workflow-lite-plan

計画パイプライン：調査 → 明確化 → 計画 → 確認 → workflow-lite-execute への引き継ぎ。 調査結果、構造化された計画（plan.json）、独立したタスクファイル（.task/TASK-*.json）を生成し、実装のために workflow-lite-execute へ引き継ぎます。

1. コンテキストの分離

重要: analyze-with-file または brainstorm-with-file から呼び出された場合、前のセッションは完了済みであり、そのすべてのフェーズの指示も終了済みです。それらを参照してはなりません。このドキュメントで定義されている LP-Phase 1-5 のみを実行してください。フェーズ番号は、以前のワークフローとは独立しています。

2. 入力

<task-description>         Task description or path to .md file (required)

フラグ	説明
-y, --yes	自動モード：確認を省略し、計画を自動確定し、実行方法を自動選択し、レビューを省略します（計画から実行までのワークフロー全体）
--force-explore	タスクに事前分析がある場合でも、コード調査を強制します

注記：ワークフローの設定（autoYes、forceExplore）はスキルの開始時に初期化する必要があります。呼び出し元から指定されていない場合、スキルはユーザーにワークフローモードの選択を求めます。

3. 出力アーティファクト

アーティファクト	説明
exploration-{angle}.json	角度ごとの調査結果（複雑さに応じて1～4ファイル）
explorations-manifest.json	すべての調査ファイルのインデックス
planning-context.md	根拠となるパスと統合された理解
plan.json	task_ids[] を含む計画の概要（plan-overview-base-schema.json）
.task/TASK-*.json	独立したタスクファイル（タスクごとに1つ）

出力ディレクトリ：.workflow/.lite-plan/{task-slug}-{YYYY-MM-DD}/

エージェントの使用：すべての複雑さに対して cli-lite-planning-agent

スキーマ参照：~/.ccw/workflows/cli-templates/schemas/plan-overview-base-schema.json

4. フェーズの概要

フェーズ	主なアクション	出力
LP-0	workflowPreferences を初期化	autoYes、forceExplore
LP-1	複雑さを評価 → cli-explore-agents を並列実行（1～4）	exploration-*.json + manifest
LP-2	clarification_needs を集約・重複排除 → AskUserQuestion を複数ラウンド実行	clarificationContext（メモリ内）
LP-3	cli-lite-planning-agent	plan.json + .task/TASK-*.json
LP-4	計画を表示 → AskUserQuestion（確認 + 実行 + レビュー）	userSelection
LP-5	executionContext を構築 → Skill("workflow-lite-execute")	引き継ぎ（Mode 1）

5. LP-Phase 0：ワークフロー設定の初期化

if (typeof workflowPreferences === 'undefined' || workflowPreferences === null) {
  workflowPreferences = {
    autoYes: false,      // false: show LP-Phase 2/4 prompts | true (-y): skip all prompts
    forceExplore: false
  }
}

6. LP-Phase 1：複数の観点によるインテリジェントな調査

セッション設定（必須）：

const getUtc8ISOString = () => new Date(Date.now() + 8 * 60 * 60 * 1000).toISOString()
const priorHeader = task_description.match(/^## Prior (?:Analysis|Brainstorm) \((.+?)\)/m)
const taskSlug = (priorHeader ? priorHeader[1] : task_description).toLowerCase().replace(/[^a-z0-9]+/g, '-').substring(0, 40).replace(/^-+|-+$/g, '')
const dateStr = getUtc8ISOString().substring(0, 10)
const sessionId = `${taskSlug}-${dateStr}`
const sessionFolder = `.workflow/.lite-plan/${sessionId}`
bash(`mkdir -p ${sessionFolder} && test -d ${sessionFolder} && echo "SUCCESS: ${sessionFolder}" || echo "FAILED: ${sessionFolder}"`)

TodoWrite テンプレート（初期状態 — 以降のフェーズでステータスを順次更新）：

// Pattern: set phases[0..N-1].status="completed", phases[N].status="in_progress"
// Only full block shown here; subsequent updates follow same structure with status changes
TodoWrite({ todos: [
  { content: `LP-Phase 1: Exploration [${complexity}] ${selectedAngles.length} angles`, status: "in_progress", activeForm: `Exploring: ${selectedAngles.join(', ')}` },
  { content: "LP-Phase 2: Clarification", status: "pending" },
  { content: "LP-Phase 3: Planning [cli-lite-planning-agent]", status: "pending" },
  { content: "LP-Phase 4: Confirmation", status: "pending" },
  { content: "LP-Phase 5: Execution", status: "pending" }
]})

調査の判断ロジック：

const hasPriorAnalysis = /##\s*Prior Analysis/i.test(task_description)
const hasHandoffSpec = /```json:handoff-spec/i.test(task_description)

// Parse structured handoff from analyze-with-file or brainstorm-with-file (if present)
let handoffSpec = null
if (hasHandoffSpec) {
  const specMatch = task_description.match(/```json:handoff-spec\s*\n([\s\S]*?)\n```/)
  if (specMatch) {
    handoffSpec = JSON.parse(specMatch[1])
    // handoffSpec contains: { source, session_id, session_folder, summary,
    //   implementation_scope[], code_anchors[], key_files[], key_findings[], decision_context[],
    //   exploration_artifacts: { exploration_codebase, explorations, perspectives, research, deep_dives[] } }
    // implementation_scope[]: { objective, rationale, priority, target_files[], acceptance_criteria[], change_summary }
    console.log(`[Handoff] From ${handoffSpec.source} session ${handoffSpec.session_id}`)
    console.log(`[Handoff] ${handoffSpec.implementation_scope.length} scoped items with acceptance criteria`)

    // Enrich task_description with handoff context for downstream planning agent
    // These fields were previously produced but unused — now injected into planning context
    if (handoffSpec.summary) {
      task_description += `\n\n## Analysis Summary\n${handoffSpec.summary}`
    }
    if (handoffSpec.key_findings?.length > 0) {
      task_description += `\n\n## Key Findings\n${handoffSpec.key_findings.map((f, i) =>
        `${i+1}. ${f.point || f} (${f.confidence || 'medium'})`).join('\n')}`
    }
    if (handoffSpec.decision_context?.length > 0) {
      task_description += `\n\n## Decision Context\n${handoffSpec.decision_context.map(d =>
        `- **${d.decision || d}**: ${d.reason || ''}`).join('\n')}`
    }
    if (handoffSpec.code_anchors?.length > 0) {
      task_description += `\n\n## Code Anchors\n${handoffSpec.code_anchors.slice(0, 10).map(a =>
        `- \`${a.file}:${a.lines}\`: ${a.significance}`).join('\n')}`
    }
  }
}

// Brainstorm handoff has no code_anchors/key_files — needs exploration for implementation context
const isBrainstormSource = handoffSpec?.source === 'brainstorm-with-file'
const isAnalysisSource = handoffSpec?.source === 'analyze-with-file'

needsExploration = workflowPreferences.forceExplore ? true
  : isBrainstormSource ? true  // brainstorm explore is lightweight, lite-plan needs deeper exploration
  : (hasPriorAnalysis || isAnalysisSource) ? false
  : (task.mentions_specific_files ||
     task.requires_codebase_context ||
     task.needs_architecture_understanding ||
     task.modifies_existing_code)

if (!needsExploration) {
  // Bridge: Build manifest from analyze session's exploration artifacts
  if (isAnalysisSource && handoffSpec?.exploration_artifacts) {
    const artifacts = handoffSpec.exploration_artifacts
    const explorationEntries = []
    let idx = 1
    const artifactMapping = [
      { key: 'exploration_codebase', angle: 'codebase-discovery' },
      { key: 'explorations', angle: 'analysis-findings' },
      { key: 'perspectives', angle: 'multi-perspective' },
      { key: 'research', angle: 'external-research' }
    ]
    artifactMapping.forEach(({ key, angle }) => {
      if (artifacts[key] && file_exists(artifacts[key])) {
        explorationEntries.push({
          angle, file: artifacts[key].split('/').pop(),
          path: artifacts[key], source_schema: 'analyze', index: idx++
        })
      }
    })
    if (artifacts.deep_dives?.length > 0) {
      artifacts.deep_dives.forEach(divePath => {
        if (file_exists(divePath)) {
          const name = divePath.match(/explorations\/(.+)\.json$/)?.[1] || `deep-dive-${idx}`
          explorationEntries.push({
            angle: name, file: `${name}.json`,
            path: divePath, source_schema: 'analyze', index: idx++
          })
        }
      })
    }
    if (explorationEntries.length > 0) {
      Write(`${sessionFolder}/explorations-manifest.json`, JSON.stringify({
        session_id: sessionId, task_description, timestamp: getUtc8ISOString(),
        complexity, exploration_count: explorationEntries.length,
        source: 'analyze-with-file', source_session: handoffSpec.session_id,
        explorations: explorationEntries
      }, null, 2))
      console.log(`[Analyze Bridge] ${explorationEntries.length} artifacts from ${handoffSpec.session_id}`)
    }
  }
  // If no manifest built; LP-Phase 3 loads with safe fallback
  proceed_to_next_phase()
}

コンテキストの保護：ファイルの読み込みが 50k 文字以上の場合は needsExploration=true を強制します（cli-explore-agent に委任）

複雑さの評価：

const complexity = analyzeTaskComplexity(task_description)
// 'Low': single file, single function, zero cross-module impact (fix typo, rename var, adjust constant)
// 'Medium': multiple files OR integration point OR new pattern (add endpoint, implement feature, refactor)
// 'High': cross-module, architectural, systemic (new subsystem, migration, security overhaul)
// Default bias: uncertain between Low/Medium → choose Medium

const ANGLE_PRESETS = {
  architecture: ['architecture', 'dependencies', 'modularity', 'integration-points'],
  security: ['security', 'auth-patterns', 'dataflow', 'validation'],
  performance: ['performance', 'bottlenecks', 'caching', 'data-access'],
  bugfix: ['error-handling', 'dataflow', 'state-management', 'edge-cases'],
  feature: ['patterns', 'integration-points', 'testing', 'dependencies']
}

function selectAngles(taskDescription, count) {
  const text = taskDescription.toLowerCase()
  let preset = 'feature'
  if (/refactor|architect|restructure|modular/.test(text)) preset = 'architecture'
  else if (/security|auth|permission|access/.test(text)) preset = 'security'
  else if (/performance|slow|optimi|cache/.test(text)) preset = 'performance'
  else if (/fix|bug|error|issue|broken/.test(text)) preset = 'bugfix'
  return ANGLE_PRESETS[preset].slice(0, count)
}

const selectedAngles = selectAngles(task_description, complexity === 'High' ? 4 : (complexity === 'Medium' ? 3 : 1))

console.log(`Exploration Plan: ${complexity} | ${selectedAngles.join(', ')} | cli-lite-planning-agent`)

並列調査の開始：

重要：run_in_background: true を使用してはなりません — 計画の前に調査結果が必須です。

const explorationTasks = selectedAngles.map((angle, index) =>
  Task(
    subagent_type="cli-explore-agent",
    run_in_background=false,
    description=`Explore: ${angle}`,
    prompt=`
## Task Objective
Execute **${angle}** exploration for task planning context.

## Output Location
**Session Folder**: ${sessionFolder}
**Output File**: ${sessionFolder}/exploration-${angle}.json

## Assigned Context
- **Exploration Angle**: ${angle}
- **Task Description**: ${task_description}
- **Exploration Index**: ${index + 1} of ${selectedAngles.length}

## Exploration Strategy (${angle} focus)

**Step 1: Structural Scan** (Bash)
- get_modules_by_depth.sh → identify modules related to ${angle}
- find/rg → locate files relevant to ${angle} aspect
- Analyze imports/dependencies from ${angle} perspective

**Step 2: Semantic Analysis** (Gemini CLI)
- How does existing code handle ${angle} concerns?
- What patterns are used for ${angle}?
- Where would new code integrate from ${angle} viewpoint?

**Step 3: Write Output**
- Consolidate ${angle} findings into JSON
- Identify ${angle}-specific clarification needs

## Expected Output
**Schema**: explore-json-schema.json (auto-loaded by agent)
- All fields scoped to ${angle} perspective
- Ensure rationale is specific and >10 chars (not generic)
- Include file:line locations in integration_points
- _metadata.exploration_angle: "${angle}"

## Success Criteria
- [ ] get_modules_by_depth.sh executed
- [ ] At least 3 relevant files with specific rationale (>10 chars) + role classification
- [ ] Patterns are actionable (code examples, not generic advice)
- [ ] Integration points include file:line locations
- [ ] Constraints are project-specific to ${angle}
- [ ] JSON follows schema; clarification_needs includes options + recommended
- [ ] Files with relevance >= 0.7 have key_code array + topic_relation

## Execution
**Write**: \`${sessionFolder}/exploration-${angle}.json\`
**Return**: 2-3 sentence summary of ${angle} findings
`
  )
)
// Execute all exploration tasks in parallel

自動検出とマニフェストの構築：

const explorationFiles = bash(`find ${sessionFolder} -name "exploration-*.json" -type f`)
  .split('\n').filter(f => f.trim())

const explorationManifest = {
  session_id: sessionId,
  task_description: task_description,
  timestamp: getUtc8ISOString(),
  complexity: complexity,
  exploration_count: explorationFiles.length,
  explorations: explorationFiles.map(file => {
    const data = JSON.parse(Read(file))
    return {
      angle: data._metadata.exploration_angle,
      file: path.basename(file),
      path: file,
      index: data._metadata.exploration_index
    }
  })
}

Write(`${sessionFolder}/explorations-manifest.json`, JSON.stringify(explorationManifest, null, 2))
console.log(`Exploration complete: ${explorationManifest.explorations.map(e => e.angle).join(', ')}`)

// TodoWrite：Phase 1 → completed、Phase 2 → in_progress

出力：exploration-{angle}.json（1～4ファイル）+ explorations-manifest.json

7. LP-Phase 2：明確化（任意、複数ラウンド）

省略条件：調査がない場合、またはすべての調査で clarification_needs が空の場合

重要：AskUserQuestion で1回に質問できるのは最大4つです。すべての明確化事項を確認し終えるまで、複数ラウンドを必ず実行してください。

const manifest = file_exists(`${sessionFolder}/explorations-manifest.json`)
  ? JSON.parse(Read(`${sessionFolder}/explorations-manifest.json`))
  : { exploration_count: 0, explorations: [] }
const explorations = manifest.explorations.map(exp => ({
  angle: exp.angle,
  data: JSON.parse(Read(exp.path))
}))

// Aggregate from all explorations
const allClarifications = []
explorations.forEach(exp => {
  if (exp.data.clarification_needs?.length > 0) {
    exp.data.clarification_needs.forEach(need => {
      allClarifications.push({ ...need, source_angle: exp.angle })
    })
  }
})

// Intelligent dedup: merge similar intent across angles, combine options
const dedupedClarifications = intelligentMerge(allClarifications)

if (workflowPreferences.autoYes) {
  console.log(`[Auto] Skipping ${dedupedClarifications.length} clarification questions`)
} else if (dedupedClarifications.length > 0) {
  const BATCH_SIZE = 4
  const totalRounds = Math.ceil(dedupedClarifications.length / BATCH_SIZE)

  for (let i = 0; i < dedupedClarifications.length; i += BATCH_SIZE) {
    const batch = dedupedClarifications.slice(i, i + BATCH_SIZE)
    const currentRound = Math.floor(i / BATCH_SIZE) + 1
    console.log(`### Clarification Round ${currentRound}/${totalRounds}`)

    AskUserQuestion({
      questions: batch.map(need => ({
        question: `[${need.source_angle}] ${need.question}\n\nContext: ${need.context}`,
        header: need.source_angle.substring(0, 12),
        multiSelect: false,
        options: need.options.map((opt, index) => ({
          label: need.recommended === index ? `${opt} ★` : opt,
          description: need.recommended === index ? `Recommended` : `Use ${opt}`
        }))
      }))
    })
    // Store batch responses in clarificationContext before next round
  }
}

出力：clarificationContext（メモリ内）

8. LP-Phase 3：計画

重要：LP-Phase 3 は計画のみを行います — コードを実行してはなりません。すべての実行は LP-Phase 5 で workflow-lite-execute を通じて行われます。

実行担当の割り当て（計画の生成後）：

// Priority: 1. User explicit ("用 gemini 分析..." → gemini) | 2. Default → agent
const executorAssignments = {}  // { taskId: { executor: 'gemini'|'codex'|'agent', reason } }
const taskFiles = Glob(`${sessionFolder}/.task/TASK-*.json`)
taskFiles.forEach(taskPath => {
  const task = JSON.parse(Read(taskPath))
  executorAssignments[task.id] = { executor: '...', reason: '...' }
})

cli-lite-planning-agent の呼び出し：

Task(
  subagent_type="cli-lite-planning-agent",
  run_in_background=false,
  description="Generate detailed implementation plan",
  prompt=`
Generate implementation plan and write plan.json.

## Output Location
**Session Folder**: ${sessionFolder}
**Output Files**:
- ${sessionFolder}/planning-context.md (evidence + understanding)
- ${sessionFolder}/plan.json (plan overview — NO embedded tasks[])
- ${sessionFolder}/.task/TASK-*.json (independent task files, one per task)

## Project Context (MANDATORY)
Execute: ccw spec load --category planning
**CRITICAL**: All generated tasks MUST comply with constraints in specs/*.md

## Task Description
${task_description}

## Multi-Angle Exploration Context

${manifest.explorations.length > 0
  ? manifest.explorations.map(exp => `### Exploration: ${exp.angle} (${exp.file})
Path: ${exp.path}
Read this file for detailed ${exp.angle} analysis.`).join('\n\n') + `

Total: ${manifest.exploration_count} | Angles: ${manifest.explorations.map(e => e.angle).join(', ')}
Manifest: ${sessionFolder}/explorations-manifest.json`
  : `No exploration files. Task Description contains "## Prior Analysis" — use as primary planning context.`}

## Structured Handoff Spec (from ${handoffSpec?.source || 'upstream workflow'})
${handoffSpec ? `
**Source**: ${handoffSpec.source} session ${handoffSpec.session_id}
**CRITICAL**: Use implementation_scope as PRIMARY input for task generation.
${isBrainstormSource ? '**NOTE**: Brainstorm source — code_anchors/key_files are empty. Use exploration results as primary file context.' : ''}
Each scope item maps to one or more tasks. Acceptance criteria become convergence.criteria.

${JSON.stringify(handoffSpec.implementation_scope, null, 2)}

**Code Anchors** (implementation targets):
${JSON.stringify(handoffSpec.code_anchors?.slice(0, 8), null, 2)}

**Key Findings** (context):
${JSON.stringify(handoffSpec.key_findings?.slice(0, 5), null, 2)}

**Task Generation Rules when handoffSpec present**:
1. Each implementation_scope item → 1 task (group only if tightly coupled)
2. scope.acceptance_criteria[] → task.convergence.criteria[]
3. scope.target_files[] → task.files[] with change from scope.change_summary
4. scope.objective → task.title, scope.rationale → task.description context
5. scope.priority → task ordering (high first)
` : 'No structured handoff spec — use task description and explorations as input.'}

## User Clarifications
${JSON.stringify(clarificationContext) || "None"}

## Complexity Level
${complexity}

## Requirements
- _metadata.exploration_angles: ${JSON.stringify(manifest.explorations.map(e => e.angle))}
- Two-layer output: plan.json (task_ids[], NO tasks[]) + .task/TASK-*.json
- Field names: files[].change (not modification_points), convergence.criteria (not acceptance)

## Task Grouping Rules
1. **Group by feature**: All changes for one feature = one task (even if 3-5 files)
2. **Group by context**: Related functional changes can be grouped together
3. **Minimize agent count**: Group simple unrelated tasks to reduce overhead
4. **Avoid file-per-task**: Do NOT create separate tasks for each file
5. **Substantial tasks**: Each task = 15-60 minutes of work
6. **True dependencies only**: depends_on only when Task B needs Task A's output
7. **Prefer parallel**: Most tasks should be independent

## Execution
1. ccw spec load → 2. Read ALL exploration files → 3. Synthesize + generate
4. Write: planning-context.md, .task/TASK-*.json, plan.json (task_ids[], NO tasks[])
5. Return brief completion summary
`
)

出力：${sessionFolder}/plan.json

// TodoWrite：Phase 3 → completed、Phase 4 → in_progress

## 9. LP-Phase 4: タスクの確認と実行方法の選択

表示プラン：

const plan = JSON.parse(Read(`${sessionFolder}/plan.json`))
const tasks = (plan.task_ids || []).map(id => JSON.parse(Read(`${sessionFolder}/.task/${id}.json`)))

console.log(`
## Implementation Plan
**Summary**: ${plan.summary}
**Approach**: ${plan.approach}
**Tasks** (${tasks.length}):
${tasks.map((t, i) => `${i+1}. ${t.title} (${t.scope || t.files?.[0]?.path || ''})`).join('\n')}
**Complexity**: ${plan.complexity} | **Time**: ${plan.estimated_time} | **Recommended**: ${plan.recommended_execution}
`)

確認の収集：

let userSelection

if (workflowPreferences.autoYes) {
  console.log(`[Auto] Allow & Execute | Auto | Skip + Skip`)
  userSelection = { confirmation: "Allow", execution_method: "Auto", code_review_tool: "Skip", convergence_review_tool: "Skip" }
} else {
  // "Other" in Execution allows specifying CLI tools from ~/.claude/cli-tools.json
  userSelection = AskUserQuestion({
    questions: [
      {
        question: `Confirm plan and authorize execution? (${tasks.length} tasks, ${plan.complexity})`,
        header: "Confirm",
        multiSelect: false,
        options: [
          { label: "Allow & Execute", description: "Approve plan and begin execution immediately (no further prompts)" },
          { label: "Modify", description: "Adjust before execution" },
          { label: "Cancel", description: "Abort workflow" }
        ]
      },
      {
        question: "Execution method:",
        header: "Execution",
        multiSelect: false,
        options: [
          { label: "Agent", description: "@code-developer agent" },
          { label: "Codex", description: "codex CLI tool" },
          { label: "Auto", description: `Auto: ${plan.complexity === 'Low' ? 'Agent' : 'Codex'}` }
        ]
      },
      {
        question: "Code review after execution? (runs in workflow-lite-execute)",
        header: "Code Review",
        multiSelect: false,
        options: [
          { label: "Gemini Review", description: "Gemini CLI: git diff quality review" },
          { label: "Codex Review", description: "Codex CLI: prompt-based code quality review (--mode analysis)" },
          { label: "Agent Review", description: "@code-reviewer agent" },
          { label: "Skip", description: "No code review" }
        ]
      },
      {
        question: "Convergence review in workflow-lite-test-review phase?",
        header: "Convergence Review",
        multiSelect: false,
        options: [
          { label: "Agent", description: "Agent: verify convergence criteria against implementation" },
          { label: "Gemini", description: "Gemini CLI: convergence verification" },
          { label: "Codex", description: "Codex CLI: convergence verification" },
          { label: "Skip", description: "Skip convergence review, run tests only" }
        ]
      }
    ]
  })
}

// TodoWrite: Phase 4 → completed [${userSelection.execution_method} | CR:${userSelection.code_review_tool} | CVR:${userSelection.convergence_review_tool}], Phase 5 → in_progress

10. LP-Phase 5: 実行への引き継ぎ

重要：lite-plan はコードを直接実行しません。すべての実行は workflow-lite-execute を通じて行います。

executionContext の構築：

const manifest = file_exists(`${sessionFolder}/explorations-manifest.json`)
  ? JSON.parse(Read(`${sessionFolder}/explorations-manifest.json`))
  : { exploration_count: 0, explorations: [] }
const explorations = {}
manifest.explorations.forEach(exp => {
  if (file_exists(exp.path)) explorations[exp.angle] = JSON.parse(Read(exp.path))
})

const plan = JSON.parse(Read(`${sessionFolder}/plan.json`))

executionContext = {
  planObject: plan,
  taskFiles: (plan.task_ids || []).map(id => ({ id, path: `${sessionFolder}/.task/${id}.json` })),
  explorationsContext: explorations,
  explorationAngles: manifest.explorations.map(e => e.angle),
  explorationManifest: manifest,
  clarificationContext: clarificationContext || null,
  executionMethod: userSelection.execution_method,
  codeReviewTool: userSelection.code_review_tool,
  convergenceReviewTool: userSelection.convergence_review_tool,
  originalUserInput: task_description,
  executorAssignments: executorAssignments,  // { taskId: { executor, reason } } — overrides executionMethod
  session: {
    id: sessionId,
    folder: sessionFolder,
    artifacts: {
      explorations: manifest.explorations.map(exp => ({ angle: exp.angle, path: exp.path })),
      explorations_manifest: `${sessionFolder}/explorations-manifest.json`,
      plan: `${sessionFolder}/plan.json`,
      task_dir: `${sessionFolder}/.task`
    }
  }
}

引き継ぎ：

if (!workflowPreferences.autoYes) {
  console.log(`Handing off to execution engine. No further prompts.`)
}

// TodoWrite: Phase 5 → completed, add LE-Phase 1 → in_progress
const taskCount = (plan.task_ids || []).length
TodoWrite({ todos: [
  { content: "LP-Phase 1: Exploration", status: "completed" },
  { content: "LP-Phase 2: Clarification", status: "completed" },
  { content: "LP-Phase 3: Planning", status: "completed" },
  { content: `LP-Phase 4: Confirmed [${userSelection.execution_method} | CR:${userSelection.code_review_tool} | CVR:${userSelection.convergence_review_tool}]`, status: "completed" },
  { content: `LP-Phase 5: Handoff → workflow-lite-execute`, status: "completed" },
  { content: `LE-Phase 1: Task Loading [${taskCount} tasks]`, status: "in_progress", activeForm: "Loading tasks" }
]})

Skill("workflow-lite-execute")
// executionContext passed as global variable (Mode 1: In-Memory Plan)

11. セッションフォルダーの構成

.workflow/.lite-plan/{task-slug}-{YYYY-MM-DD}/
├── exploration-{angle}.json (1-4)   # Per-angle exploration
├── explorations-manifest.json        # Exploration index
├── planning-context.md               # Evidence paths + understanding
├── plan.json                         # Plan overview (task_ids[])
├── code-review.md                    # Generated by workflow-lite-execute Step 4
├── test-checklist.json               # Generated by workflow-lite-test-review
├── test-review.md                    # Generated by workflow-lite-test-review
└── .task/
    ├── TASK-001.json
    ├── TASK-002.json
    └── ...

チェーン：lite-plan → workflow-lite-execute → workflow-lite-test-review

lite-plan (LP-Phase 1-5)
  └─ Skill("workflow-lite-execute")     ← executionContext (global)
       ├─ Step 1-3: Task Execution
       ├─ Step 4: Code Review (quality/correctness/security)
       └─ Step 5: Skill("workflow-lite-test-review")  ← testReviewContext (global)
            ├─ TR-Phase 1: Detect test framework
            ├─ TR-Phase 2: Convergence verification (plan criteria)
            ├─ TR-Phase 3-4: Run tests + Auto-fix
            └─ TR-Phase 5: Report + Sync specs

12. エラー処理

エラー	解決方法
探索エージェントの失敗	探索をスキップし、タスクの説明のみで続行します
計画エージェントの失敗	複雑さを下げて再試行するか、タスクを分割するよう提案します
明確化のタイムアウト	探索結果をそのまま使用します
確認のタイムアウト	コンテキストを保存し、再開手順を表示します
変更ループが 3 回を超える	タスクを分割するか、/workflow-plan を使用するよう提案します

<auto_mode> workflowPreferences.autoYes === true の場合（計画から実行までのワークフロー全体）：

• 明確化：スキップ | 計画の確認：承認して実行 | 実行：自動 | レビュー：スキップ

自動モードでは、1 回の確認で計画から実行までのワークフロー全体を承認できます。以降のプロンプトは表示されません。 </auto_mode>

<success_criteria>

• ワークフロー設定（autoYes、forceExplore）が LP-Phase 0 で初期化されている
• 複雑さが評価され、適切な探索の観点が選択されている
• run_in_background=false で並列探索エージェントが起動されている
• 自動検出されたファイルから探索マニフェストが作成されている
• 明確化が必要な項目が集約・重複排除され、4 件ずつ提示されている
• cli-lite-planning-agent によって計画が生成されている
• 計画の出力が 2 層構造になっている：plan.json（task_ids[]）+ .task/TASK-*.json
• ユーザーの確認が収集されている（または自動モードで自動承認されている）
• すべての成果物とセッション参照を含む executionContext が完全に構築されている
• executionContext とともに Skill("workflow-lite-execute") を通じて workflow-lite-execute に引き継がれている
• 計画フェーズではコードを実行しない。すべての実行は workflow-lite-execute に委ねられている </success_criteria>