@mmerterden/multi-agent-pipeline 8.6.1 → 10.0.6

package/pipeline/commands/multi-agent/diff-explain.md

@@ -3,7 +3,7 @@ description: "Map Phase 4 triage findings to branch diff lines. Read-only post-h
 argument-hint: "[#task-id | --triage <path> | --state <path>] [--branch <name>] [--base <name>]"
 ---
 
-# multi-agent diff-explain — Phase 4 Triage to Diff Bridge
+# multi-agent diff-explain  -  Phase 4 Triage to Diff Bridge
 
 Maps the Phase 4 triage output (`accepted` / `deferred` / `rejected`) onto the branch's `git diff`. Every finding lands inline with the matching file / line hunk.
 
@@ -11,13 +11,13 @@ Maps the Phase 4 triage output (`accepted` / `deferred` / `rejected`) onto the b
 
 ## When to use it
 
-- Between Phase 4 and Phase 5/6: answers "5 findings — which one belongs to which file?"
+- Between Phase 4 and Phase 5/6: answers "5 findings  -  which one belongs to which file?"
 - Phase 7 reporting: a "review summary with code context" block to embed in the Wiki / Confluence output.
 - Post-hoc audit: for a closed PR, a "what did review flag, and how did the code change" diff.
 
 ## Steps
 
-1. **Resolve input** — figure out the triage source from `$ARGUMENTS`:
+1. **Resolve input**  -  figure out the triage source from `$ARGUMENTS`:
    - `#N` or `JIRA-N`: pull the triage from the task's state file
    - `--triage <path>`: triage-output.json directly
    - `--state <path>`: agent-state.json (with embedded triage)
@@ -52,7 +52,7 @@ Maps the Phase 4 triage output (`accepted` / `deferred` / `rejected`) onto the b
 
 ## src/api/checkout.ts
 
-### ✅ 🚫 BLOCKING — line 102 (opus)
+### ✅ 🚫 BLOCKING  -  line 102 (opus)
 > Race condition: order total computed twice without lock
 **Fix:** Compute total once inside the existing transaction block
 ```diff

package/pipeline/commands/multi-agent/garbage-collect.md

@@ -0,0 +1,58 @@
+---
+description: "Sweep leftover /tmp scratch (picker state, review diffs, channel payloads, analysis drafts) from past runs. Dry-run first; confirms before deleting."
+argument-hint: "[--older-than=<minutes>] [--yes]  -  dry-run unless confirmed"
+---
+
+# multi-agent garbage-collect  -  Sweep /tmp Scratch
+
+Each run writes ephemeral scratch under `/tmp`: picker state
+(`multi-agent-picker-*`), PR/review diffs (`multi-agent-review-*`), issue
+progress bodies (`issue-progress-*`), channel payloads (`channels-*`),
+external-context bundles (`context-links-*` / `context-by-type-*`), and analysis
+drafts (`analysis-*`). Most are never cleaned up, so a long-lived machine
+accumulates them. This sweeps the known prefixes only.
+
+Backed by `$HOME/.claude/scripts/gc-tmp.sh`. Safe by default: it previews and
+deletes nothing until you confirm.
+
+## Steps
+
+1. **Preview (dry-run)**  -  run the sweeper with no `--yes`, forwarding an
+   `--older-than=<minutes>` argument if the user supplied one:
+
+   ```bash
+   bash $HOME/.claude/scripts/gc-tmp.sh ${ARGUMENTS}
+   ```
+
+   It prints each matching item and the space it would free.
+
+2. **Nothing to do**  -  if the output says `nothing to do`, stop and report
+   that there is no scratch to clean.
+
+3. **Confirm**  -  surface a native `AskUserQuestion` picker (no typed keyword),
+   in `outputLanguage`:
+   - `question`: "Delete the listed /tmp scratch items now?" (include the count
+     and freed-size estimate from step 1)
+   - `header`: "Sweep" (English, <=12 chars)
+   - `options`: `{ label: "Delete scratch", description: "Remove the listed /tmp items" }`,
+     `{ label: "Cancel", description: "Keep everything, change nothing" }`
+   - Anything other than **Delete scratch** -> cancel and change nothing.
+
+4. **Delete**  -  on confirm, re-run with `--yes` (and the same
+   `--older-than` if given):
+
+   ```bash
+   bash $HOME/.claude/scripts/gc-tmp.sh --yes ${ARGUMENTS}
+   ```
+
+5. **Report**  -  echo the `══ garbage-collect: removed N item(s), freed ~X ══`
+   summary line.
+
+## Notes
+
+- An in-flight analysis keeps its drafts in `/tmp/analysis-<slug>-<timestamp>/`
+  and `/multi-agent:resume` re-uses them. If a run is paused at
+  `awaiting_output_decision`, pass `--older-than=<minutes>` so fresh drafts are
+  spared, or finish the run first.
+- This only touches `/tmp` scratch. Persistent per-task logs live under
+  `~/.claude/logs/multi-agent/` and are cleaned by `/multi-agent:prune-logs`.

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

@@ -1,5 +1,5 @@
 ---
-description: "Multi-agent pipeline usage guide — renders in EN or TR per prefs.global.outputLanguage (falls back to promptLanguage for backward compatibility)."
+description: "Multi-agent pipeline usage guide  -  renders in EN or TR per prefs.global.outputLanguage (falls back to promptLanguage for backward compatibility)."
 ---
 
 # multi-agent help
@@ -8,25 +8,25 @@ Called with no args or `help`, show the usage guide in the user's preferred lang
 
 ## Language resolution
 
-Help is the assistant's own explanation to the user — render it in `prefs.global.outputLanguage`. Fall back to `prefs.global.promptLanguage` for legacy prefs files where `outputLanguage` did not exist yet. Two valid values: `"en"` (default) and `"tr"`. If both fields are missing / malformed → treat as `"en"`.
+Help is the assistant's own explanation to the user  -  render it in `prefs.global.outputLanguage`. Fall back to `prefs.global.promptLanguage` for legacy prefs files where `outputLanguage` did not exist yet. Two valid values: `"en"` (default) and `"tr"`. If both fields are missing / malformed → treat as `"en"`.
 
 ```bash
 PREFS="$HOME/.claude/multi-agent-preferences.json"
 LANG=$(jq -r '.global.outputLanguage // .global.promptLanguage // "en"' "$PREFS" 2>/dev/null || echo "en")
 ```
 
-Render **exactly one** of the two blocks below — the one matching `LANG`. Do not print both; the user asked for a display, not a bilingual dump.
+Render **exactly one** of the two blocks below  -  the one matching `LANG`. Do not print both; the user asked for a display, not a bilingual dump.
 
 ---
 
-## Render when `LANG == "en"` — English guide
+## Render when `LANG == "en"`  -  English guide
 
 ```
 +----------------------------------------------------------+
 |             Multi-Agent Task Orchestrator                |
 +----------------------------------------------------------+
 
-5 different input types supported — all enter the same flow:
+5 different input types supported  -  all enter the same flow:
 
   /multi-agent "{JIRA_KEY}-XXXXX"                 -> Jira ID
   /multi-agent "https://{JIRA_HOST}/browse/..."   -> Jira URL
@@ -36,7 +36,7 @@ Render **exactly one** of the two blocks below — the one matching `LANG`. Do n
 
 ------------------------------------------------------------
 
-How It Works (Phase 0 — Interactive Flow):
+How It Works (Phase 0  -  Interactive Flow):
 
   1. PARSE       Classify input, fetch info from Jira/GitHub
   2. PROJECT     $HOME scanned, projects listed -> select by number
@@ -49,17 +49,18 @@ How It Works (Phase 0 — Interactive Flow):
 
 ------------------------------------------------------------
 
-Pipeline (after Phase 0) — shown as visual cards in terminal:
+Pipeline (after Phase 0)  -  shown as visual cards in terminal:
 
   Phase 0:   Init       -> The 8 steps above
-  Phase 1:   Analysis   -> Stack detection + codebase scan (Opus)
+  Phase 1:   Analysis   -> Stack detection + codebase scan (Fable)
   Phase 2:   Planning   -> Task breakdown + architecture review + Plan Approval Gate
-                          (clarification max 2 rounds + approval loop — normal mode only;
+                          (clarification max 2 rounds + approval loop  -  normal mode only;
                            skipped for --dev, autopilot, --dev autopilot)
   Phase 3:   Dev        -> TDD: test -> code -> build (Sonnet) + build queue
-  Phase 4:   Review     -> Deterministic gates + parallel AI review + Opus triage
-                          (Claude Code: Opus + Sonnet · Copilot CLI: GPT-5.4 + Opus + Sonnet)
-  Phase 5:   Test       -> Optional: switch to branch, test in Xcode (skipped in --dev / autopilot)
+  Phase 4:   Review     -> Deterministic gates + parallel AI review + Fable triage
+                          (Claude Code: Fable + Sonnet · Copilot CLI: GPT-5.4 + Opus + Sonnet)
+  Phase 5:   Test       -> Optional: switch to branch, test in Xcode
+                          (runs in dev + full; skipped in every autopilot and local variant)
   Phase 6:   Commit     -> Commit -> push -> PR + issue body update (never auto-closes)
   Phase 7:   Report     -> Channels dispatcher (PR · Jira · Confluence · Wiki, multi-select)
                           + internal capture (agent-log · knowledge · memory)
@@ -72,11 +73,11 @@ Pipeline (after Phase 0) — shown as visual cards in terminal:
 
 Modes:
 
-  (normal)             Full 8 phases, Sonnet dev, Plan Approval Gate active, parallel review + Opus triage
-  --dev                Fast: Init -> Dev(Opus) -> Commit -> Report (no plan gate)
-  --local              No worktree — works directly on local branch
+  (normal)             Full 8 phases, Sonnet dev, Plan Approval Gate active, parallel review + Fable triage
+  --dev                Fast: Init -> Dev(Fable) -> Commit -> Report (no plan gate)
+  --local              No worktree  -  works directly on local branch
   autopilot            Skip all confirmations INCLUDING plan gate, auto commit/PR
-                       (EXCEPT Phase 7 channels menu — always pauses)
+                       (EXCEPT Phase 7 channels menu  -  always pauses)
   --dev autopilot      Fastest path
   --local --dev        Local + fast (no worktree, no analysis/review, no plan gate)
 
@@ -98,13 +99,17 @@ Status & Resume:
   /multi-agent:log [#id]      Show task log (defaults to most recent)
   /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:clear-logs     Clean global log directory
-  /multi-agent:purge          Worktree + logs — full reset (double confirm)
+  /multi-agent:prune-logs     Delete per-task project logs (audit + metrics kept; age/project/task filters, dry-run first)
+  /multi-agent:garbage-collect  Sweep leftover /tmp scratch from past runs (dry-run first)
+  /multi-agent:purge          Worktree + logs  -  full reset (double confirm)
 
 Post-Hoc & Side-Channel:
 
   /multi-agent:channels       Post multi-channel report (Jira / Confluence / Wiki / PR description)
   /multi-agent:review         Parallel review of current diff only (no full pipeline)
+  /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:build-optimize iOS-only Xcode build perf wrapper → benchmark + analyze + recommend-first .build-benchmark/optimization-plan.md
   /multi-agent:diff-explain   Map a Phase 4 triage finding back to specific diff lines
   /multi-agent:search         Cross-task log search with smart ranking; --semantic queries triage corpus
   /multi-agent:scan           Skill security scan against tiered pattern catalog
@@ -112,7 +117,7 @@ Post-Hoc & Side-Channel:
 
 Setup & Maintenance:
 
-  /multi-agent:setup          First-run wizard — Keychain tokens + Git identity + language
+  /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>     Manually switch active skill set (ios / android / backend / frontend / fullstack / all)
   /multi-agent:sync           Sync ecosystem (Claude Code + Copilot CLI + pipeline + website + remote-control)
@@ -134,7 +139,7 @@ Interactive Launchers:
 
 ------------------------------------------------------------
 
-UI Testing (standalone — not part of pipeline phases):
+UI Testing (standalone  -  not part of pipeline phases):
 
   /multi-agent:test                  Full simulator test (screenshot all screens)
   /multi-agent:test "dark mode"      Dark mode bug test
@@ -146,7 +151,7 @@ UI Testing (standalone — not part of pipeline phases):
   Uses xcrun simctl / adb (native, no external app needed).
   Booted simulator/emulator required. Auto-detects bundle ID from project.
 
-Manual Test (Phase 5 standalone — Xcode hint flow):
+Manual Test (Phase 5 standalone  -  Xcode hint flow):
 
   /multi-agent:manual-test           Checkout task branch, print Xcode/SourceTree hints,
   /multi-agent:manual-test #N        wait for your "ok" / "fix: ..." verdict.
@@ -158,19 +163,19 @@ Setup:
   /multi-agent:setup
 
   Interactive onboarding:
-  1. Dynamic Keychain Discovery — finds existing tokens by keyword
-  2. Token Mapping — maps found keys to services (preferences)
-  3. Jira Project Key — your team's key (MOBILE, APP, ENG, etc.)
-  4. Git Identity — corporate + personal (saved to preferences)
-  5. Missing Tokens — standard key names + ready-to-paste commands
-  6. Verify — re-scan, confirm ready
+  1. Dynamic Keychain Discovery  -  finds existing tokens by keyword
+  2. Token Mapping  -  maps found keys to services (preferences)
+  3. Jira Project Key  -  your team's key (MOBILE, APP, ENG, etc.)
+  4. Git Identity  -  corporate + personal (saved to preferences)
+  5. Missing Tokens  -  standard key names + ready-to-paste commands
+  6. Verify  -  re-scan, confirm ready
 
 ------------------------------------------------------------
 
 Key Features:
 
-  Multi-Platform   iOS, Android, Backend, Frontend — auto-detected
-  Build Queue      xcodebuild/Gradle serialized with lock file — parallel safe
+  Multi-Platform   iOS, Android, Backend, Frontend  -  auto-detected
+  Build Queue      xcodebuild/Gradle serialized with lock file  -  parallel safe
   Stack Aware      Auto-detects iOS/Android/Python/Node/Go/Docker, loads matching skill set
   Det. Gates       Build + lint + test + secret scan BEFORE AI review
   Multi-Repo       Per-repo worktrees, per-repo identity, integration build before commit
@@ -178,12 +183,12 @@ Key Features:
   Issue Safety     Never auto-closes issues (4 approvals required, GitHub + Jira)
   Store Compliance /multi-agent:test "store-ready" runs 17-rule iOS audit (ITMS / Privacy Manifest /
                    code signing / debug-tool leak / IPv6 / SDK list / etc.) and 21-rule Android audit
-  Bilingual        EN + TR — outputLanguage toggles assistant explanations; promptLanguage is locked en
+  Bilingual        EN + TR  -  outputLanguage toggles assistant explanations; promptLanguage is locked en
 
-Quality & Telemetry (advisory, on by default — flip prefs.global.* to disable):
+Quality & Telemetry (advisory, on by default  -  flip prefs.global.* to disable):
 
   Diff Risk Score  Phase 4 Step 1.75 ranks files before reviewer dispatch (security paths,
-                   schema migrations, no-test-change, complexity delta) — heuristic, sub-second
+                   schema migrations, no-test-change, complexity delta)  -  heuristic, sub-second
   Test Gap Report  Phase 5 Step 0 surfaces public symbols added in this branch with no paired test
   Cost Breakdown   Phase 7 appends per-phase tokens (in/out) + estimated USD to agent-log.md
   Triage Memory    Phase 7 ingests accepted/deferred/rejected findings into a per-repo corpus
@@ -201,11 +206,11 @@ Examples:
   # GitHub issue, fast mode, local
   /multi-agent "#42" --dev --local
 
-  # Interactive launchers — browse and pick
+  # Interactive launchers  -  browse and pick
   /multi-agent:jira                    # Pick from my Jira issues
   /multi-agent:issue                   # Pick from unassigned GitHub issues
 
-  # Free-text — any platform
+  # Free-text  -  any platform
   /multi-agent "LoginView dark mode fix" --dev autopilot         # iOS
   /multi-agent "Add pagination to /api/users endpoint"           # Backend
   /multi-agent "Fix bottom nav recomposition in HomeScreen"      # Android
@@ -221,14 +226,14 @@ Logs: $HOME/.claude/logs/multi-agent/{project}/{task-id}/
 
 ---
 
-## Render when `LANG == "tr"` — Türkçe rehber
+## Render when `LANG == "tr"`  -  Türkçe rehber
 
 ```
 +----------------------------------------------------------+
 |             Multi-Agent Görev Orkestratörü               |
 +----------------------------------------------------------+
 
-5 farklı girdi tipi desteklenir — hepsi aynı akışa girer:
+5 farklı girdi tipi desteklenir  -  hepsi aynı akışa girer:
 
   /multi-agent "{JIRA_KEY}-XXXXX"                 -> Jira ID
   /multi-agent "https://{JIRA_HOST}/browse/..."   -> Jira URL
@@ -238,7 +243,7 @@ Logs: $HOME/.claude/logs/multi-agent/{project}/{task-id}/
 
 ------------------------------------------------------------
 
-Nasıl Çalışır (Phase 0 — İnteraktif Akış):
+Nasıl Çalışır (Phase 0  -  İnteraktif Akış):
 
   1. PARSE       Girdiyi sınıflandır, Jira/GitHub'dan bilgi çek
   2. PROJECT     $HOME taranır, projeler listelenir -> numarayla seç
@@ -251,16 +256,16 @@ Nasıl Çalışır (Phase 0 — İnteraktif Akış):
 
 ------------------------------------------------------------
 
-Pipeline (Phase 0'dan sonra) — terminalde görsel kart olarak görünür:
+Pipeline (Phase 0'dan sonra)  -  terminalde görsel kart olarak görünür:
 
   Phase 0:   Init       -> Yukarıdaki 8 adım
-  Phase 1:   Analysis   -> Stack tespiti + codebase taraması (Opus)
+  Phase 1:   Analysis   -> Stack tespiti + codebase taraması (Fable)
   Phase 2:   Planning   -> Task kırılımı + mimari inceleme + Plan Onay Kapısı
-                          (clarification max 2 tur + onay döngüsü — sadece normal mode;
+                          (clarification max 2 tur + onay döngüsü  -  sadece normal mode;
                            --dev, autopilot, --dev autopilot'ta skip)
   Phase 3:   Dev        -> TDD: test -> kod -> build (Sonnet) + build queue
-  Phase 4:   Review     -> Deterministik kapılar + paralel AI review + Opus triage
-                          (Claude Code: Opus + Sonnet · Copilot CLI: GPT-5.4 + Opus + Sonnet)
+  Phase 4:   Review     -> Deterministik kapılar + paralel AI review + Fable triage
+                          (Claude Code: Fable + Sonnet · Copilot CLI: GPT-5.4 + Opus + Sonnet)
   Phase 5:   Test       -> Opsiyonel: branch'e geç, Xcode'da test (--dev / autopilot'ta skip)
   Phase 6:   Commit     -> Commit -> push -> PR + issue body güncelleme (hiç auto-close yok)
   Phase 7:   Report     -> Channels dispatcher (PR · Jira · Confluence · Wiki, multi-select)
@@ -274,11 +279,11 @@ Pipeline (Phase 0'dan sonra) — terminalde görsel kart olarak görünür:
 
 Modlar:
 
-  (normal)             Tam 8 faz, Sonnet dev, Plan Onay Kapısı aktif, paralel review + Opus triage
-  --dev                Hızlı: Init -> Dev(Opus) -> Commit -> Report (plan gate yok)
-  --local              Worktree yok — doğrudan local branch'te çalışır
+  (normal)             Tam 8 faz, Sonnet dev, Plan Onay Kapısı aktif, paralel review + Fable triage
+  --dev                Hızlı: Init -> Dev(Fable) -> Commit -> Report (plan gate yok)
+  --local              Worktree yok  -  doğrudan local branch'te çalışır
   autopilot            Plan gate dahil tüm onayları atla, otomatik commit/PR
-                       (İSTİSNA: Phase 7 channels menüsü — her zaman durur)
+                       (İSTİSNA: Phase 7 channels menüsü  -  her zaman durur)
   --dev autopilot      En hızlı yol
   --local --dev        Local + hızlı (worktree yok, analiz/review yok, plan gate yok)
 
@@ -300,13 +305,17 @@ Status & Resume:
   /multi-agent:log [#id]      Task log'unu göster (varsayılan: en son task)
   /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:clear-logs     Global log dizinini temizle
-  /multi-agent:purge          Worktree + log'lar — tam reset (çift onay)
+  /multi-agent:prune-logs     Task bazlı proje log'larını sil (audit + metrics korunur; yaş/proje/task filtresi, önce dry-run)
+  /multi-agent:garbage-collect  Geçmiş koşumların /tmp artıklarını süpür (önce dry-run)
+  /multi-agent:purge          Worktree + log'lar  -  tam reset (çift onay)
 
 Post-Hoc & Side-Channel:
 
   /multi-agent:channels       Multi-channel rapor gönder (Jira / Confluence / Wiki / PR description)
   /multi-agent:review         Sadece mevcut diff'i paralel review et (full pipeline yok)
+  /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:build-optimize iOS-only Xcode build performance wrapper → benchmark + analiz + recommend-first .build-benchmark/optimization-plan.md
   /multi-agent:diff-explain   Phase 4 triage bulgusunu diff satırlarına eşle
   /multi-agent:search         Task log'larında akıllı arama; --semantic triage corpus'unu sorgular
   /multi-agent:scan           Skill güvenlik taraması (tiered pattern catalog)
@@ -314,7 +323,7 @@ Post-Hoc & Side-Channel:
 
 Setup & Maintenance:
 
-  /multi-agent:setup              İlk kurulum sihirbazı — Keychain token + Git kimliği + dil
+  /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>         Aktif skill set'i manuel değiştir (ios / android / backend / frontend / fullstack / all)
   /multi-agent:sync               Ekosistemi senkronize et (Claude Code + Copilot CLI + pipeline + website + remote-control)
@@ -336,7 +345,7 @@ Setup & Maintenance:
 
 ------------------------------------------------------------
 
-UI Testing (standalone — pipeline fazlarından bağımsız):
+UI Testing (standalone  -  pipeline fazlarından bağımsız):
 
   /multi-agent:test                  Tam simulator testi (tüm ekran screenshot'ları)
   /multi-agent:test "dark mode"      Dark mode bug testi
@@ -348,7 +357,7 @@ UI Testing (standalone — pipeline fazlarından bağımsız):
   xcrun simctl / adb kullanır (harici app gerekmez).
   Booted simulator/emulator şart. Bundle ID proje'den otomatik algılanır.
 
-Manuel Test (Phase 5 standalone — Xcode hint akışı):
+Manuel Test (Phase 5 standalone  -  Xcode hint akışı):
 
   /multi-agent:manual-test           Task branch'ine checkout, Xcode/SourceTree hint basar,
   /multi-agent:manual-test #N        "ok" / "fix: ..." yanıtını bekler.
@@ -360,33 +369,33 @@ Setup:
   /multi-agent:setup
 
   İnteraktif onboarding:
-  1. Dynamic Keychain Discovery — mevcut token'ları keyword ile bulur
-  2. Token Mapping — bulunanları servislere eşler (prefs)
-  3. Jira Project Key — takımının key'i (MOBILE, APP, ENG vb.)
-  4. Git Kimliği — kurumsal + kişisel (prefs'e kaydedilir)
-  5. Eksik Token'lar — standart key isimleri + ready-to-paste komutlar
-  6. Doğrulama — yeniden tarama, hazır mı kontrol
+  1. Dynamic Keychain Discovery  -  mevcut token'ları keyword ile bulur
+  2. Token Mapping  -  bulunanları servislere eşler (prefs)
+  3. Jira Project Key  -  takımının key'i (MOBILE, APP, ENG vb.)
+  4. Git Kimliği  -  kurumsal + kişisel (prefs'e kaydedilir)
+  5. Eksik Token'lar  -  standart key isimleri + ready-to-paste komutlar
+  6. Doğrulama  -  yeniden tarama, hazır mı kontrol
 
 ------------------------------------------------------------
 
 Temel Özellikler:
 
-  Multi-Platform   iOS, Android, Backend, Frontend — otomatik tespit
-  Build Queue      xcodebuild/Gradle lock file ile seri — parallel güvenli
+  Multi-Platform   iOS, Android, Backend, Frontend  -  otomatik tespit
+  Build Queue      xcodebuild/Gradle lock file ile seri  -  parallel güvenli
   Stack Aware      iOS/Android/Python/Node/Go/Docker algılanır, eşleşen skill set yüklenir
   Det. Gates       AI review'dan ÖNCE build + lint + test + secret scan
   Multi-Repo       Repo başına worktree, repo başına identity, commit öncesi entegrasyon build'i
   Identity Routing Repo origin URL'sinden git kimliği seçimi (kurumsal vs kişisel)
   Issue Safety     Issue'lar asla auto-close edilmez (GitHub + Jira için 4 onay gerekir)
-  Store Compliance /multi-agent:test "store-ready" — iOS için 17 kurallık audit (ITMS / Privacy Manifest /
+  Store Compliance /multi-agent:test "store-ready"  -  iOS için 17 kurallık audit (ITMS / Privacy Manifest /
                    code signing / debug-tool leak / IPv6 / SDK list / vb.) + Android için 21 kurallık audit
-  Bilingual        EN + TR — outputLanguage assistant açıklamasını değiştirir; promptLanguage en kilitli
+  Bilingual        EN + TR  -  outputLanguage assistant açıklamasını değiştirir; promptLanguage en kilitli
 
-Quality & Telemetry (advisory, default açık — prefs.global.* ile kapatılabilir):
+Quality & Telemetry (advisory, default açık  -  prefs.global.* ile kapatılabilir):
 
   Diff Risk Score  Phase 4 Step 1.75 reviewer dispatch'tan önce dosyaları sıralar (güvenlik path'leri,
-                   schema migration, test eklenmemiş değişiklik, complexity delta) — heuristik, saniyenin altı
-  Test Gap Report  Phase 5 Step 0 — bu branch'te eklenmiş public sembol + eşleşen test yoksa raporlar
+                   schema migration, test eklenmemiş değişiklik, complexity delta)  -  heuristik, saniyenin altı
+  Test Gap Report  Phase 5 Step 0  -  bu branch'te eklenmiş public sembol + eşleşen test yoksa raporlar
   Cost Breakdown   Phase 7 agent-log.md'ye faz başına token (in/out) + tahmini USD ekler
   Triage Memory    Phase 7 accepted/deferred/rejected bulguları repo başına corpus'a yazar
   Prior-Art Lookup Phase 1 + Phase 4 corpus'tan benzer geçmiş bulgu sorgular, ek context olarak enjekte
@@ -403,11 +412,11 @@ Quality & Telemetry (advisory, default açık — prefs.global.* ile kapatılabi
   # GitHub issue, hızlı mode, local
   /multi-agent "#42" --dev --local
 
-  # İnteraktif launcher'lar — göz at ve seç
+  # İnteraktif launcher'lar  -  göz at ve seç
   /multi-agent:jira                    # Jira issue'larımdan seç
   /multi-agent:issue                   # Atanmamış GitHub issue'lardan seç
 
-  # Serbest metin — herhangi bir platform
+  # Serbest metin  -  herhangi bir platform
   /multi-agent "LoginView dark mode fix" --dev autopilot         # iOS
   /multi-agent "Add pagination to /api/users endpoint"           # Backend
   /multi-agent "Fix bottom nav recomposition in HomeScreen"      # Android

package/pipeline/commands/multi-agent/issue.md

@@ -1,9 +1,9 @@
 ---
 description: "List unassigned GitHub issues, pick one, auto-assign, and launch the multi-agent pipeline."
-argument-hint: "[autopilot] — optional: run the pipeline without confirmations"
+argument-hint: "[autopilot]  -  optional: run the pipeline without confirmations"
 ---
 
-# multi-agent issue — 4-Step Picker (Account → Repos → Issue → Dev Context)
+# multi-agent issue  -  4-Step Picker (Account → Repos → Issue → Dev Context)
 
 **Input**: $ARGUMENTS
 
@@ -41,7 +41,7 @@ for line in sys.stdin: items += json.loads(line)
 for i in items:
     labels=",".join(l["name"] for l in i.get("labels",[]))
     if "implemented" in labels.lower() or "in progress" in labels.lower(): continue
-    print(f"#{i[\"number\"]} — {i[\"title\"]}")
+    print(f"#{i[\"number\"]}  -  {i[\"title\"]}")
 '
 ```
 - AskUserQuestion (multiSelect=false)

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

@@ -1,9 +1,9 @@
 ---
 description: "List open Jira issues, pick one, and launch the multi-agent pipeline."
-argument-hint: "[autopilot] — optional: run the pipeline without confirmations"
+argument-hint: "[autopilot]  -  optional: run the pipeline without confirmations"
 ---
 
-# multi-agent jira — 4-Step Picker (Account → Project → Issue → Dev Context)
+# multi-agent jira  -  4-Step Picker (Account → Project → Issue → Dev Context)
 
 **Input**: $ARGUMENTS
 
@@ -40,7 +40,7 @@ curl -s -H "Authorization: Bearer $TOKEN" \
   "https://$ACCOUNT_JIRA_HOST/rest/api/2/search?jql=$(printf '%s' "$JQL" | python3 -c 'import sys,urllib.parse; print(urllib.parse.quote(sys.stdin.read()))')&fields=key,summary,status,issuetype,priority,resolution,fixVersions&maxResults=50"
 ```
 
-> **Filter**: `resolution = EMPTY` excludes already-resolved issues at JQL level. If a listed issue still surfaces a maturity blocker, the issue is marked resolved in Jira but stuck in `In Progress` — show user a hint.
+> **Filter**: `resolution = EMPTY` excludes already-resolved issues at JQL level. If a listed issue still surfaces a maturity blocker, the issue is marked resolved in Jira but stuck in `In Progress`  -  show user a hint.
 
 **Sort order (descending precedence)**:
 1. `priority` → Blocker(100) > Critical(90) > High(80) > Medium(50) > Low(30) > Lowest(10) > (none=0)
@@ -50,17 +50,17 @@ curl -s -H "Authorization: Bearer $TOKEN" \
 **Format** (priority badge prefix, status suffix):
 ```
 [3/4] Pick issue (24 found, priority-sorted):
-  > [Blocker] PROJ-12345 — Login crash on iOS 17           (In Progress)
-    [Critical] PROJ-12340 — Payment fails for refunds       (In Review)
-    [High]    PROJ-12338 — Dark mode polish                 (To Do)
-    [Medium]  PROJ-12330 — Add empty state                  (To Do)
-    [—]       PROJ-12300 — Refactor LoginViewModel          (To Do)
+  > [Blocker] PROJ-12345  -  Login crash on iOS 17           (In Progress)
+    [Critical] PROJ-12340  -  Payment fails for refunds       (In Review)
+    [High]    PROJ-12338  -  Dark mode polish                 (To Do)
+    [Medium]  PROJ-12330  -  Add empty state                  (To Do)
+    [ - ]       PROJ-12300  -  Refactor LoginViewModel          (To Do)
 ```
 
 - AskUserQuestion (multiSelect=false)
 - Output: selected `KEY` (e.g. `PROJ-12345`)
 
-> **Rule**: Sort by priority for visibility, but don't force the user. No "P1 must come first" coercion — just signal.
+> **Rule**: Sort by priority for visibility, but don't force the user. No "P1 must come first" coercion  -  just signal.
 
 ### [3.5/4] Maturity check (auto)
 
@@ -81,7 +81,7 @@ After issue selection, inspect `maturity` from `~/.claude/lib/issue-fetcher.sh`:
 | only `warnings` | AskUserQuestion: show summary + "Continue?". Autopilot auto-continues; warnings logged to `agent-log.md` |
 | both empty (score ≥ 90) | Continue silently |
 
-> **Resolution check**: If Jira `resolution` is set (`Fixed`, `Done`, `Won't Do`, `Resolved`...), `already_resolved` is added — the issue was closed already. To reopen, clear `resolution` in Jira first.
+> **Resolution check**: If Jira `resolution` is set (`Fixed`, `Done`, `Won't Do`, `Resolved`...), `already_resolved` is added  -  the issue was closed already. To reopen, clear `resolution` in Jira first.
 
 > **fixVersions**: When `descriptor.fixVersions` is non-empty (e.g. `["v1.48.0"]`) and a matching `release/v1.48.0` branch exists in `prefs.projects[*].branches`, suggest that branch. Otherwise fall back to `develop`/cwd current.
 
@@ -109,7 +109,7 @@ After issue selection, inspect `maturity` from `~/.claude/lib/issue-fetcher.sh`:
    }
    ```
 
-2. **Bridge to agent-state.json v2.1.0** — picker → Phase 0:
+2. **Bridge to agent-state.json v2.1.0**  -  picker → Phase 0:
    ```bash
    ~/.claude/lib/multi-repo-pipeline.sh bridge /tmp/multi-agent-picker-{taskId}.json
    # writes ~/.claude/logs/multi-agent/{primary}/{taskId}/agent-state.json
@@ -120,7 +120,7 @@ After issue selection, inspect `maturity` from `~/.claude/lib/issue-fetcher.sh`:
    ~/.claude/lib/multi-repo-pipeline.sh prepare /tmp/multi-agent-picker-{taskId}.json
    ```
 
-4. **Phase 0 entry** — pipeline reads the bridged `agent-state.json` and skips
+4. **Phase 0 entry**  -  pipeline reads the bridged `agent-state.json` and skips
    redundant Jira/GitHub fetches.
 
 `autopilot` arg → start with `MULTI_AGENT_AUTOPILOT=1`.

package/pipeline/commands/multi-agent/kill.md

@@ -1,19 +1,19 @@
 ---
 description: "Stop the given task, then remove its worktree and branch. Asks for confirmation."
-argument-hint: "#id — task ID to delete (e.g. #2)"
+argument-hint: "#id  -  task ID to delete (e.g. #2)"
 ---
 
-# multi-agent kill — Stop and Delete Task
+# multi-agent kill  -  Stop and Delete Task
 
 **Input**: $ARGUMENTS
 
-Stop the task and remove its worktree + branch + logs. Destructive operation — always asks for confirmation.
+Stop the task and remove its worktree + branch + logs. Destructive operation  -  always asks for confirmation.
 
 ## Steps
 
-1. **Find the task** — parse `#N` or `{JIRA-KEY}-XXXXX` from the argument.
+1. **Find the task**  -  parse `#N` or `{JIRA-KEY}-XXXXX` from the argument.
 
-2. **Show details** — print the task summary:
+2. **Show details**  -  print the task summary:
    ```
    ⚠️ Task to delete:
    - ID: #3
@@ -31,7 +31,7 @@ Stop the task and remove its worktree + branch + logs. Destructive operation —
    git branch -D {branch-name}
    ```
 
-5. **Remote branch** — also ask: "Delete the remote branch too?"
+5. **Remote branch**  -  also ask: "Delete the remote branch too?"
    - Yes → `git push origin --delete {branch-name}`
    - No → local-only delete.