@mmerterden/multi-agent-pipeline 18.0.0 → 19.1.0

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

@@ -53,27 +53,26 @@ How It Works (Phase 0  -  Interactive Flow):
 Pipeline (after Phase 0)  -  shown as visual cards in terminal:
 
   Phase 0:   Init       -> The 8 steps above
-  Phase 1:   Analysis   -> Stack detection + codebase scan (Sonnet)
-  Phase 2:   Planning   -> Task breakdown + architecture review + Plan Approval Gate
-                          (clarification max 2 rounds + approval loop  -  Full + interactive
-                           only; a Short run has no plan, autopilot may not ask)
-  Phase 3:   Dev        -> TDD: test -> code -> build (Sonnet) + build queue
-  Phase 4:   Review     -> Deterministic gates + parallel AI review + Fable triage
-                          (Claude Code: Fable + Opus + Sonnet · Copilot CLI: GPT-5.4 + Opus + Sonnet)
-  Phase 5:   Test       -> Optional: switch to branch, test in Xcode
-                          (only /multi-agent has it; every autopilot and local entry drops it)
-  Phase 6:   Commit     -> Commit -> push -> PR + issue body update (never auto-closes)
-  Phase 7:   Report     -> Channels dispatcher (PR · Jira · Confluence · Wiki, multi-select)
+  Phase 1:   Plan       -> Stack detection + codebase scan, task breakdown, architecture
+                          review, Plan Approval Gate (Opus; max 2 clarification rounds,
+                          Full + interactive only  -  a Short run has no plan)
+  Phase 2:   Dev        -> TDD: test -> code -> build (Sonnet) + build queue, then the
+                          Verify exit gate: build, lint, tests, secrets. The build runs
+                          ONCE per run and its log carries into Review
+  Phase 3:   Review     -> Parallel AI review + Fable triage, then the optional user test
+                          (Claude Code: Fable + Opus + Sonnet · Copilot: GPT-5.4 + Opus + Sonnet;
+                          the user test is the interactive half: branch, test in Xcode)
+  Phase 4:   Commit     -> Commit -> push -> PR + issue body update (never auto-closes)
+  Phase 5:   Report     -> Channels dispatcher (PR · Jira · Confluence · Wiki, multi-select)
                           + internal capture (agent-log · knowledge · memory)
 
-  Autopilot always pauses at the Phase 7 channels menu (30-min timeout → session ends cleanly).
+  Autopilot always pauses at the Phase 5 channels menu (30-min timeout → session ends cleanly).
 
   Pipeline depth is asked at Phase 0 Step 7.5, not passed as a flag:
-    Full    Analysis -> Plan -> Dev(Sonnet) -> Review -> Test -> Commit -> Report
-    Short   Dev(Opus, self-contained) -> Review -> Test -> Commit -> Report
-  Short skips Phases 1-2 only. Review is NEVER skipped.
-  Recommended from taskType: bugfix/chore -> Short, feature/refactor/component -> Full.
-  Autopilot never asks and always runs Full.
+    Full    Plan -> Dev(Sonnet) -> Review -> Commit -> Report
+    Short   Dev(Opus, self-contained) -> Review -> Commit -> Report
+  Short skips Phase 1 only; Review is NEVER skipped. Recommended from taskType:
+  bugfix/chore -> Short, feature/refactor/component -> Full. Autopilot always runs Full.
 
   Every step is logged. Error in any phase -> pause -> resume to continue.
 
@@ -90,10 +89,10 @@ Four pipeline entries:
 
   --local on the base command is the same as the :local entry.
   autopilot skips every confirmation INCLUDING the plan gate and the depth
-  question, and auto commit/PR  -  EXCEPT the Phase 7 channels menu, which
+  question, and auto commit/PR  -  EXCEPT the Phase 5 channels menu, which
   always pauses.
 
-  /multi-agent:resume-local [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 gate) → Commit/PR → Report (no dev)
 
 ------------------------------
 
@@ -126,7 +125,7 @@ Post-Hoc & Side-Channel:
   /multi-agent:complaint-analysis ["run-name"]  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
+  /multi-agent:diff-explain   Map a Phase 3 triage finding back to specific diff lines
   /multi-agent:graph         Build and query the repo code graph (symbols, imports, references), LLM-free
   /multi-agent:search         Cross-task log search with smart ranking; --semantic queries triage corpus
   /multi-agent:scan           Skill security scan against tiered pattern catalog
@@ -142,6 +141,10 @@ 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:model [on|off] Turn the top model rung (fable) on or off; keeps costBudget.pricingModel in step
+  /multi-agent:route-on       Arm policy-driven model routing: strategy, scope, rules. Ships off
+  /multi-agent:route-off      Disarm routing and KEEP the rules, so route-on does not re-ask
+  /multi-agent:route-status   What is armed, which rule applies where, and the limit: subagents stay on Anthropic
   /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 + toolkit MCP)
   /multi-agent:update         Pull latest pipeline + reinstall + run migrations
@@ -208,7 +211,7 @@ 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 3 user-test step, 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.
@@ -250,21 +253,18 @@ Key Features:
   Multi-Repo       Per-repo worktrees + identity, integration build before commit
   Identity Routing Git identity picked from the repo origin URL (corporate vs personal)
   Issue Safety     Never auto-closes issues (4 approvals, GitHub + Jira)
-  Store Compliance /multi-agent:test "store-ready"  -  18-rule iOS audit (ITMS, Privacy Manifest,
-                   signing, debug leaks, IPv6, SDK list) + 21-rule Android audit
+  Store Compliance /multi-agent:test "store-ready"  -  18-rule iOS audit (ITMS, Privacy Manifest, signing, debug leaks, IPv6, SDK) + 21-rule Android audit
   Bilingual        EN + TR  -  outputLanguage toggles assistant explanations; promptLanguage is locked en
 
 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,
-                   migrations, no-test-change, complexity)  -  heuristic, sub-second
-  Test Gap Report  Phase 5 Step 0 surfaces public symbols added in this branch with no paired test
+  Diff Risk Score  Phase 3 Step 1.75 ranks files before reviewer dispatch  -  heuristic, sub-second: security paths, migrations, no-test-change, complexity
+  Test Gap Report  Phase 3 surfaces public symbols added in this branch with no paired test
   Visual Evidence  before/after stills + flow video on UI changes; Step 7.7 asks the depth
-  Cost Breakdown   Phase 7 appends per-phase tokens + estimated USD to agent-log.md
-  Triage Memory    Phase 7 ingests accepted/deferred/rejected findings into a repo corpus
-  Prior-Art Lookup Phase 1 + Phase 4 query the corpus for similar findings, inject as context
-  Per-Persona      Dispatch reads `preferredModel` from the persona file; override per call via
-                   PHASE_MODEL_OVERRIDE; ladder fable -> opus -> sonnet -> haiku
+  Cost Breakdown   Phase 5 appends per-phase tokens + estimated USD to agent-log.md
+  Triage Memory    Phase 5 ingests accepted/deferred/rejected findings into a repo corpus
+  Prior-Art Lookup Phase 1 + Phase 3 query the corpus for similar findings, inject as context
+  Per-Persona      Dispatch reads `preferredModel` from the persona file; PHASE_MODEL_OVERRIDE overrides per call; ladder fable -> opus -> sonnet -> haiku
 
 ------------------------------
 
@@ -333,27 +333,26 @@ Nasıl Çalışır (Phase 0  -  İnteraktif Akış):
 Pipeline (Phase 0'dan sonra)  -  terminalde görsel kart olarak görünür:
 
   Phase 0:   Init       -> Yukarıdaki 8 adım
-  Phase 1:   Analysis   -> Stack tespiti + codebase taraması (Sonnet)
-  Phase 2:   Planning   -> Task kırılımı + mimari inceleme + Plan Onay Kapısı
-                          (clarification max 2 tur + onay döngüsü  -  sadece Tam +
-                           etkileşimli; Kısa'da plan yok, autopilot soru soramaz)
-  Phase 3:   Dev        -> TDD: test -> kod -> build (Sonnet) + build queue
-  Phase 4:   Review     -> Deterministik kapılar + paralel AI review + Fable triage
-                          (Claude Code: Fable + Opus + Sonnet · Copilot CLI: GPT-5.4 + Opus + Sonnet)
-  Phase 5:   Test       -> Opsiyonel: branch'e geç, Xcode'da test
-                          (yalnız /multi-agent'ta var; her autopilot ve local girişi düşürür)
-  Phase 6:   Commit     -> Commit -> push -> PR + issue body güncelleme (hiç auto-close yok)
-  Phase 7:   Report     -> Channels dispatcher (PR · Jira · Confluence · Wiki, multi-select)
+  Phase 1:   Plan       -> Stack tespiti + codebase taraması, task kırılımı, mimari
+                          inceleme, Plan Onay Kapısı (Opus; max 2 clarification turu,
+                          sadece Tam + etkileşimli  -  Kısa'da plan yok)
+  Phase 2:   Dev        -> TDD: test -> kod -> build (Sonnet) + build queue, sonra Verify
+                          çıkış kapısı: build, lint, test, sır taraması. Build koşu başına
+                          BİR kez çalışır, log'u Review'a devreder
+  Phase 3:   Review     -> Paralel AI review + Fable triage, sonra opsiyonel kullanıcı testi
+                          (Claude Code: Fable + Opus + Sonnet · Copilot: GPT-5.4 + Opus + Sonnet;
+                          kullanıcı testi etkileşimli yarısı: branch'e geç, Xcode'da test)
+  Phase 4:   Commit     -> Commit -> push -> PR + issue body güncelleme (hiç auto-close yok)
+  Phase 5:   Report     -> Channels dispatcher (PR · Jira · Confluence · Wiki, multi-select)
                           + internal capture (agent-log · knowledge · memory)
 
-  Autopilot Phase 7'deki channels menüsünde HER ZAMAN durur (30 dk timeout → session temiz biter).
+  Autopilot Phase 5'teki channels menüsünde HER ZAMAN durur (30 dk timeout → session temiz biter).
 
   Pipeline derinliği Faz 0 Adım 7.5'te sorulur, bayrakla geçilmez:
-    Tam     Analiz -> Plan -> Dev(Sonnet) -> Review -> Test -> Commit -> Report
-    Kısa    Dev(Opus, kendi kendine yeten) -> Review -> Test -> Commit -> Report
-  Kısa yalnız Faz 1-2'yi atlar. Review ASLA atlanmaz.
-  taskType'a göre önerilir: bugfix/chore -> Kısa, feature/refactor/component -> Tam.
-  Autopilot hiç sormaz, her zaman Tam koşar.
+    Tam     Plan -> Dev(Sonnet) -> Review -> Commit -> Report
+    Kısa    Dev(Opus, kendi kendine yeten) -> Review -> Commit -> Report
+  Kısa yalnız Faz 1'i atlar; Review ASLA atlanmaz. taskType'a göre önerilir:
+  bugfix/chore -> Kısa, feature/refactor/component -> Tam. Autopilot her zaman Tam koşar.
 
   Her adım loglanır. Herhangi bir fazdaki hata -> pause -> resume ile devam et.
 
@@ -370,9 +369,9 @@ Dört pipeline girişi:
 
   Ana komuta --local eklemek :local girişiyle aynıdır.
   autopilot plan kapısı ve derinlik sorusu dahil her onayı atlar, otomatik
-  commit/PR açar  -  İSTİSNA: Faz 7 channels menüsü, o her zaman durur.
+  commit/PR açar  -  İSTİSNA: Faz 5 channels menüsü, o her zaman durur.
 
-  /multi-agent:resume-local [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 kapısı) → Commit/PR → Report (dev yok)
 
 ------------------------------
 
@@ -404,7 +403,7 @@ Post-Hoc & Side-Channel:
   /multi-agent:complaint-analysis ["run-adı"]  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
+  /multi-agent:diff-explain   Phase 3 triage bulgusunu diff satırlarına eşle
   /multi-agent:graph         Repo kod grafiğini kur ve sorgula (semboller, import'lar, referanslar), LLM'siz
   /multi-agent:search         Task log'larında akıllı arama; --semantic triage corpus'unu sorgular
   /multi-agent:scan           Skill güvenlik taraması (tiered pattern catalog)
@@ -419,6 +418,10 @@ 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:model [on|off] Üst model basamağını (fable) aç/kapat; costBudget.pricingModel'i birlikte taşır
+  /multi-agent:route-on       Politika güdümlü model yönlendirmesini açar: strateji, kapsam, kurallar. Varsayılan kapalı
+  /multi-agent:route-off      Yönlendirmeyi kapatır, kuralları SAKLAR; route-on aynı şeyi tekrar sormaz
+  /multi-agent:route-status   Ne açık, hangi kural nerede geçerli, ve sınır: subagent'lar Anthropic'te kalır
   /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 + multi-agent-toolkit MCP)
   /multi-agent:update             En son pipeline'ı çek + reinstall + migration çalıştır
@@ -485,7 +488,7 @@ 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 3 kullanıcı-testi adımı, 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.
@@ -527,20 +530,17 @@ Temel Özellikler:
   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 18 kurallık audit (ITMS / Privacy Manifest /
-                   code signing / debug-tool leak / IPv6 / SDK list / vb.) + Android için 21 kurallık audit
+  Store Compliance /multi-agent:test "store-ready"  -  iOS 18 kurallık audit (ITMS / Privacy Manifest / signing / debug leak / IPv6 / SDK) + Android 21 kurallık audit
   Bilingual        EN + TR  -  outputLanguage assistant açıklamasını değiştirir; promptLanguage en kilitli
 
 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
-  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
-  Per-Persona      Reviewer/agent dispatch persona dosyasından `preferredModel` okur;
-                   per-call override PHASE_MODEL_OVERRIDE ile; merdiven fable -> opus -> sonnet -> haiku
+  Diff Risk Score  Phase 3 Step 1.75 reviewer dispatch'tan önce dosyaları sıralar  -  heuristik: güvenlik path'i, schema migration, testsiz değişiklik, complexity delta
+  Test Gap Report  Phase 3  -  bu branch'te eklenmiş public sembol + eşleşen test yoksa raporlar
+  Cost Breakdown   Phase 5 agent-log.md'ye faz başına token (in/out) + tahmini USD ekler
+  Triage Memory    Phase 5 accepted/deferred/rejected bulguları repo başına corpus'a yazar
+  Prior-Art Lookup Phase 1 + Phase 3 corpus'tan benzer geçmiş bulgu sorgular, ek context olarak enjekte
+  Per-Persona      Dispatch persona dosyasından `preferredModel` okur; per-call override PHASE_MODEL_OVERRIDE; merdiven fable -> opus -> sonnet -> haiku
 
 ------------------------------
 

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

@@ -12,7 +12,7 @@ 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 3 test prompt, Phase 4 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:** it governs the picker's structural chrome only  -  the `AskUserQuestion` `header` chip, host error UI, and internal contract identifiers. The chip stays English because it is capped at 12 characters and most Turkish equivalents overflow it. Everything a user actually reads follows `outputLanguage`: the picker `question`, each option's `label`, and each option's `description`, per the canonical per-field matrix in `multi-agent-refs/rules.md`. A picker whose question or buttons are English on a Turkish run is a bug, not the contract. The host's own **Other** row is injected by the CLI and stays English on every run; nothing in the pipeline can localize it.
@@ -109,5 +109,5 @@ Render in the **new** outputLanguage:
 
 - `setup.md` Step 0  -  first-run language picker (asks only outputLanguage; promptLanguage seeded as `en`)
 - `prefs.schema.json`  -  `global.promptLanguage` (fixed `"en"`) and `global.outputLanguage` definitions
-- `phase-5-test.md`, `phase-6-commit.md`  -  interactive prompts follow the per-field matrix: `question` + `label` + `description` in `outputLanguage`, `header` English
+- `phase-3-review.md`, `phase-4-commit.md`  -  interactive prompts follow the per-field matrix: `question` + `label` + `description` in `outputLanguage`, `header` English
 - `help.md`  -  reads outputLanguage to render its own help text

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

@@ -28,12 +28,12 @@ Same phase count and order as the normal pipeline:
 
 ```
 Phase 0: Init       → project detection, branch check, state (NO worktree)
-Phase 1: Analysis   → codebase scan (parallel explore agents, Opus)
-Phase 2: Planning   → task breakdown, Plan Approval Gate (approval loop)
-Phase 3: Dev        → TDD (Sonnet), build queue
-Phase 4: Review     → deterministic gates + parallel review + Fable triage
-Phase 6: Commit     → pre-commit checkout prompt, commit + push + PR
-Phase 7: Report     → Jira / Wiki / Confluence + log + knowledge/memory
+Phase 1: Plan (analysis)   → codebase scan (parallel explore agents, Opus)
+Phase 1: Plan   → task breakdown, Plan Approval Gate (approval loop)
+Phase 2: Dev        → TDD (Sonnet), build queue
+Phase 3: Review     → deterministic gates + parallel review + Fable triage
+Phase 4: Commit     → pre-commit checkout prompt, commit + push + PR
+Phase 5: Report     → Jira / Wiki / Confluence + log + knowledge/memory
 ```
 
 ## Delegation
@@ -73,11 +73,11 @@ bash $HOME/.claude/scripts/phase-tracker.sh update 0 in_progress
 
 # Phase 0 Step 7.5, immediately after the depth answer - the first moment this
 # mode knows its phase set. Full:
-for p in "1:Analysis" "2:Planning" "3:Dev" "4:Review" "6:Commit" "7:Report"; do
+for p in "1:Plan" "2:Dev" "3:Review" "4:Commit" "5:Report"; do
   bash $HOME/.claude/scripts/phase-tracker.sh add "${p%%:*}" "${p#*:}"
 done
 # Short (Analysis and Planning are not run, so they get no tile at all):
-for p in "3:Dev" "4:Review" "6:Commit" "7:Report"; do
+for p in "2:Dev" "3:Review" "4:Commit" "5:Report"; do
   bash $HOME/.claude/scripts/phase-tracker.sh add "${p%%:*}" "${p#*:}"
 done
 # Then the widget, narrowed to the phases that do not have a tile yet:
@@ -98,7 +98,7 @@ In Claude Code the agent MUST also drive the native TaskList widget so the user
 
 ```text
 # Register one tile per phase, capture the taskId, persist it:
-for each phase in 0:Init at Step -1, then 1:Analysis, 2:Planning, 3:Dev, 4:Review, 6:Commit, 7:Report (Full) or 3:Dev, 4:Review, 6:Commit, 7:Report (Short) at Step 7.5:
+for each phase in 0:Init at Step -1, then 1:Plan, 2:Dev, 3:Review, 4:Commit, 5:Report (Full) or 2:Dev, 3:Review, 4:Commit, 5:Report (Short) at Step 7.5:
   TaskCreate({ subject: "Phase <N>: <Name>", activeForm: "<doing-form>" })
     -> returns taskId
   bash $HOME/.claude/scripts/phase-tracker.sh meta <N> tasklist_id "<taskId>"
@@ -115,11 +115,11 @@ TaskUpdate({ taskId: <saved>, status: "completed" })
 bash $HOME/.claude/scripts/phase-tracker.sh update <N> completed
 ```
 
-`--local` mode does NOT TaskCreate phases 5  -  those are not part of the `--local` phase set (`0:Init 1:Analysis 2:Planning 3:Dev 4:Review 6:Commit 7:Report`). Only register tiles for the active set.
+`--local` mode TaskCreates all 6 phases (no phase is skipped).
 
 #### TaskCreate ordering (strict)
 
-**All TaskCreate calls in a batch fire in strict phase-number order BEFORE any TaskUpdate is applied.** For `--local` that means: Phase 0 at Step -1, then the rest in ascending order at Step 7.5 (Phase 0 → Phase 1 → Phase 2 → Phase 3 → Phase 4 → Phase 6 → Phase 7 minus whatever the depth answer drops). The native widget renders by creation order, not by phase number  -  out-of-order calls produce visually scrambled tile stacks. Full ordering contract in `$HOME/.claude/multi-agent-refs/tracker-contract.md` section "TaskCreate ordering (strict)".
+**All TaskCreate calls in a batch fire in strict phase-number order BEFORE any TaskUpdate is applied.** For `--local` that means: Phase 0 at Step -1, then the rest in ascending order at Step 7.5 (Phase 0 → Phase 1 → Phase 2 → Phase 3 → Phase 4 → Phase 5 minus whatever the depth answer drops). The native widget renders by creation order, not by phase number  -  out-of-order calls produce visually scrambled tile stacks. Full ordering contract in `$HOME/.claude/multi-agent-refs/tracker-contract.md` section "TaskCreate ordering (strict)".
 
 ### Visual channel  -  Copilot CLI / plain shell
 

package/pipeline/commands/multi-agent/local-autopilot/SKILL.md

@@ -1,6 +1,6 @@
 ---
-description: "Full pipeline + local + autopilot  -  no worktree, no confirmations; runs 7 phases (User Test skipped) end-to-end on the current branch. Use when the full pipeline should run on the current branch with no worktree and no prompts."
-description-tr: "Tam pipeline + lokal + autopilot - worktree yok, onay yok; 7 fazı (Kullanıcı Testi atlanır) mevcut branch üzerinde uçtan uca koşar."
+description: "Full pipeline + local + autopilot  -  no worktree, no confirmations; runs all 6 phases end-to-end on the current branch. Use when the full pipeline should run on the current branch with no worktree and no prompts."
+description-tr: "Tam pipeline + lokal + autopilot - worktree yok, onay yok; 6 fazı mevcut branch üzerinde uçtan uca koşar (kullanıcı testi Review'ın içinde, autopilot'ta atlanır)."
 argument-hint: '"task"  -  issue URL, Jira ID, free-text, or #id (for resume)'
 allowed-tools: Agent, Bash, Read, Write, Edit, Glob, Grep, TaskCreate, TaskUpdate, TaskList, TaskGet, AskUserQuestion, WebFetch, WebSearch, Skill
 ---
@@ -11,16 +11,16 @@ allowed-tools: Agent, Bash, Read, Write, Edit, Glob, Grep, TaskCreate, TaskUpdat
 
 > **Language (read FIRST)**: Before any status output, read `prefs.global.outputLanguage` and render every conversational line in it. `AskUserQuestion` renders its `question`, option `label`s and option `description`s in `outputLanguage`; only `header` stays English (<=12-char chip); external payload bodies follow `outputLanguage` too (identifiers, commit messages, branch names stay English). Full contract: `$HOME/.claude/multi-agent-refs/rules.md` "Language Application".
 
-Run the full pipeline **without a worktree** and **with every confirmation skipped**. Phase 5 (User Test) does not run (no worktree to check out from, and no interaction), so 7 phases execute. The `autopilot + local` combination  -  vs `/multi-agent:autopilot` the only difference is no worktree (work stays on the current branch); vs `/multi-agent:local` the only difference is zero interaction.
+Run the full pipeline **without a worktree** and **with every confirmation skipped**. All six phases execute. The user test inside Phase 3 Review is skipped  -  there is no worktree to check out from and no interaction to have  -  but it stopped being a phase of its own in v19.0.0, so nothing is dropped from the set. The `autopilot + local` combination  -  vs `/multi-agent:autopilot` the only difference is no worktree (work stays on the current branch); vs `/multi-agent:local` the only difference is zero interaction.
 
 ## Matrix (which one should I use?)
 
 | Command | Pipeline | Worktree | Confirmations |
 |---|---|---|---|
-| `/multi-agent "task"` | Full 8 phases | ✅ | ✅ (interactive) |
-| `/multi-agent:autopilot "task"` | 7 phases (no User Test) | ✅ | ❌ (autopilot) |
-| `/multi-agent:local "task"` | 7 phases (no User Test) | ❌ | ✅ (interactive) |
-| **`/multi-agent:local-autopilot "task"`** | **7 phases (no User Test)** | **❌** | **❌ (autopilot)** |
+| `/multi-agent "task"` | 6 phases, user test offered | ✅ | ✅ (interactive) |
+| `/multi-agent:autopilot "task"` | 6 phases, user test skipped | ✅ | ❌ (autopilot) |
+| `/multi-agent:local "task"` | 6 phases, user test offered | ❌ | ✅ (interactive) |
+| **`/multi-agent:local-autopilot "task"`** | **6 phases, user test skipped** | **❌** | **❌ (autopilot)** |
 
 Depth is a separate axis, asked at Phase 0 Step 7.5 rather than encoded in the command name: Full runs every phase above, Short runs Dev → Review → Test → Commit → Report. The two autopilot rows never ask and always run Full.
 
@@ -28,7 +28,7 @@ Depth is a separate axis, asked at Phase 0 Step 7.5 rather than encoded in the c
 
 **vs `/multi-agent:autopilot`**: no worktree is created; work stays on the current branch. The task runs in the same editor / IDE session  -  no second folder.
 
-**vs `/multi-agent:local`**: Phase 2 Plan Approval Gate is skipped (the safety classifier still runs) and Phase 6 commit / PR runs without confirmation. Both modes already skip Phase 5 (User Test) because neither has a worktree, so the same seven phases execute  -  review / triage / build discipline are preserved.
+**vs `/multi-agent:local`**: Phase 2 Plan Approval Gate is skipped (the safety classifier still runs) and Phase 4 commit / PR runs without confirmation. Both modes already skip Phase 5 (User Test) because neither has a worktree, so the same seven phases execute  -  review / triage / build discipline are preserved.
 
 ## When to use it
 
@@ -67,7 +67,7 @@ Depth is a separate axis, asked at Phase 0 Step 7.5 rather than encoded in the c
 
 ## Delegation
 
-Orchestrator routing: the routing table in `$HOME/.claude/commands/multi-agent/SKILL.md` resolves `local-autopilot` as the union of the `local` + `autopilot` mode mixins. Contract details: `$HOME/.claude/multi-agent-refs/phases/phase-0-init.md` Step 6 (local branch) + `$HOME/.claude/multi-agent-refs/phases/phase-2-planning.md` Step 5 (autopilot gate skip + safety classifier).
+Orchestrator routing: the routing table in `$HOME/.claude/commands/multi-agent/SKILL.md` resolves `local-autopilot` as the union of the `local` + `autopilot` mode mixins. Contract details: `$HOME/.claude/multi-agent-refs/phases/phase-0-init.md` Step 6 (local branch) + `$HOME/.claude/multi-agent-refs/phases/phase-1-plan.md` Step 5 (autopilot gate skip + safety classifier).
 ## Required: outward-facing payload contracts
 
 Before writing anything outward-facing  -  PR body, Jira comment, Confluence page, closing report  -  load `$HOME/.claude/multi-agent-refs/payload-contracts.md`. It names the canonical section set for each payload, the markup dialect per surface (PR body is Markdown, Jira is wiki markup  -  mixing them is a defect), and the token/duration numbers the closing report must carry. Improvising a payload shape from memory is the most common failure of the short modes.
@@ -88,7 +88,7 @@ Two channels run in parallel at every phase boundary:
 ```bash
 # Phase 0, very first shell call (every CLI):
 bash $HOME/.claude/scripts/phase-tracker.sh init "$TASK_ID"
-for p in "0:Init" "1:Analysis" "2:Planning" "3:Dev" "4:Review" "6:Commit" "7:Report"; do
+for p in "0:Init" "1:Plan" "2:Dev" "3:Review" "4:Commit" "5:Report"; do
   bash $HOME/.claude/scripts/phase-tracker.sh add "${p%%:*}" "${p#*:}"
 done
 bash $HOME/.claude/scripts/phase-tracker.sh update 0 in_progress
@@ -108,7 +108,7 @@ In Claude Code the agent MUST also drive the native TaskList widget so the user
 
 ```text
 # Register one tile per phase, capture the taskId, persist it:
-for each phase in 0:Init, 1:Analysis, 2:Planning, 3:Dev, 4:Review, 6:Commit, 7:Report:
+for each phase in 0:Init, 1:Plan, 2:Dev, 3:Review, 4:Commit, 5:Report:
   TaskCreate({ subject: "Phase <N>: <Name>", activeForm: "<doing-form>" })
     -> returns taskId
   bash $HOME/.claude/scripts/phase-tracker.sh meta <N> tasklist_id "<taskId>"
@@ -125,11 +125,11 @@ TaskUpdate({ taskId: <saved>, status: "completed" })
 bash $HOME/.claude/scripts/phase-tracker.sh update <N> completed
 ```
 
-`--local autopilot` mode does NOT TaskCreate phases 5  -  those are not part of the `--local autopilot` phase set (`0:Init 1:Analysis 2:Planning 3:Dev 4:Review 6:Commit 7:Report`). Only register tiles for the active set.
+`--local autopilot` mode TaskCreates all 6 phases (no phase is skipped).
 
 #### TaskCreate ordering (strict)
 
-**All TaskCreate calls in a batch fire in strict phase-number order BEFORE any TaskUpdate is applied.** For `--local autopilot` that means: Phase 0 → Phase 1 → Phase 2 → Phase 3 → Phase 4 → Phase 6 → Phase 7. The native widget renders by creation order, not by phase number  -  out-of-order calls produce visually scrambled tile stacks. Full ordering contract in `$HOME/.claude/multi-agent-refs/tracker-contract.md` section "TaskCreate ordering (strict)".
+**All TaskCreate calls in a batch fire in strict phase-number order BEFORE any TaskUpdate is applied.** For `--local autopilot` that means: Phase 0 → Phase 1 → Phase 2 → Phase 3 → Phase 4 → Phase 5. The native widget renders by creation order, not by phase number  -  out-of-order calls produce visually scrambled tile stacks. Full ordering contract in `$HOME/.claude/multi-agent-refs/tracker-contract.md` section "TaskCreate ordering (strict)".
 
 ### Visual channel  -  Copilot CLI / plain shell
 

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

@@ -15,7 +15,7 @@ Show the task's detailed agent-log.md report.
 1. **Parse task ID**  -  extract the `#N` form from the argument.
    - No argument → find the most recent (highest-ID) worktree.
 
-2. **Find the worktree**  -  search the known repos. A task whose worktree was removed after its PR (Phase 6 finalize) is found under `$HOME/.claude/logs/multi-agent/<project>/<task-id>/` instead; the `agent-log.md` was always there, and `artifacts/agent-state.json` holds the state. Look there before reporting "task not found":
+2. **Find the worktree**  -  search the known repos. A task whose worktree was removed after its PR (Phase 4 finalize) is found under `$HOME/.claude/logs/multi-agent/<project>/<task-id>/` instead; the `agent-log.md` was always there, and `artifacts/agent-state.json` holds the state. Look there before reporting "task not found":
    ```bash
    find ~/my-ios-app/.worktrees/ ~/my-figma-app/.worktrees/ ~/my-ui-components/.worktrees/ -name "agent-state.json" -maxdepth 2 2>/dev/null
    ```
@@ -23,7 +23,7 @@ Show the task's detailed agent-log.md report.
 
 3. **Read agent-log.md**  -  display the file.
 
-4. **Cost + durations come from the tracker, not only the log.** The tracker contract promises token/duration data "surfaced in `:log` reports", and agent-log.md only carries it when Phase 7 appended the Cost Breakdown. When that section is absent, render it live:
+4. **Cost + durations come from the tracker, not only the log.** The tracker contract promises token/duration data "surfaced in `:log` reports", and agent-log.md only carries it when Phase 5 appended the Cost Breakdown. When that section is absent, render it live:
    ```bash
    bash $HOME/.claude/scripts/render-agent-log-cost.sh "<task-id>" 2>/dev/null
    ```

package/pipeline/commands/multi-agent/manual-test/SKILL.md

@@ -1,9 +1,9 @@
 ---
-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). Use when a finished change needs trying by hand on a device or simulator."
-description-tr: "Aktif görevin branch'ine geçer ve Xcode'da manuel test için hazırlar. Faz 5'in bağımsız hali (UI Bug Hunter /multi-agent:test'te)."
+description: "Switch to the active task's branch and prepare it for manual testing in Xcode. Phase 3 user-test step, standalone (the UI Bug Hunter lives at /multi-agent:test). Use when a finished change needs trying by hand on a device or simulator."
+description-tr: "Aktif görevin branch'ine geçer ve Xcode'da manuel test için hazırlar. Faz 3 kullanıcı-test adımının bağımsız hali (UI Bug Hunter /multi-agent:test'te)."
 ---
 
-# multi-agent manual-test  -  Phase 5 Manual Test Mode
+# multi-agent manual-test  -  Phase 3 Manual Test Mode
 
 **Input**: $ARGUMENTS
 
@@ -13,7 +13,7 @@ Lets you switch to the task branch for manual testing in Xcode before the PR is
 
 1. **Find the task**  -  parse `#N` from the argument or pick the most recent task
 
-2. **Check state**  -  the task must have completed Phase 3 or later
+2. **Check state**  -  the task must have completed Phase 2 (Dev) or later
    - Phase < 3 → "No code yet, run `resume #N` first"
 
 3. **Remove the worktree and switch to the branch**:
@@ -25,8 +25,8 @@ Lets you switch to the task branch for manual testing in Xcode before the PR is
 
    Then mark the tracker as waiting (this CONTINUES the task's existing `tracker-state.json`; never `init` here - see `$HOME/.claude/multi-agent-refs/tracker-contract.md` "Continuation runs"). On Claude Code in a fresh session, first rebuild the TaskList from state per the same contract:
    ```bash
-   bash $HOME/.claude/scripts/phase-tracker.sh update 5 in_progress
-   bash $HOME/.claude/scripts/phase-tracker.sh now 5 "awaiting local test (user)"
+   bash $HOME/.claude/scripts/phase-tracker.sh update 3 in_progress
+   bash $HOME/.claude/scripts/phase-tracker.sh now 3 "awaiting local test (user)"
    bash $HOME/.claude/scripts/phase-tracker.sh render
    ```
 
@@ -40,7 +40,7 @@ Lets you switch to the task branch for manual testing in Xcode before the PR is
      • Manual test on the simulator
 
    Reply:
-     ✅ "ok" → continue to Phase 6 (commit)
+     ✅ "ok" → continue to Phase 4 (commit)
      ❌ "fix: ..." → recreate the worktree and apply the fix
    ```
 
@@ -51,5 +51,5 @@ Lets you switch to the task branch for manual testing in Xcode before the PR is
      ```json
      {"criteria":[{"spec":"<quote>","source":"analysis 15.2 | plan task 3 | user","observed":"<what was seen>","verdict":"pass|fail|not-tested","reason":"<required when not-tested>","screenshot":"<path or null>"}],"verdict":"passed|failed"}
      ```
-     then run `node $HOME/.claude/scripts/evidence-gate.mjs --claim manual --status passed --evidence "$WORKTREE/.pipeline/manual-test.json"`, adding `--require-screenshot` when `state.visualEvidence.required` is true (a passing criterion then has to name a screenshot that is actually on disk). Exit 1 means the "ok" is not accepted: name the criterion that is missing evidence and wait for the next reply. Exit 0 → `phase-tracker.sh update 5 completed` + `phase-tracker.sh meta 5 Result "local test passed (user)"`, recreate the worktree, continue to Phase 6. Full contract: `$HOME/.claude/multi-agent-refs/phases/phase-5-test.md` step 5, whose "UI flow video, when Phase 3 produced none" block applies here too: invoked standalone, this command is the only phase that ran, so if `visualEvidence.required` is set and `visualEvidence.video.file` is empty, the recording has to happen here or nowhere.
-   - **Fix needed** → `phase-tracker.sh now 5 "applying fix: <summary>"`, recreate the worktree, apply the fix
+     then run `node $HOME/.claude/scripts/evidence-gate.mjs --claim manual --status passed --evidence "$WORKTREE/.pipeline/manual-test.json"`, adding `--require-screenshot` when `state.visualEvidence.required` is true (a passing criterion then has to name a screenshot that is actually on disk). Exit 1 means the "ok" is not accepted: name the criterion that is missing evidence and wait for the next reply. Exit 0 → `phase-tracker.sh update 3 completed` + `phase-tracker.sh meta 3 Result "local test passed (user)"`, recreate the worktree, continue to Phase 4. Full contract: `$HOME/.claude/multi-agent-refs/phases/phase-3-review.md` step 5, whose "UI flow video, when Phase 2 produced none" block applies here too: invoked standalone, this command is the only phase that ran, so if `visualEvidence.required` is set and `visualEvidence.video.file` is empty, the recording has to happen here or nowhere.
+   - **Fix needed** → `phase-tracker.sh now 3 "applying fix: <summary>"`, recreate the worktree, apply the fix

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

@@ -0,0 +1,69 @@
+---
+description: "Turn the top model rung on or off and keep the cost ledger's pricing in step with it. Use when asked to enable or disable Fable, or which model the pipeline dispatches."
+description-tr: "Üst model basamağını açıp kapatır ve maliyet defterinin fiyatlamasını onunla birlikte taşır. Fable'ı aç/kapat sorulduğunda ya da pipeline hangi modeli çağırıyor sorulduğunda kullanılır."
+argument-hint: "[on | off]  -  no argument reports the current state"
+---
+
+# multi-agent model  -  which rung the pipeline dispatches on
+
+The ladder is `fable -> opus -> sonnet -> haiku` and it does not change here.
+What changes is whether the top rung is in play at all, which is
+`prefs.global.modelFallback.fableEnabled` and ships `false`.
+
+```bash
+bash "$HOME/.claude/lib/model-rung.sh" ${ARGUMENTS}
+```
+
+## Why this command exists
+
+The switch existed before the command did. It could only be flipped by editing
+preferences by hand, and `model-fallback.md` said so in a line most people never
+reached. That is a knob with no handle.
+
+It also never travelled alone. `prefs.global.costBudget.pricingModel` defaults to
+`fable` so the estimate stays an upper bound; with the rung off, that default
+prices every call above what it can cost, trips the budget ceiling early, and
+triggers a downgrade nobody needed. The documentation asked the user to set both.
+This command sets both, together:
+
+| `fableEnabled` | `costBudget.pricingModel` |
+|---|---|
+| `true` | `fable` |
+| `false` | `opus` |
+
+Flipping one without the other is the defect this closes, so the pair moves as
+one write or not at all.
+
+## What it reports with no argument
+
+The current rung, the pricing model, and **what the switch means on this host** -
+because it does not mean the same thing on all three:
+
+| Host | What `off` does | Why |
+|---|---|---|
+| Claude Code | every `preferredModel: fable` persona (architects, reviewer 1, triage) starts on `opus` | the only host where the rung is Fable 5 |
+| Copilot CLI | nothing | Fable 5 is not offered there; its personas never sat on this rung |
+| Codex CLI | nothing, deliberately | the `fable` rung there means `gpt-5.6 @ xhigh`, a different model on a different account - switching it from a knob named after an Anthropic model would surprise a Codex user |
+
+So on two of the three hosts this command is a **status report**, not a switch,
+and it says which one it is rather than claiming a change it did not make.
+
+## The consequence it prints when turning the rung off
+
+Phase 3's reviewer panel collapses from three models to two. Reviewer 1 lands on
+`opus`, which Reviewer 2 already holds, and dispatching one model twice is not
+cross-model review. `consensus.reviewerCount` records `2`, and the `unverified`
+verdict rule matters more rather than less - two Anthropic models agreeing on a
+judgment call was already weak evidence and there is now one fewer of them.
+Triage also runs on `opus`, making it the same model as Reviewer 1; the Phase 3
+Step 3 anonymisation requirement covers that case and is not optional here.
+
+This is printed at the moment of the change, not left in a doc.
+
+## Related
+
+- `/multi-agent:route-on` - policy-driven rung selection per persona or phase, a
+  separate feature that also ships off. This command decides whether a rung
+  EXISTS; that one decides which rung a given call picks.
+- Full fallback contract, including the three failure triggers this switch is
+  deliberately not one of: `$HOME/.claude/multi-agent-refs/features/model-fallback.md`

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

@@ -110,7 +110,7 @@ Procedure:
 
 ## Step 0c: DEV-TOOLKIT  -  current MCP practice for the companion toolkit
 
-The pipeline's hands on devices and browsers are MCP tools served by a companion repo (`multi-agent-toolkit-mcp`): Phase 5 test, `manual-test`, `design-check` and `apple-archive-compliance` all call them, and several pipeline skills declare a minimum toolkit version (see `cross-cli-contract.md`). That repo therefore has to track the MCP field, not just its own README. This step researches what current practice is and audits the toolkit against it.
+The pipeline's hands on devices and browsers are MCP tools served by a companion repo (`multi-agent-toolkit-mcp`): Phase 3 test, `manual-test`, `design-check` and `apple-archive-compliance` all call them, and several pipeline skills declare a minimum toolkit version (see `cross-cli-contract.md`). That repo therefore has to track the MCP field, not just its own README. This step researches what current practice is and audits the toolkit against it.
 
 Full procedure  -  resolution (configuration first, never a hardcoded path; skip when nothing resolves or `enabled` is false), the 5 research axes, the audit command block, and the band-E output table + rules  -  lives in `$HOME/.claude/multi-agent-refs/refactor/toolkit-research.md`. Read it before running this step.
 
@@ -145,8 +145,8 @@ 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) |
+| 1 | 4:reviewer-json-invalid | 12 | 3 | 4 | 14.x-15.x | reviewer prompt lets prose leak | tighten schema instruction in phase-3-review.md | Yes (P0) |
+| 2 | phase-3-failed | 5 | 2 | 3 | 15.0.x | build step misses a stack toolchain | add preflight in phase-2-dev.md | Yes (P1) |
 ```
 
 Rules for this band:

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

@@ -19,7 +19,7 @@ Resume a paused or failed task from the last successful phase.
 2. **Read + validate state**  -  parse `agent-state.json`:
    - Validate first: `node $HOME/.claude/scripts/validate-state.mjs <state-file>` (resume-safety check, tolerant of legacy shapes). On non-zero exit, do NOT guess a phase  -  surface the errors and stop with `ERR: agent-state.json is unsafe to resume; inspect it or 'kill #N' and restart.`
    - Confirm the worktree (`worktreePath` / `projects[].worktreePath`) exists and is usable; if missing or locked, run the Phase 0 "Worktree stale-lock heal" before continuing.
-- **Unless `state.worktreeRemovedAt` is set.** Then the worktree was removed on purpose by Phase 6 once the PR opened, the branch is still local, and the artefacts live under `state.artifactsPath`. Do NOT heal or recreate it: read state from `artifactsPath`, and if the remaining work needs a checkout (a Phase 7 pause needs none), ask before moving the user's HEAD  -  they may be mid-work on another branch, which is exactly why the removal did not check the branch out.
+- **Unless `state.worktreeRemovedAt` is set.** Then the worktree was removed on purpose by Phase 4 once the PR opened, the branch is still local, and the artefacts live under `state.artifactsPath`. Do NOT heal or recreate it: read state from `artifactsPath`, and if the remaining work needs a checkout (a Phase 5 pause needs none), ask before moving the user's HEAD  -  they may be mid-work on another branch, which is exactly why the removal did not check the branch out.
    - `currentPhase`  -  last completed phase
    - `status`  -  `paused` | `failed` | `in_progress`
    - `haltReason`  -  if set, show it so the user knows why the run stopped; clear it on successful re-entry
@@ -30,7 +30,7 @@ Resume a paused or failed task from the last successful phase.
    - **Handoff first (v10.8.0)**: read the LATEST `## Handoff` block in `agent-log.md`  -  it carries done/remaining/decisions/open-findings and the exact re-entry point (phase + subStep). When present, it is the primary context source; cross-check its `Next:` line against `state.currentPhase` and trust state on mismatch (state is the machine truth, handoff is the narrative).
    - Fall back to per-phase findings for logs written before v10.8 (no handoff blocks):
      - Phase 1 analysis → use it from Phase 2+
-     - Phase 2 plan → use it from Phase 3+
+     - Phase 1 plan → use it from Phase 2+
      - Phase 3 code → already in the worktree
    - Recent `git log --oneline -10` in the worktree grounds what was actually committed vs. claimed.
 
@@ -42,13 +42,13 @@ Resume a paused or failed task from the last successful phase.
    run re-enters THAT step rather than the next phase. `currentPhase + 1` is the fallback,
    not the rule - a run that stopped mid-phase to ask a human has `currentPhase` pointing at
    the phase it is still inside, so resuming past it skips the question permanently. That
-   was already true of Phase 7's channels pause, which documented itself as resumable
+   was already true of Phase 5's channels pause, which documented itself as resumable
    through this field while this file never mentioned it.
 
    | `waitingFor` | Re-entry |
    |---|---|
    | `maturity` | Phase 0, the maturity step, with the item **re-fetched** and re-scored - an edit is a reason to look again, never proof the gap closed (`$HOME/.claude/multi-agent-refs/features/maturity-followup.md`) |
-   | `user-channels-choice` | Phase 7, the channels multi-select, with the stored `channelsInput` |
+   | `user-channels-choice` | Phase 5, the channels multi-select, with the stored `channelsInput` |
    | absent | `currentPhase + 1`, as before (same pipeline as the main multi-agent command) |
 
    Clear `waitingFor` in the same write that records the answer, the moment the step is