@claude-pw/framework 0.11.3 → 0.12.0

package/README.es.md

@@ -60,7 +60,7 @@ npx @claude-pw/framework --update
 1. **`/cpw-startup`** te entrevista, escanea código existente (si hay), y genera un plan con fases, pasos y docs de arquitectura. En ciclos posteriores, carga el contexto previo y agrega nuevas fases.
 2. **`/cpw-discuss`** identifica zonas grises y captura tus preferencias antes de construir (opcional, por fase)
 3. **`/cpw-next-step`** ejecuta un pipeline adaptativo por paso — luego cierra, commitea y avanza automáticamente
-4. Cuando todas las fases se completan, **`/cpw-cleanup --complete`** se ejecuta automáticamente: genera un resumen del plan, revisa docs, archiva todas las fases, resetea el estado de ejecución y deja el proyecto listo para el siguiente `/cpw-startup`
+4. Cuando todas las fases se completan, **`/cpw-cleanup`** se ejecuta automáticamente: genera un resumen del plan, revisa docs, archiva todas las fases, resetea el estado de ejecución y deja el proyecto listo para el siguiente `/cpw-startup`
 
 Cada paso pasa por:
 
@@ -138,7 +138,7 @@ Issue capturado. ¿Arreglar ahora? (sí/no)
 | `/cpw-todos` | Captura ideas para después o revisa todos pendientes |
 | `/cpw-reflect` | Revisa correcciones capturadas, convierte en learnings (`--scan-history`, `--dedupe`) |
 | `/cpw-impact` | Analiza impacto de decisiones en todo el plan |
-| `/cpw-cleanup` | Archiva fases completadas y limpia estado (`--complete` para reset completo del plan) |
+| `/cpw-cleanup` | Archiva fases completadas y limpia estado (auto-detecta reset completo cuando el plan termina) |
 | `/cpw-update` | Actualización inteligente del framework — diff, merge de conflictos, preserva customizaciones |
 
 ## Configuración

package/README.ja.md

@@ -60,7 +60,7 @@ npx @claude-pw/framework --update
 1. **`/cpw-startup`** インタビューを行い、既存コード（あれば）をスキャンし、フェーズ・ステップ・アーキテクチャドキュメントを含む計画を生成。後続サイクルでは、以前のコンテキストを読み込み、新しいフェーズを追加。
 2. **`/cpw-discuss`** グレーゾーンを特定し、ビルド前にあなたの好みを把握（任意、フェーズごと）
 3. **`/cpw-next-step`** ステップごとに適応型パイプラインを実行 — 完了後、自動的にクローズ・コミット・次へ進行
-4. 全フェーズ完了時、**`/cpw-cleanup --complete`** が自動実行：計画サマリー生成、ドキュメントレビュー、全フェーズアーカイブ、実行状態リセット、次の `/cpw-startup` に備える
+4. 全フェーズ完了時、**`/cpw-cleanup`** が自動実行：計画サマリー生成、ドキュメントレビュー、全フェーズアーカイブ、実行状態リセット、次の `/cpw-startup` に備える
 
 各ステップは以下を経由します：
 
@@ -138,7 +138,7 @@ Issue captured. Fix now? (yes/no)
 | `/cpw-todos` | アイデアの記録または保留中の TODO の確認 |
 | `/cpw-reflect` | キャプチャした修正をレビューし、学習に変換（`--scan-history`, `--dedupe`） |
 | `/cpw-impact` | 計画全体にわたる意思決定の影響分析 |
-| `/cpw-cleanup` | 完了フェーズのアーカイブと状態クリーンアップ（`--complete` で計画全体リセット） |
+| `/cpw-cleanup` | 完了フェーズのアーカイブと状態クリーンアップ（計画完了時に自動で完全リセット） |
 | `/cpw-update` | スマートフレームワーク更新 — 差分、コンフリクトマージ、カスタマイズ保持 |
 
 ## 設定

package/README.md

@@ -60,7 +60,7 @@ npx @claude-pw/framework --update
 1. **`/cpw-startup`** interviews you, scans existing code (if any), and generates a plan with phases, steps, and architecture docs. On subsequent cycles, loads prior context and appends new phases.
 2. **`/cpw-discuss`** identifies gray areas and captures your preferences before building (optional, per phase)
 3. **`/cpw-next-step`** runs an adaptive pipeline per step — then closes, commits, and advances automatically
-4. When all phases complete, **`/cpw-cleanup --complete`** runs automatically: generates a plan summary, reviews docs for drift, archives all phase files, resets execution state, and leaves the project ready for the next `/cpw-startup`
+4. When all phases complete, **`/cpw-cleanup`** runs automatically: generates a plan summary, reviews docs for drift, archives all phase files, resets execution state, and leaves the project ready for the next `/cpw-startup`
 
 Every step goes through:
 
@@ -138,7 +138,7 @@ Issue captured. Fix now? (yes/no)
 | `/cpw-todos` | Capture ideas for later or review pending todos |
 | `/cpw-reflect` | Review captured corrections, convert to learnings (`--scan-history`, `--dedupe`) |
 | `/cpw-impact` | Analyze decision impact across the entire plan |
-| `/cpw-cleanup` | Archive completed phases and clean state (`--complete` for full plan reset) |
+| `/cpw-cleanup` | Archive completed phases and clean state (auto-detects full reset when plan is done) |
 | `/cpw-update` | Smart framework update — diff, merge conflicts, preserve customizations |
 
 ## Configuration

package/README.pt-br.md

@@ -60,7 +60,7 @@ npx @claude-pw/framework --update
 1. **`/cpw-startup`** entrevista você, analisa o código existente (se houver) e gera um plano com fases, etapas e documentos de arquitetura. Em ciclos posteriores, carrega o contexto anterior e adiciona novas fases.
 2. **`/cpw-discuss`** identifica áreas cinzentas e captura suas preferências antes de construir (opcional, por fase)
 3. **`/cpw-next-step`** executa um pipeline adaptativo por etapa — então fecha, commita e avança automaticamente
-4. Quando todas as fases completam, **`/cpw-cleanup --complete`** executa automaticamente: gera resumo do plano, revisa docs, arquiva todas as fases, reseta estado de execução e deixa o projeto pronto para o próximo `/cpw-startup`
+4. Quando todas as fases completam, **`/cpw-cleanup`** executa automaticamente: gera resumo do plano, revisa docs, arquiva todas as fases, reseta estado de execução e deixa o projeto pronto para o próximo `/cpw-startup`
 
 Cada etapa passa por:
 
@@ -138,7 +138,7 @@ Issue captured. Fix now? (yes/no)
 | `/cpw-todos` | Capturar ideias para depois ou revisar todos pendentes |
 | `/cpw-reflect` | Revisar correções capturadas, converter em aprendizados (`--scan-history`, `--dedupe`) |
 | `/cpw-impact` | Analisar impacto de decisões em todo o plano |
-| `/cpw-cleanup` | Arquivar fases completadas e limpar estado (`--complete` para reset completo do plano) |
+| `/cpw-cleanup` | Arquivar fases completadas e limpar estado (auto-detecta reset completo quando o plano termina) |
 | `/cpw-update` | Atualização inteligente do framework — diff, merge de conflitos, preserva customizações |
 
 ## Configuração

package/README.zh-cn.md

@@ -60,7 +60,7 @@ npx @claude-pw/framework --update
 1. **`/cpw-startup`** 对你进行访谈，扫描现有代码（如果有），生成包含阶段、步骤和架构文档的计划。后续周期中，加载之前的上下文并追加新阶段。
 2. **`/cpw-discuss`** 识别灰色地带，在构建前捕获你的偏好（可选，按阶段）
 3. **`/cpw-next-step`** 按步骤运行自适应流水线——然后自动关闭、提交并推进
-4. 当所有阶段完成时，**`/cpw-cleanup --complete`** 自动运行：生成计划摘要、审查文档、归档所有阶段文件、重置执行状态，为下一个 `/cpw-startup` 做好准备
+4. 当所有阶段完成时，**`/cpw-cleanup`** 自动运行：生成计划摘要、审查文档、归档所有阶段文件、重置执行状态，为下一个 `/cpw-startup` 做好准备
 
 每个步骤经过：
 
@@ -138,7 +138,7 @@ UAT 演练：
 | `/cpw-todos` | 捕获想法或查看待办事项 |
 | `/cpw-reflect` | 审查捕获的修正，转化为学习成果（`--scan-history`、`--dedupe`） |
 | `/cpw-impact` | 分析决策对整个计划的影响 |
-| `/cpw-cleanup` | 归档已完成阶段并清理状态（`--complete` 用于完整计划重置） |
+| `/cpw-cleanup` | 归档已完成阶段并清理状态（计划完成时自动执行完整重置） |
 | `/cpw-update` | 智能框架更新 — 差异对比、冲突合并、保留自定义 |
 
 ## 配置

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@claude-pw/framework",
-  "version": "0.11.3",
+  "version": "0.12.0",
   "description": "Structured Project Workflow for Claude Code — adaptive pipeline, context management, quality gates",
   "bin": {
     "claude-pw": "./install.js"

package/templates/claude/commands/cpw-cleanup.md

@@ -5,123 +5,8 @@ description: "Archive completed phases and clean accumulated state"
 ## Arguments
 - No arguments: dry-run (show what would be cleaned, ask for confirmation)
 - `--execute`: skip confirmation, execute immediately
-- `--complete`: full plan completion cycle (summary, docs review, archive ALL, reset state). Auto-triggered by `/cpw-next-step` when the last phase completes. Can also be run manually.
 
----
-
-## --complete mode (plan completion cycle)
-
-If `--complete` is passed, execute the full completion cycle. This mode is designed to
-close a finished plan, archive everything, and leave the project ready for `/cpw-startup`.
-
-### 1. Plan completion summary
-Generate `.planning/plan-summary.md`:
-- Read all phase sub-plans (plans/phase-N.md for each phase in PLAN.md)
-- Read plans/decisions.md
-- For each phase, extract: name, step count, Objective line
-- From decisions.md, extract decisions made during these phases
-- Get date range from git: first plan commit and today
-
-Write `.planning/plan-summary.md`:
-```markdown
-# Plan Summary
-
-## Completed
-- **Date**: [today]
-- **Phases**: [N]
-- **Steps**: [total across all phases]
-
-## Phases
-| # | Phase | Steps | Key output |
-|---|-------|-------|------------|
-| 0 | Stack and Scaffolding | 6 | Project setup, toolchain, CI |
-| 1 | Interfaces | 5 | Module contracts, type system |
-| ... | ... | ... | ... |
-
-## Key decisions
-- Phase N: [decision summary from decisions.md]
-- ...
-
-## Key deliverables
-- [extracted from each phase's Objective]
-- ...
-```
-
-If a previous `.planning/plan-summary.md` exists (from a prior cycle), rename it
-to `.planning/plan-summary-[date].md` before writing the new one.
-
-### 2. Docs evolution review
-Review if docs/ need updating after the full plan:
-- Read `docs/architecture.md` — does it reflect what was actually built?
-  Compare with the plan phases and deliverables. If outdated, update it.
-- Read `docs/interfaces.md` — are interfaces current with the final state of `src/interfaces/`?
-  If outdated, update it.
-- If any docs were updated:
-  `make commit m="docs: update architecture and interfaces after plan completion"`
-
-This is a lightweight pass to catch drift — not a full rewrite.
-
-### 3. Archive ALL phase files
-```bash
-mkdir -p .planning/archive
-```
-For every phase in PLAN.md (regardless of `archiveCompletedPhases` config — in --complete mode, everything gets archived):
-- Move `plans/phase-N.md` to `.planning/archive/phase-N.md`
-- Move `plans/phase-N-context.md` to `.planning/archive/phase-N-context.md` (if exists)
-
-Update PLAN.md: sub-plan column → `(archived)` for all phases.
-
-### 4. Reset execution state
-Clean execution artifacts. These served the current plan cycle and are not needed for the next:
-- **Delete** `STATUS.md` (session pointer — no longer needed)
-- **Reset** `.planning/quick/log.md` to empty table header only
-- **Delete** all files in `.planning/debug/resolved/`
-- **Delete** `.planning/debug/active-session.md` (if exists)
-- **Delete** `.planning/handoff.md` (if exists)
-- **Delete** `.planning/uat.md` (if exists)
-
-Do NOT touch (project context that survives between cycles):
-- `plans/decisions.md` — cumulative project history
-- `docs/*` — project documentation (just reviewed in step 2)
-- `.planning/config.json` — workflow settings carry over
-- `.planning/plan-summary.md` — just generated in step 1
-- `.planning/learnings/queue.md` — pending corrections carry over (may still need processing)
-- `.planning/learnings/applied.md` — deduplication reference (knowledge already extracted to rules/skills)
-- `PLAN.md` — updated with (archived) markers
-- `CLAUDE.md` — project instructions
-- `.claude/skills/*` — extracted knowledge
-- `.claude/rules/*` — project rules
-- All source code, tests, Makefile, etc.
-
-### 5. Commit
-`make commit m="chore: plan complete — archived [N] phases, reset execution state"`
-
-### 6. Report
-```
-══════════════════════════════════════
-PLAN COMPLETE
-══════════════════════════════════════
-All [N] phases finished.
-Summary: .planning/plan-summary.md
-
-Archived: [N] phase files → .planning/archive/
-Cleaned: STATUS.md, quick log, debug sessions
-
-Project is ready for the next development cycle.
-Run /cpw-startup to begin.
-══════════════════════════════════════
-```
-
-STOP.
-
----
-
-## Standard mode (mid-plan cleanup)
-
-If `--complete` is NOT passed, run the standard cleanup flow below.
-This is for archiving completed phases while the plan is still in progress.
-
-### 0. Load state
+## 0. Load state and detect mode
 
 Read `.planning/config.json` -> extract `cleanupPolicy` (use defaults if missing):
 - `archiveCompletedPhases`: true
@@ -129,53 +14,97 @@ Read `.planning/config.json` -> extract `cleanupPolicy` (use defaults if missing
 - `keepResolvedDebug`: 5
 - `keepQuickLogDone`: 10
 
-Read PLAN.md -> extract phases table. Identify phases with Status = "done".
-Read STATUS.md -> identify current phase (to avoid archiving it).
+Read PLAN.md -> extract phases table.
 
-If no completed phases and no accumulated state to clean:
-```
-Nothing to clean up. All phases are current or pending.
-```
-STOP.
+**Auto-detect mode:**
+- If ALL phases have Status "done" AND no phase has Status "in progress" or "pending" → **COMPLETE mode** (plan finished)
+- Otherwise → **MID-PLAN mode** (plan still in progress)
+
+## 1. Identify what to clean
 
-### 1. Identify what to clean
+### 1.1 Phase files
 
-#### 1.1 Completed phase files
-If `archiveCompletedPhases` is true:
-For each phase with Status "done" in PLAN.md:
+**COMPLETE mode:** archive ALL phase files (every phase in PLAN.md).
+**MID-PLAN mode:** archive only phases with Status "done" that still have files in `plans/` (if `archiveCompletedPhases` is true). NEVER archive the current phase or pending phases. Read STATUS.md to identify current phase.
+
+For each phase to archive:
 - Check if `plans/phase-N.md` still exists (not already archived)
 - Check if `plans/phase-N-context.md` exists
 - Add to archive list
-- NEVER archive the current phase or pending phases
 
-#### 1.2 Quick log done entries
-Read `.planning/quick/log.md` (if exists):
-- Count entries with Status: done or dismissed
-- If count > `keepQuickLogDone`: mark oldest excess entries for removal
+### 1.2 Quick log done entries
+
+**COMPLETE mode:** mark ALL entries for removal (reset to empty table header).
+**MID-PLAN mode:** read `.planning/quick/log.md` (if exists). If done/dismissed entries > `keepQuickLogDone`: mark oldest excess for removal.
 
-#### 1.3 Resolved debug sessions
+### 1.3 Resolved debug sessions
 List `.planning/debug/resolved/` (if exists):
-- Count files
 - If count > `keepResolvedDebug`: mark oldest files for deletion (by filename date prefix)
 
-#### 1.4 Applied learnings
+### 1.4 Applied learnings
 Read `.planning/learnings/applied.md` (if exists):
 - Count entries (each entry starts with `---`)
 - If count > `keepAppliedLearnings`: mark oldest excess entries for trimming
 
-#### 1.5 Stale files
-- `.planning/handoff.md` — if it exists AND STATUS.md does NOT show a handoff in progress
-- `.planning/uat.md` — if it exists AND all phases it references are done (no active UAT)
+NEVER touch `.planning/learnings/queue.md` — pending corrections always carry over.
 
-### 2. Present cleanup plan
+### 1.5 Stale files
+- `.planning/handoff.md` — if it exists
+- `.planning/uat.md` — if it exists AND all phases it references are done
+- `.planning/debug/active-session.md` — **COMPLETE mode only** (if exists)
 
+### 1.6 COMPLETE mode extras
+Only in COMPLETE mode:
+- STATUS.md will be deleted (session pointer no longer needed)
+- Plan summary will be generated
+- Docs will be reviewed for drift
+
+## 2. Present cleanup plan
+
+**COMPLETE mode:**
+```
+══════════════════════════════════════
+PLAN COMPLETE — Cleanup
+══════════════════════════════════════
+
+GENERATE:
+  - .planning/plan-summary.md (plan history)
+
+DOCS REVIEW:
+  - docs/architecture.md (check for drift)
+  - docs/interfaces.md (check for drift)
+
+ARCHIVE (move to .planning/archive/):
+  - plans/phase-0.md (6 steps)
+  - plans/phase-1.md (4 steps)
+  - plans/phase-2.md (5 steps)
+
+TRIM:
+  - quick/log.md: reset to empty
+  - debug/resolved/: delete N old sessions (keeping last M)
+  - learnings/applied.md: trim N old entries (keeping last M)
+
+DELETE:
+  - STATUS.md
+  - .planning/handoff.md
+  - .planning/debug/active-session.md
+
+NO CHANGES:
+  - plans/decisions.md (cumulative)
+  - .planning/learnings/queue.md (pending corrections)
+  - .planning/config.json (workflow settings)
+  - docs/* (reviewed, not deleted)
+  - .claude/skills/*, .claude/rules/*
+══════════════════════════════════════
+```
+
+**MID-PLAN mode:**
 ```
 Cleanup Summary:
 
 ARCHIVE (move to .planning/archive/):
   - plans/phase-0.md (6 steps, all done)
   - plans/phase-0-context.md
-  - plans/phase-1.md (4 steps, all done)
 
 TRIM:
   - quick/log.md: remove N done entries (keeping last M)
@@ -203,9 +132,52 @@ STOP.
 If `--execute`: show the summary and proceed to step 3.
 Otherwise: ask "Proceed? (yes/no)". If no: STOP.
 
-### 3. Execute
+## 3. Execute
+
+### 3.1 COMPLETE mode: Plan summary
+Only in COMPLETE mode. Generate `.planning/plan-summary.md`:
+- Read all phase sub-plans (plans/phase-N.md for each phase in PLAN.md)
+- Read plans/decisions.md
+- For each phase, extract: name, step count, Objective line
+- From decisions.md, extract decisions made during these phases
+- Get date range from git: first plan commit and today
+
+Write `.planning/plan-summary.md`:
+```markdown
+# Plan Summary
+
+## Completed
+- **Date**: [today]
+- **Phases**: [N]
+- **Steps**: [total across all phases]
+
+## Phases
+| # | Phase | Steps | Key output |
+|---|-------|-------|------------|
+| 0 | Stack and Scaffolding | 6 | Project setup, toolchain, CI |
+| 1 | Interfaces | 5 | Module contracts, type system |
+| ... | ... | ... | ... |
+
+## Key decisions
+- Phase N: [decision summary from decisions.md]
+- ...
+
+## Key deliverables
+- [extracted from each phase's Objective]
+- ...
+```
+
+If a previous plan-summary.md exists (prior cycle), rename to `plan-summary-[date].md`.
+
+### 3.2 COMPLETE mode: Docs evolution review
+Only in COMPLETE mode. Review if docs/ need updating:
+- Read `docs/architecture.md` — does it reflect what was actually built? If outdated, update.
+- Read `docs/interfaces.md` — are interfaces current? If outdated, update.
+- If any docs were updated: `make commit m="docs: update architecture and interfaces after plan completion"`
 
-#### 3.1 Archive phase files
+Lightweight pass to catch drift — not a full rewrite.
+
+### 3.3 Archive phase files
 ```bash
 mkdir -p .planning/archive
 ```
@@ -213,7 +185,7 @@ For each phase in the archive list:
 - Move `plans/phase-N.md` to `.planning/archive/phase-N.md`
 - Move `plans/phase-N-context.md` to `.planning/archive/phase-N-context.md` (if exists)
 
-#### 3.2 Update PLAN.md
+### 3.4 Update PLAN.md
 For each archived phase, change the sub-plan column from `plans/phase-N.md` to `(archived)`:
 ```
 | 0 | Stack and Scaffolding | plans/phase-0.md | done |
@@ -223,25 +195,30 @@ becomes:
 | 0 | Stack and Scaffolding | (archived) | done |
 ```
 
-#### 3.3 Trim quick log
-Remove done/dismissed entries beyond the keep limit from `.planning/quick/log.md`.
-Keep the most recent N entries (by date). Preserve the table header.
+### 3.5 Trim quick log
+**COMPLETE mode:** reset `.planning/quick/log.md` to empty table header only.
+**MID-PLAN mode:** remove done/dismissed entries beyond the keep limit. Keep the most recent N entries (by date). Preserve the table header.
 
-#### 3.4 Delete old debug sessions
+### 3.6 Trim debug sessions
 Delete files from `.planning/debug/resolved/` beyond the keep limit.
 Delete the oldest by filename date prefix.
 
-#### 3.5 Trim applied learnings
+### 3.7 Trim applied learnings
 Remove the oldest entries from `.planning/learnings/applied.md` beyond the keep limit.
 Keep the most recent N entries. Each entry is delimited by `---`.
 
-#### 3.6 Delete stale files
-Delete identified stale files (handoff.md, uat.md).
+### 3.8 Delete stale files
+Delete identified stale files (handoff.md, uat.md, and active-session.md in COMPLETE mode).
+
+### 3.9 COMPLETE mode: Delete STATUS.md
+Only in COMPLETE mode. Delete STATUS.md (session pointer no longer needed — its absence signals a completed plan to /cpw-startup and /cpw-next-step).
 
-#### 3.7 Commit
+### 3.10 Commit
 Read `commitPlanning` from `.planning/config.json`.
 
-Build commit message based on what was actually executed:
+**COMPLETE mode:** `make commit m="chore: plan complete — archived [N] phases, reset execution state"`
+
+**MID-PLAN mode:** Build commit message based on what was actually executed:
 - If phases were archived AND state was trimmed: `"chore: archive phases N-M and trim planning state"`
 - If only phases were archived: `"chore: archive completed phases N-M"`
 - If only state was trimmed: `"chore: trim accumulated planning state"`
@@ -252,11 +229,29 @@ Git add the changes:
 - `.planning/` (only if `commitPlanning: true`)
 
 Check if there are staged changes (`git diff --cached --quiet`).
-- If there are changes: `make commit m="[built message]"`
+- If there are changes: commit
 - If there are NO changes (e.g., only .planning/ was modified and commitPlanning is false): skip commit. Report: "Only local state cleaned (.planning/ is gitignored) — no commit needed."
 
-### 4. Report
+## 4. Report
+
+**COMPLETE mode:**
+```
+══════════════════════════════════════
+PLAN COMPLETE
+══════════════════════════════════════
+All [N] phases finished.
+Summary: .planning/plan-summary.md
+
+Archived: [N] phase files → .planning/archive/
+Trimmed: quick log, [K] debug sessions, [L] learnings
+Cleaned: STATUS.md, handoff, debug active session
+
+Project is ready for the next development cycle.
+Run /cpw-startup to begin.
+══════════════════════════════════════
+```
 
+**MID-PLAN mode:**
 ```
 Cleanup complete.
 

package/templates/claude/commands/cpw-next-step.md

@@ -582,10 +582,11 @@ Read PLAN.md. Check if there is a next phase (any phase with Status "pending" or
 
 **If there is NO next phase — plan complete:**
 
-All phases are done. Delegate the full completion cycle to `/cpw-cleanup --complete`.
-This will: generate plan summary, review docs, archive all phases, reset execution state.
+All phases are done. Delegate to `/cpw-cleanup` which will auto-detect COMPLETE mode
+(all phases done) and run the full completion cycle: plan summary, docs review, archive
+all phases, trim state, reset execution artifacts.
 
-Execute `/cpw-cleanup --complete` now (invoke the command inline, do NOT ask the user to run it manually).
+Execute `/cpw-cleanup --execute` now (invoke the command inline, skip confirmation).
 
 After cleanup completes, STOP. Do NOT attempt to advance to a non-existent phase.
 

package/templates/claude/commands/cpw-startup.md

@@ -10,7 +10,7 @@ analysis report. You can stop after the scan by declining plan generation.
 
 ### Check for existing completed plan (new cycle detection)
 Detect new cycle by ANY of these signals:
-1. PLAN.md exists AND `.planning/config.json` exists AND STATUS.md does NOT exist (post-completion state — STATUS.md was deleted by /cpw-cleanup --complete)
+1. PLAN.md exists AND `.planning/config.json` exists AND STATUS.md does NOT exist (post-completion state — STATUS.md was deleted by /cpw-cleanup)
 2. PLAN.md exists AND all phases have Status "done" AND no phase has Status "in progress" or "pending" (implicit completion — cleanup may not have run)
 
 If PLAN.md exists with phases "in progress" or "pending" → NOT a new cycle. Skip to standard mode detection below.