refactor: 统一 lite 工作流产物结构，合并 exploration+understanding 为 planning-context

- 合并 exploration.md 和 understanding.md 为单一的 planning-context.md - 为所有 lite 工作流添加 Output Artifacts 表格 - 统一 agent 提示词的 Output Location 格式 - 更新 Session Folder Structure 包含 planning-context.md 涉及文件: - cli-lite-planning-agent.md: 更新产物文档和格式模板 - collaborative-plan.md: 简化为 planning-context.md + sub-plan.json - lite-plan.md: 添加产物表格和输出地址 - lite-fix.md: 添加产物表格和输出地址
2026-02-05 01:50:27 +08:00 · 2026-01-30 10:25:45 +08:00
parent 3f46a02df3
commit 64d2156319
4 changed files with 206 additions and 161 deletions
--- a/.claude/agents/cli-lite-planning-agent.md
+++ b/.claude/agents/cli-lite-planning-agent.md
@@ -1,13 +1,14 @@
 ---
 name: cli-lite-planning-agent
 description: |
-  Generic planning agent for lite-plan and lite-fix workflows. Generates structured plan JSON based on provided schema reference.
+  Generic planning agent for lite-plan, collaborative-plan, and lite-fix workflows. Generates structured plan JSON based on provided schema reference.

  Core capabilities:
  - Schema-driven output (plan-json-schema or fix-plan-json-schema)
  - Task decomposition with dependency analysis
  - CLI execution ID assignment for fork/merge strategies
  - Multi-angle context integration (explorations or diagnoses)
+  - Process documentation (planning-context.md) for collaborative workflows
 color: cyan
 ---

@@ -15,6 +16,40 @@ You are a generic planning agent that generates structured plan JSON for lite wo

 **CRITICAL**: After generating plan.json, you MUST execute internal **Plan Quality Check** (Phase 5) using CLI analysis to validate and auto-fix plan quality before returning to orchestrator. Quality dimensions: completeness, granularity, dependencies, acceptance criteria, implementation steps, constraint compliance.

+## Output Artifacts
+
+The agent produces different artifacts based on workflow context:
+
+### Standard Output (lite-plan, lite-fix)
+
+| Artifact | Description |
+|----------|-------------|
+| `plan.json` | Structured plan following plan-json-schema.json |
+
+### Extended Output (collaborative-plan sub-agents)
+
+When invoked with `process_docs: true` in input context:
+
+| Artifact | Description |
+|----------|-------------|
+| `planning-context.md` | Evidence paths + synthesized understanding (insights, decisions, approach) |
+| `sub-plan.json` | Sub-plan following plan-json-schema.json with source_agent metadata |
+
+**planning-context.md format**:
+```markdown
+# Planning Context: {focus_area}
+
+## Source Evidence
+- `exploration-{angle}.json` - {key finding}
+- `{file}:{line}` - {what this proves}
+
+## Understanding
+- Current state: {analysis}
+- Proposed approach: {strategy}
+
+## Key Decisions
+- Decision: {what} | Rationale: {why} | Evidence: {file ref}
+```

 ## Input Context

@@ -34,10 +69,39 @@ You are a generic planning agent that generates structured plan JSON for lite wo
  clarificationContext: { [question]: answer } | null,
  complexity: "Low" | "Medium" | "High",  // For lite-plan
  severity: "Low" | "Medium" | "High" | "Critical",  // For lite-fix
-  cli_config: { tool, template, timeout, fallback }
+  cli_config: { tool, template, timeout, fallback },
+
+  // Process documentation (collaborative-plan)
+  process_docs: boolean,              // If true, generate planning-context.md
+  focus_area: string,                 // Sub-requirement focus area (collaborative-plan)
+  output_folder: string               // Where to write process docs (collaborative-plan)
 }
 ```

+## Process Documentation (collaborative-plan)
+
+When `process_docs: true`, generate planning-context.md before sub-plan.json:
+
+```markdown
+# Planning Context: {focus_area}
+
+## Source Evidence
+- `exploration-{angle}.json` - {key finding from exploration}
+- `{file}:{line}` - {code evidence for decision}
+
+## Understanding
+- **Current State**: {what exists now}
+- **Problem**: {what needs to change}
+- **Approach**: {proposed solution strategy}
+
+## Key Decisions
+- Decision: {what} | Rationale: {why} | Evidence: {file:line or exploration ref}
+
+## Dependencies
+- Depends on: {other sub-requirements or none}
+- Provides for: {what this enables}
+```
+
 ## Schema-Driven Output

 **CRITICAL**: Read the schema reference first to determine output structure:
--- a/.claude/commands/workflow/collaborative-plan.md
+++ b/.claude/commands/workflow/collaborative-plan.md
@@ -29,13 +29,33 @@ When `--yes` or `-y`: Auto-approve splits, use default merge rule, skip confirma
 **CLI Tools**: cli-lite-planning-agent (internally calls ccw cli with gemini/codex/qwen)
 **Schema**: plan-json-schema.json (sub-plans & final plan share same base schema)

+## Output Artifacts
+
+### Per Sub-Agent (Phase 2)
+
+| Artifact | Description |
+|----------|-------------|
+| `planning-context.md` | Evidence paths + synthesized understanding |
+| `sub-plan.json` | Sub-plan following plan-json-schema.json |
+
+### Final Output (Phase 4)
+
+| Artifact | Description |
+|----------|-------------|
+| `requirement-analysis.json` | Requirement breakdown and sub-agent assignments |
+| `conflicts.json` | Detected conflicts between sub-plans |
+| `plan.json` | Merged plan (plan-json-schema + merge_metadata) |
+| `plan.md` | Human-readable plan summary |
+
+**Agent**: `cli-lite-planning-agent` with `process_docs: true` for sub-agents
+
 ## Overview

 Unified collaborative planning workflow that:

 1. **Analyzes** complex requirements and splits into sub-requirements
 2. **Spawns** parallel sub-agents, each responsible for one sub-requirement
-3. **Each agent** maintains process files: exploration.md → understanding.md → sub-plan.json
+3. **Each agent** maintains process files: planning-refs.md + sub-plan.json
 4. **Merges** all sub-plans into unified plan.json with conflict resolution

 ```
@@ -51,10 +71,9 @@ Unified collaborative planning workflow that:
 │  Phase 2: Parallel Sub-Agent Execution                                   │
 │     ┌──────────────┬──────────────┬──────────────┐                       │
 │     │   Agent 1    │   Agent 2    │   Agent N    │                       │
-│     ├──────────────┼──────────────┼──────────────┤                       │
-│     │ exploration  │ exploration  │ exploration  │  → exploration.md     │
-│     │ understanding│ understanding│ understanding│  → understanding.md   │
-│     │ planning     │ planning     │ planning     │  → sub-plan.json      │
+├──────────────┼──────────────┼──────────────┤                       │
+│     │ planning     │ planning     │ planning     │  → planning-context.md│
+│     │ + sub-plan   │ + sub-plan   │ + sub-plan   │  → sub-plan.json      │
 │     └──────────────┴──────────────┴──────────────┘                       │
 │                                                                          │
 │  Phase 3: Cross-Verification & Conflict Detection                        │
@@ -77,9 +96,8 @@ Unified collaborative planning workflow that:
 ├── requirement-analysis.json     # Phase 1: Requirement breakdown
 ├── agents/                       # Phase 2: Per-agent process files
 │   ├── {focus-area-1}/
-│   │   ├── exploration.md        # What was discovered
-│   │   ├── understanding.md      # Synthesized insights
-│   │   └── sub-plan.json         # Agent's plan for this focus area
+│   │   ├── planning-context.md  # Evidence + understanding
+│   │   └── sub-plan.json        # Agent's plan for this focus area
 │   ├── {focus-area-2}/
 │   │   └── ...
 │   └── {focus-area-N}/
@@ -243,129 +261,38 @@ const agentPromises = subRequirements.map((sub, index) => {
    run_in_background: false,
    description: `Plan: ${sub.focus_area}`,
    prompt: `
-## Sub-Agent Mission
+## Sub-Agent Context

-You are responsible for planning ONE sub-requirement of a larger task.
-Maintain 3 process files documenting your exploration, understanding, and plan.
+You are planning ONE sub-requirement. Generate process docs + sub-plan.

-## Your Focus Area
-
-**Index**: ${index + 1}
 **Focus Area**: ${sub.focus_area}
 **Description**: ${sub.description}
 **Key Concerns**: ${sub.key_concerns.join(', ')}
-**Suggested Tool**: ${sub.suggested_cli_tool}
+**CLI Tool**: ${sub.suggested_cli_tool}
 **Depth**: ${depth}

-## Parent Context
+## Input Context

-**Original Requirement**: ${taskDescription}
-**Session**: ${sessionId}
-**Your Folder**: ${sessionFolder}/agents/${sub.focus_area}/
-
-## Schema Reference
-
-Execute: cat ~/.claude/workflows/cli-templates/schemas/plan-json-schema.json
-
-## Execution Process (3 Stages)
-
-### Stage 1: Exploration (→ exploration.md)
-
-Use ccw cli to explore the codebase for your focus area:
-
-\`\`\`bash
-ccw cli -p "
-PURPOSE: Explore codebase for ${sub.focus_area}
-Success: Identify all relevant files, patterns, and constraints
-
-TASK:
-• Find existing code related to ${sub.focus_area}
-• Identify current architecture and patterns
-• Discover integration points and dependencies
-• Note any constraints or limitations
-
-CONTEXT: @**/*
-MODE: analysis
-" --tool ${sub.suggested_cli_tool} --mode analysis
+\`\`\`json
+{
+  "task_description": "${sub.description}",
+  "schema_path": "~/.claude/workflows/cli-templates/schemas/plan-json-schema.json",
+  "session": { "id": "${sessionId}", "folder": "${sessionFolder}" },
+  "process_docs": true,
+  "focus_area": "${sub.focus_area}",
+  "output_folder": "${sessionFolder}/agents/${sub.focus_area}",
+  "cli_config": { "tool": "${sub.suggested_cli_tool}" },
+  "parent_requirement": "${taskDescription}"
+}
 \`\`\`

-After CLI completes, write exploration.md:
-
-\`\`\`markdown
-# Exploration: ${sub.focus_area}
-
-## Discovered Files
- [list relevant files with brief descriptions]
-
-## Current Architecture
- [describe existing structure]
-
-## Integration Points
- [list dependencies and interfaces]
-
-## Constraints & Limitations
- [note any blockers or constraints]
-
-## Key Findings
- [most important discoveries]
-\`\`\`
-
-### Stage 2: Understanding (→ understanding.md)
-
-Synthesize exploration findings into actionable understanding:
-
-\`\`\`markdown
-# Understanding: ${sub.focus_area}
-
-## Problem Statement
-[Restate what needs to be done for this focus area]
-
-## Current State Analysis
-[What exists now, what's missing]
-
-## Proposed Approach
-[High-level strategy for implementation]
-
-## Technical Decisions
- Decision 1: [choice] because [rationale]
- Decision 2: [choice] because [rationale]
-
-## Risks & Mitigations
- Risk 1: [description] → Mitigation: [approach]
-
-## Dependencies on Other Sub-Requirements
- Depends on: [list any dependencies on other focus areas]
- Provides for: [what this provides to other focus areas]
-
-## Key Insights
-[Most important understanding gained]
-\`\`\`
-
-### Stage 3: Planning (→ sub-plan.json)
-
-Generate sub-plan.json following plan-json-schema.json:
- 2-5 tasks for this focus area
- Clear modification_points with file, target, change
- Verification criteria (unit_tests, integration_tests, manual_checks)
- Risk assessment per task
- Dependencies (internal to this sub-plan)
- Add source_agent: "${sub.focus_area}" to _metadata
-
 ## Output Requirements

-Write exactly 3 files:
-1. \`${sessionFolder}/agents/${sub.focus_area}/exploration.md\`
-2. \`${sessionFolder}/agents/${sub.focus_area}/understanding.md\`
-3. \`${sessionFolder}/agents/${sub.focus_area}/sub-plan.json\`
+Write 2 files to \`${sessionFolder}/agents/${sub.focus_area}/\`:
+1. **planning-context.md** - Evidence paths + synthesized understanding
+2. **sub-plan.json** - Plan with \`_metadata.source_agent: "${sub.focus_area}"\`

-## Success Criteria
-
- [ ] Exploration covers all relevant code areas
- [ ] Understanding synthesizes findings into clear approach
- [ ] sub-plan.json follows plan-json-schema.json with 2-5 tasks
- [ ] Each task has modification_points, acceptance, verification
- [ ] Dependencies clearly stated
- [ ] All 3 files written to correct location
+See cli-lite-planning-agent documentation for file formats.
 `
  })
 })
@@ -515,9 +442,9 @@ TodoWrite({ todos: [
  { content: "Phase 4: Merge & Synthesis", status: "in_progress", activeForm: "Merging plans" }
 ]})

-// Collect all understanding documents for context
-const understandingDocs = subRequirements.map(sub => {
-  const path = `${sessionFolder}/agents/${sub.focus_area}/understanding.md`
+// Collect all planning context documents for context
+const contextDocs = subRequirements.map(sub => {
+  const path = `${sessionFolder}/agents/${sub.focus_area}/planning-context.md`
  return {
    focus_area: sub.focus_area,
    content: Read(path)
@@ -559,11 +486,11 @@ ${JSON.stringify(sp.plan, null, 2)}
 \`\`\`
 `).join('\n')}

-## Understanding Documents
+## Planning Context Documents

-${understandingDocs.map(ud => `
-### Understanding: ${ud.focus_area}
-${ud.content}
+${contextDocs.map(cd => `
+### Context: ${cd.focus_area}
+${cd.content}
 `).join('\n')}

 ## Detected Conflicts
@@ -740,8 +667,7 @@ ${task.acceptance?.map(ac => `- ${ac}`).join('\n') || 'N/A'}

 ${subRequirements.map(sub => `
 ### ${sub.focus_area}
- Exploration: \`${sessionFolder}/agents/${sub.focus_area}/exploration.md\`
- Understanding: \`${sessionFolder}/agents/${sub.focus_area}/understanding.md\`
+- Context: \`${sessionFolder}/agents/${sub.focus_area}/planning-context.md\`
 - Sub-Plan: \`${sessionFolder}/agents/${sub.focus_area}/sub-plan.json\`
 `).join('\n')}

@@ -776,8 +702,7 @@ console.log(`
 ├── requirement-analysis.json   # Requirement breakdown
 ├── agents/                     # Per-agent process files
 ${subRequirements.map(sub => `│   ├── ${sub.focus_area}/
-│   │   ├── exploration.md
-│   │   ├── understanding.md
+│   │   ├── planning-context.md
 │   │   └── sub-plan.json`).join('\n')}
 ├── conflicts.json              # Detected conflicts
 ├── plan.json                   # Unified plan (execution-ready)
@@ -792,7 +717,7 @@ Execute the plan:

 Review a specific agent's work:
 \`\`\`bash
-cat ${sessionFolder}/agents/{focus-area}/understanding.md
+cat ${sessionFolder}/agents/{focus-area}/planning-context.md
 \`\`\`
 `)
 ```
@@ -827,7 +752,7 @@ cat ${sessionFolder}/agents/{focus-area}/understanding.md
 ## Best Practices

 1. **Be Specific**: Detailed requirements lead to better splits
-2. **Review Process Files**: Check exploration.md and understanding.md for insights
+2. **Review Process Files**: Check planning-context.md for insights
 3. **Trust the Merge**: Conflict resolution follows defined rules
 4. **Iterate if Needed**: Re-run with different --merge-rule if results unsatisfactory

--- a/.claude/commands/workflow/lite-fix.md
+++ b/.claude/commands/workflow/lite-fix.md
@@ -37,6 +37,23 @@ Intelligent lightweight bug fixing command with dynamic workflow adaptation base
 /workflow:lite-fix -y --hotfix "生产环境数据库连接失败"   # Auto + hotfix mode
 ```

+## Output Artifacts
+
+| Artifact | Description |
+|----------|-------------|
+| `diagnosis-{angle}.json` | Per-angle diagnosis results (1-4 files based on severity) |
+| `diagnoses-manifest.json` | Index of all diagnosis files |
+| `planning-context.md` | Evidence paths + synthesized understanding |
+| `fix-plan.json` | Structured fix plan (fix-plan-json-schema.json) |
+
+**Output Directory**: `.workflow/.lite-fix/{bug-slug}-{YYYY-MM-DD}/`
+
+**Agent Usage**:
+- Low/Medium severity → Direct Claude planning (no agent)
+- High/Critical severity → `cli-lite-planning-agent` generates `fix-plan.json`
+
+**Schema Reference**: `~/.claude/workflows/cli-templates/schemas/fix-plan-json-schema.json`
+
 ## Auto Mode Defaults

 When `--yes` or `-y` flag is used:
@@ -192,11 +209,15 @@ const diagnosisTasks = selectedAngles.map((angle, index) =>
 ## Task Objective
 Execute **${angle}** diagnosis for bug root cause analysis. Analyze codebase from this specific angle to discover root cause, affected paths, and fix hints.

+## Output Location
+
+**Session Folder**: ${sessionFolder}
+**Output File**: ${sessionFolder}/diagnosis-${angle}.json
+
 ## Assigned Context
 - **Diagnosis Angle**: ${angle}
 - **Bug Description**: ${bug_description}
 - **Diagnosis Index**: ${index + 1} of ${selectedAngles.length}
- **Output File**: ${sessionFolder}/diagnosis-${angle}.json

 ## MANDATORY FIRST STEPS (Execute by Agent)
 **You (cli-explore-agent) MUST execute these steps in order:**
@@ -225,8 +246,6 @@ Execute **${angle}** diagnosis for bug root cause analysis. Analyze codebase fro

 ## Expected Output

-**File**: ${sessionFolder}/diagnosis-${angle}.json
-
 **Schema Reference**: Schema obtained in MANDATORY FIRST STEPS step 3, follow schema exactly

 **Required Fields** (all ${angle} focused):
@@ -255,9 +274,9 @@ Execute **${angle}** diagnosis for bug root cause analysis. Analyze codebase fro
 - [ ] JSON output follows schema exactly
 - [ ] clarification_needs includes options + recommended

-## Output
-Write: ${sessionFolder}/diagnosis-${angle}.json
-Return: 2-3 sentence summary of ${angle} diagnosis findings
+## Execution
+**Write**: \`${sessionFolder}/diagnosis-${angle}.json\`
+**Return**: 2-3 sentence summary of ${angle} diagnosis findings
 `
  )
 )
@@ -493,6 +512,13 @@ Task(
  prompt=`
 Generate fix plan and write fix-plan.json.

+## Output Location
+
+**Session Folder**: ${sessionFolder}
+**Output Files**:
+- ${sessionFolder}/planning-context.md (evidence + understanding)
+- ${sessionFolder}/fix-plan.json (fix plan)
+
 ## Output Schema Reference
 Execute: cat ~/.claude/workflows/cli-templates/schemas/fix-plan-json-schema.json (get schema reference before generating plan)

@@ -588,8 +614,9 @@ Generate fix-plan.json with:
   - For High/Critical: REQUIRED new fields (rationale, verification, risks, code_skeleton, data_flow, design_decisions)
   - Each task MUST have rationale (why this fix), verification (how to verify success), and risks (potential issues)
 5. Parse output and structure fix-plan
-6. Write JSON: Write('${sessionFolder}/fix-plan.json', jsonContent)
-7. Return brief completion summary
+6. **Write**: \`${sessionFolder}/planning-context.md\` (evidence paths + understanding)
+7. **Write**: \`${sessionFolder}/fix-plan.json\`
+8. Return brief completion summary

 ## Output Format for CLI
 Include these sections in your fix-plan output:
@@ -747,22 +774,24 @@ SlashCommand(command="/workflow:lite-execute --in-memory --mode bugfix")

 ```
 .workflow/.lite-fix/{bug-slug}-{YYYY-MM-DD}/
-|- diagnosis-{angle1}.json      # Diagnosis angle 1
-|- diagnosis-{angle2}.json      # Diagnosis angle 2
-|- diagnosis-{angle3}.json      # Diagnosis angle 3 (if applicable)
-|- diagnosis-{angle4}.json      # Diagnosis angle 4 (if applicable)
-|- diagnoses-manifest.json      # Diagnosis index
-+- fix-plan.json                # Fix plan
+├── diagnosis-{angle1}.json      # Diagnosis angle 1
+├── diagnosis-{angle2}.json      # Diagnosis angle 2
+├── diagnosis-{angle3}.json      # Diagnosis angle 3 (if applicable)
+├── diagnosis-{angle4}.json      # Diagnosis angle 4 (if applicable)
+├── diagnoses-manifest.json      # Diagnosis index
+├── planning-context.md          # Evidence + understanding
+└── fix-plan.json                # Fix plan
 ```

 **Example**:
 ```
-.workflow/.lite-fix/user-avatar-upload-fails-413-2025-11-25-14-30-25/
-|- diagnosis-error-handling.json
-|- diagnosis-dataflow.json
-|- diagnosis-validation.json
-|- diagnoses-manifest.json
-+- fix-plan.json
+.workflow/.lite-fix/user-avatar-upload-fails-413-2025-11-25/
+├── diagnosis-error-handling.json
+├── diagnosis-dataflow.json
+├── diagnosis-validation.json
+├── diagnoses-manifest.json
+├── planning-context.md
+└── fix-plan.json
 ```

 ## Error Handling
--- a/.claude/commands/workflow/lite-plan.md
+++ b/.claude/commands/workflow/lite-plan.md
@@ -37,6 +37,23 @@ Intelligent lightweight planning command with dynamic workflow adaptation based
 /workflow:lite-plan -y -e "优化数据库查询性能"       # Auto mode + force exploration
 ```

+## Output Artifacts
+
+| Artifact | Description |
+|----------|-------------|
+| `exploration-{angle}.json` | Per-angle exploration results (1-4 files based on complexity) |
+| `explorations-manifest.json` | Index of all exploration files |
+| `planning-context.md` | Evidence paths + synthesized understanding |
+| `plan.json` | Structured implementation plan (plan-json-schema.json) |
+
+**Output Directory**: `.workflow/.lite-plan/{task-slug}-{YYYY-MM-DD}/`
+
+**Agent Usage**:
+- Low complexity → Direct Claude planning (no agent)
+- Medium/High complexity → `cli-lite-planning-agent` generates `plan.json`
+
+**Schema Reference**: `~/.claude/workflows/cli-templates/schemas/plan-json-schema.json`
+
 ## Auto Mode Defaults

 When `--yes` or `-y` flag is used:
@@ -193,11 +210,15 @@ const explorationTasks = selectedAngles.map((angle, index) =>
 ## Task Objective
 Execute **${angle}** exploration for task planning context. Analyze codebase from this specific angle to discover relevant structure, patterns, and constraints.

+## 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}
- **Output File**: ${sessionFolder}/exploration-${angle}.json

 ## MANDATORY FIRST STEPS (Execute by Agent)
 **You (cli-explore-agent) MUST execute these steps in order:**
@@ -225,8 +246,6 @@ Execute **${angle}** exploration for task planning context. Analyze codebase fro

 ## Expected Output

-**File**: ${sessionFolder}/exploration-${angle}.json
-
 **Schema Reference**: Schema obtained in MANDATORY FIRST STEPS step 3, follow schema exactly

 **Required Fields** (all ${angle} focused):
@@ -252,9 +271,9 @@ Execute **${angle}** exploration for task planning context. Analyze codebase fro
 - [ ] JSON output follows schema exactly
 - [ ] clarification_needs includes options + recommended

-## Output
-Write: ${sessionFolder}/exploration-${angle}.json
-Return: 2-3 sentence summary of ${angle} findings
+## Execution
+**Write**: \`${sessionFolder}/exploration-${angle}.json\`
+**Return**: 2-3 sentence summary of ${angle} findings
 `
  )
 )
@@ -443,6 +462,13 @@ Task(
  prompt=`
 Generate implementation plan and write plan.json.

+## Output Location
+
+**Session Folder**: ${sessionFolder}
+**Output Files**:
+- ${sessionFolder}/planning-context.md (evidence + understanding)
+- ${sessionFolder}/plan.json (implementation plan)
+
 ## Output Schema Reference
 Execute: cat ~/.claude/workflows/cli-templates/schemas/plan-json-schema.json (get schema reference before generating plan)

@@ -492,8 +518,9 @@ Generate plan.json following the schema obtained above. Key constraints:
 2. Execute CLI planning using Gemini (Qwen fallback)
 3. Read ALL exploration files for comprehensive context
 4. Synthesize findings and generate plan following schema
-5. Write JSON: Write('${sessionFolder}/plan.json', jsonContent)
-6. Return brief completion summary
+5. **Write**: \`${sessionFolder}/planning-context.md\` (evidence paths + understanding)
+6. **Write**: \`${sessionFolder}/plan.json\`
+7. Return brief completion summary
 `
 )
 ```