skipped review.) `/multi-agent:resume-local` picks up from there and runs the **pipeline tail** over that existing local work in one command: parallel review, a build + test success gate, commit/push + PR, then the technical analysis and a **Jira comment with test scenarios**. It does NOT re-develop  -  Analysis / Planning / Dev (phases 1-3) are intentionally skipped; the diff already on the branch IS the input.
 
 ## When to use it
 
@@ -24,10 +24,10 @@ You already did the work locally  -  wrote code on the current branch and maybe
 ## Input
 
 ```bash
-/multi-agent:ship                       # current branch vs its base; resolve Jira id from branch name
-/multi-agent:ship PROJ-12345          # bind to an explicit Jira id for the Phase 7 comment
-/multi-agent:ship --base develop         # override the base branch for the diff
-/multi-agent:ship autopilot              # no gate prompts: auto-fix blocking findings, auto-PR, auto-comment
+/multi-agent:resume-local                       # current branch vs its base; resolve Jira id from branch name
+/multi-agent:resume-local PROJ-12345          # bind to an explicit Jira id for the Phase 7 comment
+/multi-agent:resume-local --base develop         # override the base branch for the diff
+/multi-agent:resume-local autopilot              # no gate prompts: auto-fix blocking findings, auto-PR, auto-comment
 ```
 
 ## Pipeline
@@ -54,7 +54,7 @@ Phases 1-3 (Analysis / Planning / Dev) are skipped by design  -  `ship` treats t
 
 - **Phase 4 Review** - run per `$HOME/.claude/multi-agent-refs/phases/phase-4-review.md` against the resolved diff: deterministic gates (Step 1.x), stack-specific parallel reviewers (Fable + Sonnet on Claude Code; GPT + Opus + Sonnet on Copilot CLI), Fable triage → `triage.accepted`. Blocking/important accepted findings:
   - interactive: present them and ask (`AskUserQuestion`) whether to fix now (loop back through a minimal Phase-3-style TDD fix) or proceed;
-  - `autopilot` (or `prefs.global.ship.autoFix == true`): auto-fix accepted blocking/important findings, then re-review the fix, before advancing.
+  - `autopilot` (or `prefs.global.resumeLocal.autoFix == true`): auto-fix accepted blocking/important findings, then re-review the fix, before advancing.
 - **Phase 5 Build+Test** - the **automated success gate** (this is what "build+test success" means here; the interactive device user-test is `/multi-agent:manual-test`). Stack-aware: build via `figma-config.build` (iOS scheme / Android gradle / detected backend/frontend build) and run the existing test suite if present (`swift test` / `xcodebuild test` / `./gradlew test` / `pytest` / `npm test` / `vitest`). Require success to advance; on failure, surface logs and (interactive) stop or (autopilot) attempt a bounded fix loop. **If the repo has no tests, report "no tests present" - never fabricate test results.**
 - **Phase 6 Commit/PR** - per `$HOME/.claude/multi-agent-refs/phases/phase-6-commit.md`: stage + commit any remaining local changes with a conventional message (`{type}(scope): desc [{JIRA_KEY}-{id}]`), push, and open a PR **only if one does not already exist** for the branch. PR body per `$HOME/.claude/multi-agent-refs/rules.md "External System Outputs"` and `$HOME/.claude/rules/git-conventions.md` - `Ref: #N` / `Related: #N`, never `Closes/Fixes/Resolves`; NO AI/bot attribution anywhere.
 - **Phase 7 Report** - per `$HOME/.claude/multi-agent-refs/phases/phase-7-report.md` + `channels.md`: produce the **technical analysis** and **test scenarios**, then post to the configured channels. Default content for `ship`: a Jira **comment** carrying the technical analysis + the test scenarios (and, when the PR was opened, the PR description). Every body runs through the humanizer; bot/tool/AI signatures are FORBIDDEN in comments.
@@ -108,5 +108,5 @@ No TaskList widget. After every state change call `bash $HOME/.claude/scripts/ph
 ```bash
 /multi-agent:dev-local "PROJ-12345"     # develop locally (Init→Dev→Commit→Report, no review/test)
 # ... you inspect / hand-test the change ...
-/multi-agent:ship                        # now: review + build/test + PR + Jira analysis & test scenarios
+/multi-agent:resume-local                        # now: review + build/test + PR + Jira analysis & test scenarios
 ```

package/pipeline/commands/multi-agent/scan/SKILL.md

@@ -66,7 +66,7 @@ Known legitimate domains are embedded in the scanner (github, anthropic, figma,
 
 ## Smoke  -  self-verification
 
-`pipeline/scripts/smoke-skill-scan.sh` confirms the scanner triggers on positive fixtures for every severity and produces no false positives on the real tree. The smoke must be 13/13 green before a team rollout.
+`pipeline/scripts/smoke-skill-scan.sh` confirms the scanner triggers on positive fixtures for every severity and produces no false positives on the real tree. This is a maintainer-repo gate (smoke scripts are excluded from the npm package): it runs from a pipeline checkout and in CI, where it must be 13/13 green before a team rollout.
 
 ## Integration points
 

package/pipeline/commands/multi-agent/setup/SKILL.md

@@ -883,12 +883,12 @@ Stack skills ship as versioned plugins in the `{owner}/multi-agent-plugins` mark
    claude marketplace add {owner}/multi-agent-plugins 2>/dev/null || true
    ```
 2. Detect the project stack from markers and enable the matching plugin(s) plus the always-on common plugin in the project's `.claude/settings.json` `enabledPlugins`:
-   - `.xcodeproj` / `Package.swift` / `*.xcworkspace` → `ai-ios-engineering-toolkit`
-   - `build.gradle` / `settings.gradle` → `ai-android-engineering-toolkit`
-   - `package.json` with `react`/`next` → `ai-frontend-engineering-toolkit`
+   - `.xcodeproj` / `Package.swift` / `*.xcworkspace` → `ai-ios-toolkit`
+   - `build.gradle` / `settings.gradle` → `ai-android-toolkit`
+   - `package.json` with `react`/`next` → `ai-frontend-toolkit`
    - `requirements.txt` / `pyproject.toml` / server `package.json` → `ai-backend-toolkit`
-   - **no clear marker → default `ai-ios-engineering-toolkit`**
-   `ai-common-engineering-toolkit@multi-agent-plugins` is always set `true` alongside the stack plugin.
+   - **no clear marker → default `ai-ios-toolkit`**
+   `ai-common-toolkit@multi-agent-plugins` is always set `true` alongside the stack plugin.
 3. Report the enabled set. To change later, run `/multi-agent:stack <ios|android|frontend|backend|...>` in the repo. Pipeline Phase 1 auto-detects the stack for its own routing regardless of enablement.
 
 The marketplace repo name (`multi-agent-plugins`) is generic; a different org points `{owner}` at its own fork - nothing in the pipeline is coupled to a specific account.

package/pipeline/commands/multi-agent/stack/SKILL.md

@@ -1,25 +1,29 @@
 ---
-description: "Select the active stack for this repo by enabling the matching marketplace plugin(s) in .claude/settings.json (ios/android/mobile/backend/frontend/fullstack/all). Use when a repo's stack changed or the wrong plugins are enabled for it."
-description-tr: "Bu repo için aktif stack'i seçer: eşleşen marketplace plugin'lerini .claude/settings.json'da etkinleştirir (ios/android/mobile/backend/frontend/fullstack/all)."
-allowed-tools: Bash, Read, Edit, Write
+description: "Select the active stack(s) for this repo by enabling the matching marketplace plugin(s) in .claude/settings.json. Multi-select: pass several stacks (ios backend) or pick them in the native picker. Use when a repo's stack changed or the wrong plugins are enabled for it."
+description-tr: "Bu repo için aktif stack'leri seçer: eşleşen marketplace plugin'lerini .claude/settings.json'da etkinleştirir. Çoklu seçim: birden fazla stack yazılabilir (ios backend) ya da native picker'dan seçilir."
+argument-hint: "[ios|android|frontend|web|backend|mobile|fullstack|all ...]"
+allowed-tools: Bash, Read, Edit, Write, AskUserQuestion
 ---
 
-# multi-agent stack  -  Select Stack via Plugin Enablement
+# multi-agent stack  -  Select Stack(s) via Plugin Enablement
 
-Stack skills ship as plugins in the `{owner}/multi-agent-plugins` marketplace. Selecting a stack = **enabling the matching plugin(s)** in the current repo's `.claude/settings.json` `enabledPlugins`. The `ai-common-engineering-toolkit` (accessibility audit, humanizer, Firebase) is always enabled alongside the stack plugin.
+Stack skills ship as plugins in the `{owner}/multi-agent-plugins` marketplace. Selecting a stack = **enabling the matching plugin(s)** in the current repo's `.claude/settings.json` `enabledPlugins`. The `ai-common-toolkit` (accessibility audit, humanizer, Firebase) is always enabled alongside the stack plugin(s).
+
+On Claude Code the marketplace plugins are the ONLY source of stack skills - nothing is copied into `~/.claude/skills` anymore. A stack that is not enabled here is simply absent from the session. Copilot CLI and Codex CLI have no plugin loader; they receive a local copy filtered to the enabled stacks at install time, which is why step 5 below offers to refresh those copies after a change.
 
 This replaces the old `stack-swap.sh` mechanic that physically moved skill directories in `~/.claude/skills/`. There is no SessionStart hook and no directory shuffling - enablement is declarative, per-repo, and versioned.
 
 ## Usage
 
 ```bash
-/multi-agent:stack                 # show which plugins are enabled here
+/multi-agent:stack                 # no arg → native multi-select picker (current state pre-noted)
 /multi-agent:stack ios             # SwiftUI toolkit + common
+/multi-agent:stack ios backend     # any combination, space-separated
 /multi-agent:stack android         # Compose toolkit + common
-/multi-agent:stack mobile          # iOS + Android + common
+/multi-agent:stack mobile          # alias: ios + android + common
 /multi-agent:stack backend         # Python / Node spec-driven toolkit + common
-/multi-agent:stack frontend        # React / TSX toolkit + common
-/multi-agent:stack fullstack       # frontend + backend + common
+/multi-agent:stack frontend        # React / TSX toolkit + common (alias: web)
+/multi-agent:stack fullstack       # alias: frontend + backend + common
 /multi-agent:stack all             # all four stack toolkits + common
 ```
 
@@ -27,26 +31,38 @@ This replaces the old `stack-swap.sh` mechanic that physically moved skill direc
 
 | Stack | Plugins enabled (all `@multi-agent-plugins`) |
 |---|---|
-| `ios` | `ai-common-engineering-toolkit`, `ai-ios-engineering-toolkit` |
-| `android` | `ai-common-engineering-toolkit`, `ai-android-engineering-toolkit` |
-| `frontend` | `ai-common-engineering-toolkit`, `ai-frontend-engineering-toolkit` |
-| `backend` | `ai-common-engineering-toolkit`, `ai-backend-toolkit` |
-| `mobile` | common + `ai-ios-engineering-toolkit` + `ai-android-engineering-toolkit` |
-| `fullstack` | common + `ai-frontend-engineering-toolkit` + `ai-backend-toolkit` |
+| `ios` | `ai-common-toolkit`, `ai-ios-toolkit` |
+| `android` | `ai-common-toolkit`, `ai-android-toolkit` |
+| `frontend` / `web` | `ai-common-toolkit`, `ai-frontend-toolkit` |
+| `backend` | `ai-common-toolkit`, `ai-backend-toolkit` |
+| `mobile` | common + `ai-ios-toolkit` + `ai-android-toolkit` |
+| `fullstack` | common + `ai-frontend-toolkit` + `ai-backend-toolkit` |
 | `all` | common + all four stack toolkits |
 
+Multiple args union their plugin sets: `ios backend` → common + iOS + backend.
+
 ## Behaviour
 
-1. **No arg → status mode.** Read `.claude/settings.json` (repo) + `~/.claude/settings.json` (global) and print which `@multi-agent-plugins` plugins are currently enabled. Do not modify anything.
-2. **Arg present → enable mode.** Ensure the marketplace is known, then write the matching `enabledPlugins` entries into the **current repo's** `.claude/settings.json`, disabling the stack toolkits that don't belong to the selected stack. `ai-common-engineering-toolkit` is always set to `true`.
-3. **Unknown arg** → show the list above; do not guess.
+1. **No arg → native multi-select picker.** Read `.claude/settings.json` (repo) + `~/.claude/settings.json` (global) to learn the current state, then ask with `AskUserQuestion` (`multiSelect: true`) - NEVER a numbered text menu:
+   - `question` (in `outputLanguage`): which stacks should be active in this repo, noting the currently enabled ones
+   - `header`: "Stacks" (English, UI contract)
+   - `options` (4): `ios` / `android` / `frontend (web)` / `backend`, each `description` (in `outputLanguage`) naming the plugin it enables and marking the ones already enabled with "(currently on)" / "(şu an açık)"
+   - Map each selected label back to its canonical arg before step 2: the token before any parenthesis (`frontend (web)` → `frontend`).
+   - Empty selection or cancel → **status mode**: print the currently enabled `@multi-agent-plugins` plugins and exit without modifying anything. Status mode never runs the Implementation block below - that block is enable-mode only.
+2. **Arg(s) present → enable mode.** Accept multiple space-separated stacks. Resolve each through the alias table (`web`→`frontend`, `mobile`→`ios android`, `fullstack`→`frontend backend`, `all`→every stack), union the plugin sets, then write the **current repo's** `.claude/settings.json`.
+3. **Write rules:**
+   - every plugin in the union is set to `true`
+   - every stack toolkit **not** in the union is set to `false` (leave non-`@multi-agent-plugins` entries untouched)
+   - `ai-common-toolkit@multi-agent-plugins` is always `true`
+   - **legacy-key cleanup**: delete any `ai-*-engineering-toolkit@multi-agent-plugins` keys - those plugin names were retired by the `ai-<stack>-toolkit` rename and a stale `true` there enables a plugin that no longer exists in the marketplace
+4. **Unknown arg** → show the table above; do not guess.
+5. **Copilot/Codex refresh offer.** Their local skill copies are filtered to the enabled stacks at install time, so after a change ask (single `AskUserQuestion`, not silent): "Refresh Copilot/Codex local copies now?" - Yes runs `node <pipelineRepo>/install.js --copilot --codex`, No leaves them stale with a one-line warning naming the command to run later. Skip this question entirely when neither `~/.copilot` nor `~/.codex` exists.
 
 ## Implementation
 
 ```bash
 REPO_SETTINGS=".claude/settings.json"
 MP="multi-agent-plugins"
-ARG="${1:-status}"
 
 # --- ensure the marketplace is known (idempotent) -------------------------
 if ! claude marketplace list 2>/dev/null | grep -q "$MP"; then
@@ -54,38 +70,44 @@ if ! claude marketplace list 2>/dev/null | grep -q "$MP"; then
     || echo "note: add the marketplace once with: claude marketplace add {owner}/multi-agent-plugins"
 fi
 
-COMMON="ai-common-engineering-toolkit@${MP}"
-IOS="ai-ios-engineering-toolkit@${MP}"
-ANDROID="ai-android-engineering-toolkit@${MP}"
-FRONTEND="ai-frontend-engineering-toolkit@${MP}"
+COMMON="ai-common-toolkit@${MP}"
+IOS="ai-ios-toolkit@${MP}"
+ANDROID="ai-android-toolkit@${MP}"
+FRONTEND="ai-frontend-toolkit@${MP}"
 BACKEND="ai-backend-toolkit@${MP}"
 
-if [ "$ARG" = "status" ]; then
-  echo "Enabled multi-agent plugins (repo + global):"
-  { [ -f "$REPO_SETTINGS" ] && cat "$REPO_SETTINGS"; cat "$HOME/.claude/settings.json"; } 2>/dev/null \
-    | grep -oE "ai-[a-z-]+@${MP}\"[[:space:]]*:[[:space:]]*(true|false)" | sort -u
+# Enable-mode only: with zero args the write rules below would set every stack
+# toolkit to false (nothing but $COMMON is in $ON), silently wiping the repo's
+# selection. No args belongs to the picker / status path (Behaviour step 1).
+if [ "$#" -eq 0 ]; then
+  echo "No stack given - nothing changed. Pass stacks (ios backend ...) or use the picker."
   exit 0
 fi
 
-# resolve the desired ON set
-case "$ARG" in
-  ios)       ON="$COMMON $IOS" ;;
-  android)   ON="$COMMON $ANDROID" ;;
-  frontend)  ON="$COMMON $FRONTEND" ;;
-  backend)   ON="$COMMON $BACKEND" ;;
-  mobile)    ON="$COMMON $IOS $ANDROID" ;;
-  fullstack) ON="$COMMON $FRONTEND $BACKEND" ;;
-  all)       ON="$COMMON $IOS $ANDROID $FRONTEND $BACKEND" ;;
-  *) echo "Unknown stack '$ARG'. One of: ios android mobile backend frontend fullstack all"; exit 1 ;;
-esac
+# resolve every arg through the alias table, union the ON set
+ON="$COMMON"
+for ARG in "$@"; do
+  case "$ARG" in
+    ios)              ON="$ON $IOS" ;;
+    android)          ON="$ON $ANDROID" ;;
+    frontend|web)     ON="$ON $FRONTEND" ;;
+    "frontend (web)") ON="$ON $FRONTEND" ;;
+    backend)          ON="$ON $BACKEND" ;;
+    mobile)           ON="$ON $IOS $ANDROID" ;;
+    fullstack)        ON="$ON $FRONTEND $BACKEND" ;;
+    all)              ON="$ON $IOS $ANDROID $FRONTEND $BACKEND" ;;
+    *) echo "Unknown stack '$ARG'. One of: ios android mobile backend frontend web fullstack all"; exit 1 ;;
+  esac
+done
 ```
 
 After resolving `$ON`, edit `.claude/settings.json` (create `{ "enabledPlugins": {} }` if absent) so that:
 - every plugin in `$ON` is set to `true`,
 - every stack toolkit **not** in `$ON` is set to `false` (leave non-`@multi-agent-plugins` entries untouched),
-- `ai-common-engineering-toolkit@multi-agent-plugins` is always `true`.
+- `ai-common-toolkit@multi-agent-plugins` is always `true`,
+- every `ai-*-engineering-toolkit@multi-agent-plugins` key is **deleted** (retired names).
 
-Use the Read + Edit/Write tools (JSON must stay valid). Then print the resulting `enabledPlugins` block.
+Use the Read + Edit/Write tools (JSON must stay valid). Then print the resulting `enabledPlugins` block and run step 5 (Copilot/Codex refresh offer).
 
 ## Notes
 

package/pipeline/commands/multi-agent/store-ready/SKILL.md

@@ -39,7 +39,7 @@ a package the store itself refuses, and a policy a human enforces.
 |---|---|---|
 | 1 Static | `ios_app_store_audit({archive_path, rules: "all"})`  -  18 rules with real ITMS codes. Needs an `.xcarchive`. Reference: `apple-archive-compliance` skill | `android_apk_audit` plus the `google-play-compliance` skill's 21 rules: `bundletool validate` + manifest dump, `aapt2 dump badging`, `apksigner verify`, ABI / native scan. Needs an `.aab` (an `.apk` narrows it, see Step 3) |
 | 2 Authoritative | `ios_testflight_validate({ipa_path, platform: "ios", <credentials>})` → `xcrun altool --validate-app`. Needs an `.ipa` + credentials | **No client shipped.** Play's authoritative check exists only server-side, through a Publishing API draft edit that is validated and then abandoned. The pipeline has no tool for it, so this gate reports `SKIPPED (no local Play validator)` and the report says so. Do not substitute `bundletool validate`  -  that is Gate 1 |
-| 3 Policy | `app-store-review` skill vs repo source | `play-store-review` skill vs repo source |
+| 3 Policy | `ai-ios-toolkit:app-store-review` skill vs repo source | `ai-android-toolkit:play-store-review` skill vs repo source |
 
 Gate 2's asymmetry is real and is reported as an asymmetry, not smoothed over. On
 iOS it is the only gate that catches a version+build pair already used  -  the most
@@ -248,7 +248,7 @@ reporting it here would fake a cleared gate.
 Load the platform's review skill and review the repo against it. This is the gate
 that catches what a human reviewer rejects, so it reads source, not the binary.
 
-**iOS**  -  `app-store-review`:
+**iOS**  -  `ai-ios-toolkit:app-store-review`:
 
 | Area | Evidence to gather |
 |---|---|
@@ -260,7 +260,7 @@ that catches what a human reviewer rejects, so it reads source, not the binary.
 | IAP | anything unlocking features goes through StoreKit, with no external purchase path |
 | Sign in with Apple | present when a third-party social login is offered |
 
-**Android**  -  `play-store-review`:
+**Android**  -  `ai-android-toolkit:play-store-review`:
 
 | Area | Evidence to gather |
 |---|---|