@mmerterden/multi-agent-pipeline 8.6.1 → 10.0.6

package/pipeline/skills/shared/core/multi-agent-language/SKILL.md

@@ -3,10 +3,10 @@ name: multi-agent-language
 language: en
 description: "Toggle outputLanguage (assistant explanations). promptLanguage is fixed to English. External payloads stay English."
 user-invocable: true
-argument-hint: "[en|tr] — sets outputLanguage; omit for interactive picker; use 'output en|tr' for explicit form"
+argument-hint: "[en|tr]  -  sets outputLanguage; omit for interactive picker; use 'output en|tr' for explicit form"
 ---
 
-# multi-agent language — Language Preference Toggle
+# multi-agent language  -  Language Preference Toggle
 
 **Input**: $ARGUMENTS
 
@@ -14,7 +14,7 @@ Two-axis language preference for the pipeline:
 
 | Field | Controls | Stored at | Mutability |
 |---|---|---|---|
-| `promptLanguage` | Interactive prompts during a pipeline run (account picker, project picker, dev-context picker, base-branch picker, branch-name picker, maturity ack, channels picker, Phase 5 test prompt, Phase 6 local-checkout prompt) | `prefs.global.promptLanguage` | **Fixed to `en`** — never toggled by this skill |
+| `promptLanguage` | Interactive prompts during a pipeline run (account picker, project picker, dev-context picker, base-branch picker, branch-name picker, maturity ack, channels picker, Phase 5 test prompt, Phase 6 local-checkout prompt) | `prefs.global.promptLanguage` | **Fixed to `en`**  -  never toggled by this skill |
 | `outputLanguage` | Assistant's explanations, status updates, error messages, and pipeline-generated reports rendered to the user (NOT external payloads) | `prefs.global.outputLanguage` | Toggled by this skill |
 
 **Why promptLanguage is fixed:** Pipeline picker UI, confirmation prompts, and error messages are authored in English to keep tooling consistent across CLIs. Mixing Turkish prompts into otherwise-English skill output looks inconsistent. Only the assistant's free-form replies follow `outputLanguage`.
@@ -26,9 +26,9 @@ Two-axis language preference for the pipeline:
 | Form | Behavior |
 |---|---|
 | `/multi-agent-language` (Copilot) / `/multi-agent:language` (Claude Code) | Interactive: shows current outputLanguage, prompts for a new value. |
-| `… en` or `… tr` | Sets `outputLanguage` to the given value. `promptLanguage` is left untouched (always `en`). |
-| `… output en\|tr` | Same as the single-token form — sets only `outputLanguage`. |
-| `… prompt …` | **Rejected.** Print: `promptLanguage is fixed to "en" and cannot be changed.` |
+| `... en` or `... tr` | Sets `outputLanguage` to the given value. `promptLanguage` is left untouched (always `en`). |
+| `... output en\|tr` | Same as the single-token form  -  sets only `outputLanguage`. |
+| `... prompt ...` | **Rejected.** Print: `promptLanguage is fixed to "en" and cannot be changed.` |
 
 ## Steps
 
@@ -39,7 +39,7 @@ PREFS="$HOME/.claude/multi-agent-preferences.json"
 OUTPUT_LANG=$(jq -r '.global.outputLanguage // "<unset>"' "$PREFS" 2>/dev/null || echo "<unset>")
 ```
 
-`promptLanguage` is intentionally NOT read — it is fixed `en`.
+`promptLanguage` is intentionally NOT read  -  it is fixed `en`.
 
 ### Branch on argument shape
 
@@ -48,7 +48,7 @@ OUTPUT_LANG=$(jq -r '.global.outputLanguage // "<unset>"' "$PREFS" 2>/dev/null |
    - Ask new outputLanguage value; "keep" leaves it untouched
 2. **Single token (`en` | `tr`)** → set `outputLanguage` only. Do NOT touch `promptLanguage`.
 3. **`output en|tr`** → equivalent to the single-token form.
-4. **`prompt …`** → reject with `promptLanguage is fixed to "en" and cannot be changed.` (exit non-zero).
+4. **`prompt ...`** → reject with `promptLanguage is fixed to "en" and cannot be changed.` (exit non-zero).
 5. **Anything else** → print usage and exit non-zero.
 
 ### Self-heal promptLanguage
@@ -81,7 +81,7 @@ Render in the new outputLanguage:
 
 ## Cross-reference
 
-- `multi-agent-setup` — first-run language picker (asks only outputLanguage; promptLanguage seeded as `en`)
-- `prefs.schema.json` — `global.promptLanguage` (fixed `"en"`) and `global.outputLanguage`
-- Phase 5 / Phase 6 — read promptLanguage for interactive prompts (always English)
-- `multi-agent-help` — reads outputLanguage for its own copy
+- `multi-agent-setup`  -  first-run language picker (asks only outputLanguage; promptLanguage seeded as `en`)
+- `prefs.schema.json`  -  `global.promptLanguage` (fixed `"en"`) and `global.outputLanguage`
+- Phase 5 / Phase 6  -  read promptLanguage for interactive prompts (always English)
+- `multi-agent-help`  -  reads outputLanguage for its own copy

package/pipeline/skills/shared/core/multi-agent-local/SKILL.md

@@ -1,32 +1,32 @@
 ---
 name: multi-agent-local
 language: en
-description: "Full pipeline in local mode — no worktree, runs directly on the current branch."
+description: "Full pipeline in local mode  -  no worktree, runs directly on the current branch."
 user-invocable: true
 ---
 
-# multi-agent local — Full Pipeline, Local Branch
+# multi-agent local  -  Full Pipeline, Local Branch
 
-Tüm 8 fazlı pipeline (normal mod — Plan Approval Gate + parallel review + triage dahil), **worktree oluşturmadan** mevcut branch'te çalışır. `multi-agent "task" --local` flag formunun dedicated karşılığı.
+Runs the full 8-phase pipeline (normal mode  -  including the Plan Approval Gate + parallel review + triage) on the current branch **without creating a worktree**. The dedicated equivalent of the `multi-agent "task" --local` flag form.
 
 ## When to use it
 
-- Açık ek bir worktree istemiyorsun — aynı klasörde editor/IDE açıksa bölünmez
-- Zaten doğru branch'tesin ve sadece pipeline disiplinini uygulamak istiyorsun
-- Küçük proje / prototip — worktree overhead'i gereksiz
+- You do not want an extra open worktree  -  if an editor/IDE is open in the same folder, it is not disrupted
+- You are already on the correct branch and just want to apply the pipeline discipline
+- Small project / prototype  -  worktree overhead is unnecessary
 
 ## When NOT to use it
 
-- Paralel birden fazla task aynı anda — worktree izolasyonu kaybolur
-- Multi-repo task — `--local` tek repo'ya kilitlenir
+- Multiple tasks in parallel at the same time  -  worktree isolation is lost
+- Multi-repo task  -  `--local` locks to a single repo
 
 ## Pipeline
 
-Normal pipeline'la aynı 8 faz: Init → Analysis → Planning → Dev → Review → Test → Commit → Report. Sadece Phase 0 Step 8 (workspace creation) worktree yerine mevcut branch üzerinde devam eder; `state.projects[*].worktreePath` alanı `null` kalır.
+The same 8 phases as the normal pipeline: Init → Analysis → Planning → Dev → Review → Test → Commit → Report. Only Phase 0 Step 8 (workspace creation) continues on the current branch instead of a worktree; the `state.projects[*].worktreePath` field stays `null`.
 
 ## Delegation
 
-Orchestrator skill'ine (`multi-agent/SKILL.md`) `--local` flag'i ile delege eder. Phase 0 Step 8 worktree adımı atlanır; diğer tüm phase contract'ları olduğu gibi geçerli (Plan Approval Gate, 2-model/3-model review, triage, secret scan, PR creation).
+Delegates to the orchestrator skill (`multi-agent/SKILL.md`) with the `--local` flag. The Phase 0 Step 8 worktree step is skipped; all other phase contracts apply as is (Plan Approval Gate, 2-model/3-model review, triage, secret scan, PR creation).
 
 ## Examples
 

package/pipeline/skills/shared/core/multi-agent-local-autopilot/SKILL.md

@@ -1,25 +1,25 @@
 ---
 name: multi-agent-local-autopilot
 language: en
-description: "Full pipeline + local + autopilot — no worktree, no confirmations, all 8 phases run end-to-end on the current branch."
+description: "Full pipeline + local + autopilot  -  no worktree, no confirmations, all 8 phases run end-to-end on the current branch."
 user-invocable: true
-argument-hint: '"task" — issue URL, Jira ID, free-text, or #id (for resume)'
+argument-hint: '"task"  -  issue URL, Jira ID, free-text, or #id (for resume)'
 ---
 
-# multi-agent-local-autopilot — Full Pipeline, Local Branch, Autonomous
+# multi-agent-local-autopilot  -  Full Pipeline, Local Branch, Autonomous
 
 **Input**: $ARGUMENTS
 
-Tüm 8 fazlı pipeline'ı **worktree oluşturmadan** + **tüm onayları atlayarak** çalıştırır. `autopilot + local` kombinasyonu. `/multi-agent:local-autopilot` (Claude Code colon-form) ile byte-identical behavior.
+Runs the full 8-phase pipeline **without creating a worktree** + **skipping all confirmations**. The `autopilot + local` combination. Byte-identical behavior to `/multi-agent:local-autopilot` (Claude Code colon-form).
 
 ## Matrix (which one should I use?)
 
-| Komut | Pipeline | Worktree | Onay |
+| Command | Pipeline | Worktree | Confirmation |
 |---|---|---|---|
-| `multi-agent "task"` | Full 8 faz | ✅ | ✅ (interactive) |
-| `multi-agent-autopilot "task"` | Full 8 faz | ✅ | ❌ |
-| `multi-agent-local "task"` | Full 8 faz | ❌ | ✅ |
-| **`multi-agent-local-autopilot "task"`** | **Full 8 faz** | **❌** | **❌** |
+| `multi-agent "task"` | Full 8 phases | ✅ | ✅ (interactive) |
+| `multi-agent-autopilot "task"` | Full 8 phases | ✅ | ❌ |
+| `multi-agent-local "task"` | Full 8 phases | ❌ | ✅ |
+| **`multi-agent-local-autopilot "task"`** | **Full 8 phases** | **❌** | **❌** |
 | `multi-agent-dev "task"` | Init → Dev → Commit → Report | ✅ | ✅ |
 | `multi-agent-dev-autopilot "task"` | Init → Dev → Commit → Report | ✅ | ❌ |
 | `multi-agent-dev-local "task"` | Init → Dev → Commit → Report | ❌ | ✅ |
@@ -27,17 +27,17 @@ Tüm 8 fazlı pipeline'ı **worktree oluşturmadan** + **tüm onayları atlayara
 
 ## What changes
 
-- Phase 0 Step 8 worktree adımı atlanır (local contract)
-- Phase 2 Plan Approval Gate atlanır (autopilot contract) — `state.autopilot === true`
-- Phase 5 test prompt'u atlanır, Phase 6 commit/PR onay beklemez
-- **v7.0.0+**: Phase 2 safety classifier (`classify-plan-safety.mjs`) her zaman çalışır; score ≥ 50 ise autopilot olsa da tek seferlik manuel onay ister (`prefs.global.autopilotSafetyGate`, default on)
+- The Phase 0 Step 8 worktree step is skipped (local contract)
+- The Phase 2 Plan Approval Gate is skipped (autopilot contract)  -  `state.autopilot === true`
+- The Phase 5 test prompt is skipped, Phase 6 commit/PR does not wait for confirmation
+- **v7.0.0+**: The Phase 2 safety classifier (`classify-plan-safety.mjs`) always runs; if the score is ≥ 50 it asks for a single manual confirmation even in autopilot (`prefs.global.autopilotSafetyGate`, default on)
 
 ## What is NEVER skipped
 
-- 🔴 Review blocking → Otomatik fix + rebuild (max 3 retry)
-- 💥 Build fail → Otomatik fix + rebuild (max 3 retry, sonra pause)
-- 🛡️ Safety classifier pause → high-risk plan tespitinde manuel onay
-- ⚠️ Kill/Purge → Her zaman onay ister (destructive)
+- 🔴 Review blocking → Automatic fix + rebuild (max 3 retries)
+- 💥 Build fail → Automatic fix + rebuild (max 3 retries, then pause)
+- 🛡️ Safety classifier pause → manual confirmation when a high-risk plan is detected
+- ⚠️ Kill/Purge → Always asks for confirmation (destructive)
 
 ## Examples
 
@@ -50,4 +50,4 @@ multi-agent-local-autopilot "#3"
 
 ## Delegation
 
-Orchestrator skill (`multi-agent/SKILL.md`) `--local` + `"autopilot": true` state flag'lerini birlikte alır. Contract: `refs/phases/phase-0-init.md` Step 8 (local branch) + `refs/phases/phase-2-planning.md` Step 5 (gate skip) + Step 5c (safety classifier, v7.0.0+).
+The orchestrator skill (`multi-agent/SKILL.md`) takes the `--local` + `"autopilot": true` state flags together. Contract: `refs/phases/phase-0-init.md` Step 8 (local branch) + `refs/phases/phase-2-planning.md` Step 5 (gate skip) + Step 5c (safety classifier, v7.0.0+).

package/pipeline/skills/shared/core/multi-agent-log/SKILL.md

@@ -1,12 +1,12 @@
 ---
 name: multi-agent-log
-language: tr
+language: en
 description: "Show the agent-log.md for the given task. With no ID, shows the most recent task."
 user-invocable: true
-argument-hint: "[#id] — optional: task ID (e.g. #3). If omitted, the most recent task is used."
+argument-hint: "[#id]  -  optional: task ID (e.g. #3). If omitted, the most recent task is used."
 ---
 
-# multi-agent log — Task Log Viewer
+# multi-agent log  -  Task Log Viewer
 
 **Input**: $ARGUMENTS
 
@@ -14,15 +14,15 @@ Show the task's detailed agent-log.md report.
 
 ## Steps
 
-1. **Task ID parse et** — Argümandan `#N` formatını çıkar
-   - Argüman yoksa → en son (en yüksek ID'li) worktree'yi bul
+1. **Parse the task ID**  -  extract the `#N` format from the argument
+   - If no argument → find the most recent (highest-ID) worktree
 
-2. **Worktree bul** — Bilinen repo'larda ara:
+2. **Find the worktree**  -  search known repos:
    ```bash
    find ~/my-ui-components/.worktrees/ ~/my-figma-app/.worktrees/ ~/my-ios-app/.worktrees/ -name "agent-state.json" -maxdepth 2 2>/dev/null
    ```
-   - `taskId` veya short ID eşleşen worktree'yi seç
+   - Pick the worktree whose `taskId` or short ID matches
 
-3. **agent-log.md oku** — Dosyayı göster
+3. **Read agent-log.md**  -  display the file
 
-4. **Özet sun** — Log çok uzunsa sadece Timeline tablosu + Review Consensus'u göster, tam log için dosya yolunu ver
+4. **Provide a summary**  -  if the log is very long, show only the Timeline table + Review Consensus, and give the file path for the full log

package/pipeline/skills/shared/core/multi-agent-manual-test/SKILL.md

@@ -1,12 +1,12 @@
 ---
 name: multi-agent-manual-test
-language: tr
+language: en
 description: "Switch to the active task's branch and prepare it for manual testing in Xcode. Phase 5 standalone (the UI Bug Hunter lives at multi-agent-test)."
 user-invocable: true
-argument-hint: "[#id] — opsiyonel: task ID. Verilmezse en son task"
+argument-hint: "[#id]  -  optional: task ID. Defaults to the latest task if omitted"
 ---
 
-# multi-agent manual-test — Phase 5 Manual Test Mode
+# multi-agent manual-test  -  Phase 5 Manual Test Mode
 
 **Input**: $ARGUMENTS
 
@@ -14,34 +14,34 @@ Lets you switch to the task branch for manual testing in Xcode before the PR is
 
 ## Steps
 
-1. **Task bul** — Argümandan `#N` parse et veya en son task'ı bul
+1. **Find the task**  -  parse `#N` from the argument or find the most recent task
 
-2. **State kontrol** — Task'ın Phase 3+ tamamlanmış olmalı
-   - Phase < 3 → "Henüz kod yazılmamış, önce `resume #N` çalıştır"
+2. **Check the state**  -  the task must have completed Phase 3+
+   - Phase < 3 → "No code has been written yet, run `resume #N` first"
 
-3. **Worktree kaldır ve branch'e geç**:
+3. **Remove the worktree and switch to the branch**:
    ```bash
    cd {project-root}
    git worktree remove .worktrees/PROJ-{id} 2>/dev/null
    git checkout {branch-name}
    ```
 
-4. **Test talimatı ver**:
+4. **Give test instructions**:
    ```
-   🧪 Branch'e geçildi: {branch-name}
+   🧪 Switched to branch: {branch-name}
 
-   Test için:
-     • SourceTree → commit'leri ve diff'i kontrol et
-     • Xcode → .xcworkspace aç → Cmd+B → Cmd+U
-     • Simulatör'de manual test
+   To test:
+     • SourceTree → review the commits and the diff
+     • Xcode → open .xcworkspace → Cmd+B → Cmd+U
+     • Manual test in the Simulator
 
-   Sonuç:
-     ✅ "tamam" → Phase 6'ya geçer (commit)
-     ❌ "fix: ..." → worktree tekrar oluşturulur, düzeltme yapılır
+   Result:
+     ✅ "ok" → proceeds to Phase 6 (commit)
+     ❌ "fix: ..." → the worktree is recreated and the fix is applied
    ```
 
-5. **Kullanıcı yanıtını bekle**
+5. **Wait for the user's response**
 
-6. **Sonuca göre**:
-   - **OK** → Worktree tekrar oluştur, Phase 6'ya geç
-   - **Fix gerekli** → Worktree tekrar oluştur, düzeltmeyi uygula
+6. **Based on the result**:
+   - **OK** → recreate the worktree, proceed to Phase 6
+   - **Fix needed** → recreate the worktree, apply the fix

package/pipeline/skills/shared/core/multi-agent-prune-logs/SKILL.md

@@ -0,0 +1,63 @@
+---
+name: multi-agent-prune-logs
+language: en
+description: "Delete per-task project logs under ~/.claude/logs/multi-agent (filter by age/project/task). Audit trail + metrics are preserved. Dry-run first; confirms before deleting."
+user-invocable: true
+argument-hint: "[--older-than=<days>] [--project=<name>] [--task=<id>] [--yes]"
+---
+
+# multi-agent prune-logs  -  Clear Per-Task Project Logs
+
+Every run persists a task log dir at
+`~/.claude/logs/multi-agent/<project>/<task>/` (agent-state.json, agent-log.md,
+tracker-state.json, otel-spans.jsonl). These accumulate forever. This prunes
+whole task dirs, with optional age / project / task filters.
+
+Backed by `$HOME/.claude/scripts/prune-logs.sh`. Safe by default: it previews
+and deletes nothing until you confirm. The audit trail (`audit.jsonl` +
+rotations) and the metrics corpus (`metrics.jsonl`, `metrics-summary.md`) live
+at the log-root top level and are never removed; `.counter` files survive too.
+
+Unlike `/multi-agent:purge` (which wipes worktrees, branches, logs, and state
+together), this only removes log dirs and leaves your worktrees and branches
+untouched.
+
+## Steps
+
+1. **Preview (dry-run)**  -  run the pruner with no `--yes`, forwarding any
+   `--older-than=<days>`, `--project=<name>`, or `--task=<id>` the user gave:
+
+   ```bash
+   bash $HOME/.claude/scripts/prune-logs.sh ${ARGUMENTS}
+   ```
+
+   It lists each task log dir that matches and the space it would free.
+
+2. **Nothing to do**  -  if the output says `nothing matched`, stop and report
+   there is nothing to prune.
+
+3. **Confirm**  -  surface a native `AskUserQuestion` picker (no typed keyword),
+   in `outputLanguage`:
+   - `question`: "Delete the listed task log dirs now?" (include the count and
+     freed-size estimate, and note audit + metrics are preserved)
+   - `header`: "Prune logs" (English, <=12 chars)
+   - `options`: `{ label: "Delete logs", description: "Remove the listed task log dirs" }`,
+     `{ label: "Cancel", description: "Keep everything, change nothing" }`
+   - Anything other than **Delete logs** -> cancel and change nothing.
+
+4. **Delete**  -  on confirm, re-run with `--yes` plus the same filters:
+
+   ```bash
+   bash $HOME/.claude/scripts/prune-logs.sh --yes ${ARGUMENTS}
+   ```
+
+5. **Report**  -  echo the `══ prune-logs: removed N task log dir(s), freed ~X ══`
+   summary line.
+
+## Notes
+
+- Pruning a log dir does not affect the run's git history or its commit/PR;
+  it only removes the local state + log artifacts.
+- To also reclaim `/tmp` scratch, use `/multi-agent:garbage-collect`.
+- For a full reset (worktrees + branches + logs + state), use
+  `/multi-agent:purge`.

package/pipeline/skills/shared/core/multi-agent-purge/SKILL.md

@@ -1,42 +1,45 @@
 ---
 name: multi-agent-purge
-language: tr
+language: en
 description: "⚠️ Wipes every worktree, branch, log, and state file. Irreversible; asks for double confirmation."
 user-invocable: true
 ---
 
-# multi-agent purge — Full Reset
+# multi-agent purge  -  Full Reset
 
-Reset every multi-agent state. Nuclear option — requires double confirmation.
+Reset every multi-agent state. Nuclear option  -  requires double confirmation.
 
 ## Steps
 
-1. **Tarama** — Tüm worktree'leri bul:
+1. **Scan**  -  Find all worktrees:
    ```bash
    find {repo}/.worktrees/ -name "agent-state.json" -maxdepth 2
    ```
 
-2. **Liste göster**:
+2. **Show list**:
    ```
-   ⚠️ DIKKAT: Silinecekler:
+   ⚠️ WARNING: Will be deleted:
    - .worktrees/PROJ-133139/ (branch: feature/PROJ-133139-...)
    - .worktrees/PROJ-133408/ (branch: feature/PROJ-133408-...)
    - .worktrees/.multi-agent-counter
-   Toplam: N worktree, N branch
+   Total: N worktree, N branch
    ```
 
-3. **İlk onay**: "Bu geri alınamaz. Emin misin?"
+3. **First confirmation**: "This cannot be undone. Are you sure?"
 
-4. **İkinci onay**: "Devam etmek için 'purge' yaz"
+4. **Second confirmation** (paranoia gate)  -  a native `AskUserQuestion` picker (no typed keyword):
+   - `question`: "This is irreversible. Permanently wipe every worktree, branch, log, and state file now?" (`outputLanguage`)
+   - `header`: "Purge" (English, <=12 chars) · `options`: `{ label: "Purge permanently", description: "Delete all worktrees, branches, logs, and state" }`, `{ label: "Cancel", description: "Abort, change nothing" }`
+   - Anything other than **Purge permanently** → cancel.
 
-5. **Sil** (her worktree için):
+5. **Delete** (for each worktree):
    ```bash
    git worktree remove .worktrees/PROJ-{id} --force
    git branch -D {branch-name}
    ```
 
-6. **Remote branch** — Sor: "Remote branch'leri de silmek istiyor musun?"
+6. **Remote branch**  -  Ask: "Do you also want to delete the remote branches?"
 
-7. **Counter sıfırla** — `.worktrees/.multi-agent-counter` sil
+7. **Reset counter**  -  Delete `.worktrees/.multi-agent-counter`
 
-8. **Onayla**: `🔥 Purge complete`
+8. **Confirm**: `🔥 Purge complete`