feat: add exploration and plan JSON schemas for task context and planning

.claude/commands/workflow/lite-plan.md

@@ -21,7 +21,6 @@ Intelligent lightweight planning command with dynamic workflow adaptation based
 
 ## Usage
 
-### Command Syntax
 ```bash
 /workflow:lite-plan [FLAGS] <TASK_DESCRIPTION>
 
@@ -32,24 +31,8 @@ Intelligent lightweight planning command with dynamic workflow adaptation based
 <task-description>         Task description or path to .md file (required)
 ```
 
-### Input Requirements
-- **Task description**: String or path to .md file (required)
-  - Should be specific and concrete
-  - Can include context about existing code or requirements
-  - Examples:
-    - "Implement user authentication with JWT tokens"
-    - "Refactor logging module for better performance"
-    - "Add unit tests for authentication service"
-- **Flags** (optional):
-  - `-e` or `--explore`: Force exploration when:
-    - Task appears simple but requires codebase context
-    - Auto-detection might miss integration points
-    - Comprehensive code understanding needed before planning
-
 ## Execution Process
 
-### Workflow Overview
-
 ```
 User Input → Task Analysis & Exploration Decision (Phase 1)
           ↓
@@ -60,147 +43,99 @@ User Input → Task Analysis & Exploration Decision (Phase 1)
      Task Confirmation & Execution Selection (Phase 4)
           ↓
      Dispatch to Execution (Phase 5)
-          ↓
-     Planning Complete (lite-execute continues)
 ```
 
-### Phase Summary
+## Implementation
-
-**Phase 1: Task Analysis & Exploration Decision** (10-60 seconds)
-- Analyze task to determine exploration needs
-- Decision logic: `--explore` flag OR requires codebase context
-- If needed: Launch cli-explore-agent for code analysis
-- Output: `explorationContext` with relevant files, patterns, constraints
-
-**Phase 2: Clarification** (30-60 seconds, optional)
-- Skip if no ambiguities found in Phase 1
-- Use exploration findings to generate targeted questions
-- AskUserQuestion based on `clarification_needs` from exploration
-- Output: `clarificationContext` with user responses
-
-**Phase 3: Complexity Assessment & Planning** (20-60 seconds)
-- Assess complexity (Low/Medium/High) from multiple factors
-- Strategy selection:
-  - Low: Direct planning by current Claude (fast, 20-30s)
-  - Medium/High: Delegate to cli-lite-planning-agent (detailed, 40-60s)
-- Output: `planObject` with tasks, time estimates, recommendations
-
-**Phase 4: Task Confirmation & Execution Selection** (user interaction)
-- Step 1: Display complete plan as text to user
-- Step 2: Collect four inputs via AskUserQuestion:
-  1. Confirm plan (Allow/Modify/Cancel + supplements via "Other")
-  2. Execution method (Agent/Codex/Auto)
-  3. Code review tool (Skip/Gemini/Agent + custom via "Other")
-  4. Export JSON (Yes/No for Enhanced Task JSON export)
-
-**Phase 5: Dispatch to Execution** (<1 second)
-- Export Enhanced Task JSON (optional, if user selected "Yes")
-- Store `executionContext` in memory with full plan + context
-- Call `/workflow:lite-execute --in-memory`
-- Execution tracking delegated to lite-execute
-
-## Detailed Phase Execution
 
 ### Phase 1: Task Analysis & Exploration Decision
 
+**Session Setup**:
+```javascript
+const taskSlug = task_description.toLowerCase().replace(/[^a-z0-9]+/g, '-').substring(0, 40)
+const timestamp = new Date().toISOString().replace(/[:.]/g, '-')
+const shortTimestamp = timestamp.substring(0, 19).replace('T', '-')
+const sessionId = `${taskSlug}-${shortTimestamp}`
+const sessionFolder = `.workflow/.lite-plan/${sessionId}`
+
+bash(`mkdir -p ${sessionFolder}`)
+```
+
 **Decision Logic**:
 ```javascript
 needsExploration = (
-  flags.includes('--explore') || flags.includes('-e') ||  // Force if flag present
+  flags.includes('--explore') || flags.includes('-e') ||
-  (
+  task.mentions_specific_files ||
-    task.mentions_specific_files ||
+  task.requires_codebase_context ||
-    task.requires_codebase_context ||
+  task.needs_architecture_understanding ||
-    task.needs_architecture_understanding ||
+  task.modifies_existing_code
-    task.modifies_existing_code
-  )
 )
 ```
 
-**Decision Criteria**:
+**If exploration needed** - Invoke cli-explore-agent:
 
-| Task Type | Needs Exploration | Reason |
-|-----------|-------------------|--------|
-| Any task with `-e`/`--explore` flag | **Yes (forced)** | **Flag overrides auto-detection** |
-| "Implement new feature X" | Maybe | Depends on integration needs |
-| "Refactor module Y" | Yes | Needs current implementation understanding |
-| "Add tests for Z" | Yes | Needs code structure understanding |
-| "Create standalone utility" | No | Self-contained, no existing context |
-| "Update documentation" | No | Doesn't require code exploration |
-| "Fix bug in function F" | Yes | Needs implementation understanding |
-
-**Exploration Execution** (if needed):
 ```javascript
-// Generate session identifiers for artifact storage
-const taskSlug = task_description.toLowerCase().replace(/[^a-z0-9]+/g, '-').substring(0, 40)
-const timestamp = new Date().toISOString().replace(/[:.]/g, '-')
-const shortTimestamp = timestamp.substring(0, 19).replace('T', '-') // YYYY-MM-DD-HH-mm-ss
-const sessionId = `${taskSlug}-${shortTimestamp}`
-const sessionFolder = `.workflow/.lite-plan/${sessionId}`
-
 Task(
   subagent_type="cli-explore-agent",
   description="Analyze codebase for task context",
   prompt=`
-  Task: ${task_description}
+Analyze codebase for task context and generate exploration.json.
 
-  Analyze and return structured information:
+## Output Schema Reference
-  1. Project Structure: Architecture and module organization
+~/.claude/workflows/cli-templates/schemas/explore-json-schema.json
-  2. Relevant Files: Files to be affected (with paths)
-  3. Current Patterns: Code patterns, conventions, styles
-  4. Dependencies: External/internal module dependencies
-  5. Integration Points: Task connections with existing code
-  6. Architecture Constraints: Technical limitations/requirements
-  7. Clarification Needs: Ambiguities requiring user input
 
-  Time Limit: 60 seconds
+## Task Description
-  Output Format: JSON-like structured object
+${task_description}
-  `
+
+## Requirements
+Generate exploration.json with:
+- project_structure: Architecture and module organization
+- relevant_files: File paths to be affected
+- patterns: Code patterns, conventions, styles
+- dependencies: External/internal module dependencies
+- integration_points: Task connections with existing code
+- constraints: Technical limitations/requirements
+- clarification_needs: Ambiguities requiring user input
+- _metadata: timestamp, task_description, source
+
+## Execution
+1. Structural scan: get_modules_by_depth.sh, find, rg
+2. Semantic analysis: Gemini for patterns/architecture
+3. Write JSON: Write('${sessionFolder}/exploration.json', jsonContent)
+4. Return brief completion summary
+
+Time Limit: 60 seconds
+`
 )
-
-// Save exploration results for CLI/agent access in lite-execute
-const explorationFile = `${sessionFolder}/exploration.json`
-Write(explorationFile, JSON.stringify(explorationContext, null, 2))
 ```
 
-**Output**: `explorationContext` (in-memory, see Data Structures section)
+**Output**: `${sessionFolder}/exploration.json` (if exploration performed)
-**Artifact**: Saved to `{sessionFolder}/exploration.json` for CLI/agent use
-
-**Progress Tracking**:
-- Mark Phase 1 completed
-- If `clarification_needs.length > 0`: Mark Phase 2 in_progress
-- Else: Skip to Phase 3
 
 ---
 
 ### Phase 2: Clarification (Optional)
 
-**Skip Condition**: Only run if `needsClarification = true` from Phase 1
+**Skip if**: No exploration or `clarification_needs` is empty
 
-**Operations**:
+**If clarification needed**:
-- Review `explorationContext.clarification_needs`
-- Generate AskUserQuestion from exploration findings
-- Focus on ambiguities affecting implementation approach
-
-**Question Generation**:
 ```javascript
-AskUserQuestion({
+const exploration = JSON.parse(Read(`${sessionFolder}/exploration.json`))
-  questions: explorationContext.clarification_needs.map(need => ({
+
-    question: `${need.context}\n\n${need.question}`,
+if (exploration.clarification_needs?.length > 0) {
-    header: "Clarification",
+  AskUserQuestion({
-    multiSelect: false,
+    questions: exploration.clarification_needs.map(need => ({
-    options: need.options.map(opt => ({
+      question: `${need.context}\n\n${need.question}`,
-      label: opt,
+      header: "Clarification",
-      description: `Use ${opt} approach`
+      multiSelect: false,
+      options: need.options.map(opt => ({
+        label: opt,
+        description: `Use ${opt} approach`
+      }))
     }))
-  }))
+  })
-})
+}
 ```
 
-**Output**: `clarificationContext` in format `{ question_id: selected_answer }`
+**Output**: `clarificationContext` (in-memory)
-
-**Progress Tracking**:
-- Mark Phase 2 completed
-- Mark Phase 3 in_progress
 
 ---
 
@@ -209,149 +144,96 @@ AskUserQuestion({
 **Complexity Assessment**:
 ```javascript
 complexityScore = {
-  file_count: exploration.files_to_modify.length,
+  file_count: exploration?.relevant_files?.length || 0,
-  integration_points: exploration.dependencies.length,
+  integration_points: exploration?.dependencies?.length || 0,
-  architecture_changes: exploration.requires_architecture_change,
+  architecture_changes: exploration?.constraints?.includes('architecture'),
-  technology_stack: exploration.unfamiliar_technologies.length,
+  task_scope: estimated_steps > 5
-  task_scope: (task.estimated_steps > 5),
-  cross_cutting_concerns: exploration.affects_multiple_modules
 }
 
-// Calculate complexity
+// Low: score < 3, Medium: 3-5, High: > 5
-if (complexityScore < 3) complexity = "Low"
-else if (complexityScore < 6) complexity = "Medium"
-else complexity = "High"
 ```
 
-**Complexity Levels**:
+**Low Complexity** - Direct planning by Claude:
+- Generate plan directly, write to `${sessionFolder}/plan.json`
+- No agent invocation
 
-| Level | Characteristics | Planning Strategy |
+**Medium/High Complexity** - Invoke cli-lite-planning-agent:
-|-------|----------------|-------------------|
-| Low | 1-2 files, simple changes, clear requirements | Direct planning (current Claude) |
-| Medium | 3-5 files, moderate integration, some ambiguity | cli-lite-planning-agent |
-| High | 6+ files, complex architecture, high uncertainty | cli-lite-planning-agent with detailed analysis |
 
-**Option A: Direct Planning (Low Complexity)**
-
-Current Claude generates plan directly:
-- Summary: 2-3 sentence overview
-- Approach: High-level implementation strategy
-- Task Breakdown: 3-5 specific, actionable tasks with file paths
-- Estimated Time: Total implementation time
-- Recommended Execution: "Agent"
-
-```javascript
-// Save planning results to session folder (same as Option B)
-const planFile = `${sessionFolder}/plan.json`
-Write(planFile, JSON.stringify(planObject, null, 2))
-```
-
-**Artifact**: Saved to `{sessionFolder}/plan.json` for CLI/agent use
-
-**Option B: Agent-Based Planning (Medium/High Complexity)**
-
-Delegate to cli-lite-planning-agent:
 ```javascript
 Task(
   subagent_type="cli-lite-planning-agent",
   description="Generate detailed implementation plan",
   prompt=`
-  ## Task Description
+Generate implementation plan and write plan.json.
-  ${task_description}
 
-  ## Exploration Context
+## Output Schema Reference
-  ${JSON.stringify(explorationContext, null, 2) || "No exploration performed"}
+~/.claude/workflows/cli-templates/schemas/plan-json-schema.json
 
-  ## User Clarifications
+## Task Description
-  ${JSON.stringify(clarificationContext, null, 2) || "None provided"}
+${task_description}
 
-  ## Complexity Level
+## Exploration Context
-  ${complexity}
+${sessionFolder}/exploration.json (if exists)
 
-  ## Your Task
+## User Clarifications
-  1. Execute CLI planning using Gemini (Qwen fallback)
+${JSON.stringify(clarificationContext) || "None"}
-  2. Parse CLI output and extract structured plan
-  3. Enhance tasks with file paths and pattern references
-  4. Generate planObject with:
-     - Summary (2-3 sentences)
-     - Approach (high-level strategy)
-     - Tasks (3-10 actionable steps)
-     - Estimated time (with breakdown)
-     - Recommended execution (Agent for Low, Codex for Medium/High)
-  5. Return planObject (no file writes)
 
-  ## Quality Requirements
+## Complexity Level
-  Each task MUST include:
+${complexity}
-  - Action verb (Create/Update/Add/Implement/Refactor)
-  - Specific file path
-  - Detailed changes
-  - Pattern reference from exploration
 
-  Format: "{Action} in {file_path}: {details} following {pattern}"
+## Requirements
-  `
+Generate plan.json with:
+- summary: 2-3 sentence overview
+- approach: High-level implementation strategy
+- tasks: 3-10 structured tasks with:
+  - title, file, action, description
+  - implementation (3-7 steps)
+  - reference (pattern, files, examples)
+  - acceptance (2-4 criteria)
+- estimated_time, recommended_execution, complexity
+- _metadata: timestamp, source, planning_mode
+
+## Execution
+1. Execute CLI planning using Gemini (Qwen fallback)
+2. Parse output and structure plan
+3. Write JSON: Write('${sessionFolder}/plan.json', jsonContent)
+4. Return brief completion summary
+`
 )
-
-// Save planning results to session folder
-const planFile = `${sessionFolder}/plan.json`
-Write(planFile, JSON.stringify(planObject, null, 2))
 ```
 
-**Output**: `planObject` (see Data Structures section)
+**Output**: `${sessionFolder}/plan.json`
-**Artifact**: Saved to `{sessionFolder}/plan.json` for CLI/agent use
-
-**Progress Tracking**:
-- Mark Phase 3 completed
-- Mark Phase 4 in_progress
-
-**Expected Duration**:
-- Low: 20-30 seconds (direct)
-- Medium/High: 40-60 seconds (agent-based)
 
 ---
 
 ### Phase 4: Task Confirmation & Execution Selection
 
-**Two-Step Confirmation Process**
+**Step 4.1: Display Plan**
+```javascript
+const plan = JSON.parse(Read(`${sessionFolder}/plan.json`))
 
-**Step 4.1: Display Plan Summary**
+console.log(`
-
-Output complete plan as regular text:
-
-```
 ## Implementation Plan
 
-**Summary**: ${planObject.summary}
+**Summary**: ${plan.summary}
+**Approach**: ${plan.approach}
 
-**Approach**: ${planObject.approach}
+**Tasks** (${plan.tasks.length}):
+${plan.tasks.map((t, i) => `${i+1}. ${t.title} (${t.file})`).join('\n')}
 
-**Task Breakdown** (${planObject.tasks.length} tasks):
+**Complexity**: ${plan.complexity}
-${planObject.tasks.map((task, i) => `
+**Estimated Time**: ${plan.estimated_time}
-${i+1}. **${task.title}** (${task.file})
+**Recommended**: ${plan.recommended_execution}
-   - What: ${task.description}
+`)
-   - How: ${task.implementation.length} steps
-   - Reference: ${task.reference.pattern}
-   - Verification: ${task.acceptance.length} criteria
-`).join('')}
-
-**Complexity**: ${planObject.complexity}
-**Estimated Time**: ${planObject.estimated_time}
-**Recommended Execution**: ${planObject.recommended_execution}
 ```
 
-**Step 4.2: Collect User Confirmation**
+**Step 4.2: Collect Confirmation**
-
-Three questions via single AskUserQuestion call:
-
 ```javascript
 AskUserQuestion({
   questions: [
     {
-      question: `**Plan Summary**: ${planObject.summary}
+      question: `Confirm plan? (${plan.tasks.length} tasks, ${plan.complexity})`,
-
+      header: "Confirm",
-**Tasks**: ${planObject.tasks.length} | **Complexity**: ${planObject.complexity} | **Time**: ${planObject.estimated_time}
-
-Confirm plan? (Multi-select: can supplement via "Other")`,
-      header: "Confirm Plan",
       multiSelect: true,
       options: [
         { label: "Allow", description: "Proceed as-is" },
@@ -360,22 +242,22 @@ Confirm plan? (Multi-select: can supplement via "Other")`,
       ]
     },
     {
-      question: "Select execution method:",
+      question: "Execution method:",
       header: "Execution",
       multiSelect: false,
       options: [
         { label: "Agent", description: "@code-developer agent" },
         { label: "Codex", description: "codex CLI tool" },
-        { label: "Auto", description: `Auto: ${planObject.complexity === 'Low' ? 'Agent' : 'Codex'}` }
+        { label: "Auto", description: `Auto: ${plan.complexity === 'Low' ? 'Agent' : 'Codex'}` }
       ]
     },
     {
-      question: "Enable code review after execution?\n\n(Custom tools via \"Other\": qwen, codex, etc.)",
+      question: "Code review after execution?",
-      header: "Code Review",
+      header: "Review",
       multiSelect: false,
       options: [
-        { label: "Gemini Review", description: "Gemini CLI (gemini-2.5-pro)" },
+        { label: "Gemini Review", description: "Gemini CLI" },
-        { label: "Agent Review", description: "@code-reviewer agent" },
+        { label: "Agent Review", description: "@code-reviewer" },
         { label: "Skip", description: "No review" }
       ]
     }
@@ -383,351 +265,95 @@ Confirm plan? (Multi-select: can supplement via "Other")`,
 })
 ```
 
-**Decision Flow**:
-```
-Task Confirmation (Multi-select):
-  ├─ Allow (+ supplements) → Execution Method Selection
-  ├─ Modify (+ supplements) → Re-run Phase 3
-  └─ Cancel → Exit
-
-Execution Method (Single-select):
-  ├─ Agent → Launch @code-developer
-  ├─ Codex → Execute with codex CLI
-  └─ Auto → Low complexity: Agent | Medium/High: Codex
-
-Code Review (after execution):
-  ├─ Skip → No review
-  ├─ Gemini Review → gemini CLI analysis
-  ├─ Agent Review → Current Claude review
-  └─ Other → Custom tool (e.g., qwen, codex)
-```
-
-**Progress Tracking**:
-- Mark Phase 4 completed
-- Mark Phase 5 in_progress
-
 ---
 
 ### Phase 5: Dispatch to Execution
 
-**Step 5.1: Export Enhanced Task JSON**
+**Step 5.1: Generate task.json** (by command, not agent)
-
-Always export Enhanced Task JSON to session folder:
 
 ```javascript
 const taskId = `LP-${shortTimestamp}`
-const filename = `${sessionFolder}/task.json`
+const exploration = file_exists(`${sessionFolder}/exploration.json`)
+  ? JSON.parse(Read(`${sessionFolder}/exploration.json`))
+  : null
+const plan = JSON.parse(Read(`${sessionFolder}/plan.json`))
 
-const enhancedTaskJson = {
+const taskJson = {
   id: taskId,
-  title: original_task_description,
+  title: task_description,
   status: "pending",
 
   meta: {
     type: "planning",
     created_at: new Date().toISOString(),
-    complexity: planObject.complexity,
+    complexity: plan.complexity,
-    estimated_time: planObject.estimated_time,
+    estimated_time: plan.estimated_time,
-    recommended_execution: planObject.recommended_execution,
+    recommended_execution: plan.recommended_execution,
     workflow: "lite-plan",
     session_id: sessionId,
     session_folder: sessionFolder
   },
 
   context: {
-    requirements: [original_task_description],
+    requirements: [task_description],
     plan: {
-      summary: planObject.summary,
+      summary: plan.summary,
-      approach: planObject.approach,
+      approach: plan.approach,
-      tasks: planObject.tasks
+      tasks: plan.tasks
     },
-    exploration: explorationContext || null,
+    exploration: exploration,
     clarifications: clarificationContext || null,
-    focus_paths: explorationContext?.relevant_files || [],
+    focus_paths: exploration?.relevant_files || [],
-    acceptance: planObject.tasks.flatMap(t => t.acceptance)
+    acceptance: plan.tasks.flatMap(t => t.acceptance)
   }
 }
 
-Write(filename, JSON.stringify(enhancedTaskJson, null, 2))
+Write(`${sessionFolder}/task.json`, JSON.stringify(taskJson, null, 2))
-console.log(`Enhanced Task JSON exported to: ${filename}`)
-console.log(`Session folder: ${sessionFolder}`)
-console.log(`Reuse with: /workflow:lite-execute ${filename}`)
 ```
 
-**Step 5.2: Store Execution Context**
+**Step 5.2: Store executionContext**
 
 ```javascript
 executionContext = {
-  planObject: planObject,
+  planObject: plan,
-  explorationContext: explorationContext || null,
+  explorationContext: exploration,
   clarificationContext: clarificationContext || null,
   executionMethod: userSelection.execution_method,
   codeReviewTool: userSelection.code_review_tool,
-  originalUserInput: original_task_description,
+  originalUserInput: task_description,
-
-  // Session artifacts location
   session: {
     id: sessionId,
     folder: sessionFolder,
     artifacts: {
-      exploration: explorationContext ? `${sessionFolder}/exploration.json` : null,
+      exploration: exploration ? `${sessionFolder}/exploration.json` : null,
       plan: `${sessionFolder}/plan.json`,
-      task: `${sessionFolder}/task.json`  // Always exported
+      task: `${sessionFolder}/task.json`
     }
   }
 }
 ```
 
-**Step 5.3: Call lite-execute**
+**Step 5.3: Dispatch**
 
 ```javascript
 SlashCommand(command="/workflow:lite-execute --in-memory")
 ```
 
-**Execution Handoff**:
+## Session Folder Structure
-- lite-execute reads `executionContext` variable from memory
-- `executionContext.session.artifacts` contains file paths to saved planning artifacts:
-  - `exploration` - exploration.json (if exploration performed)
-  - `plan` - plan.json (always exists)
-  - `task` - task.json (if user selected export)
-- All execution logic handled by lite-execute
-- lite-plan completes after successful handoff
 
-**Progress Tracking**:
+```
-- Mark Phase 5 completed
+.workflow/.lite-plan/{task-slug}-{timestamp}/
-- Execution tracking delegated to lite-execute
+├── exploration.json    # If exploration performed (by cli-explore-agent)
-
+├── plan.json           # Always created (by agent or direct planning)
-## Best Practices
+└── task.json           # Always created (by command)
-
+```
-### Workflow Intelligence
-
-1. **Dynamic Adaptation**: Workflow adjusts based on task characteristics
-   - Smart exploration: Only when codebase context needed
-   - Adaptive planning: Simple → direct, complex → specialized agent
-   - Context-aware clarification: Only when truly needed
-   - Reduces unnecessary steps while maintaining thoroughness
-
-2. **Flag-Based Control**: Use `-e`/`--explore` to force exploration when:
-   - Task appears simple but requires codebase context
-   - Auto-detection might miss subtle integration points
-   - Comprehensive code understanding needed
-
-3. **Progressive Clarification**: Information gathered at right time
-   - Phase 1: Explore codebase (current state)
-   - Phase 2: Ask questions (based on findings)
-   - Phase 3: Plan with complete context
-   - Avoids premature assumptions, reduces rework
-
-4. **Complexity-Aware Planning**: Strategy matches task complexity
-   - Low (1-2 files): Direct planning (fast, 20-30s)
-   - Medium (3-5 files): CLI planning (detailed, 40-50s)
-   - High (6+ files): CLI planning with risk analysis (thorough, 50-60s)
-
-5. **Two-Step Confirmation**: Clear separation between plan and control
-   - Step 1: Display plan as readable text (not in question)
-   - Step 2: Collect multi-dimensional input
-     - Plan confirmation (multi-select with supplements)
-     - Execution method selection
-     - Code review tool selection (custom via "Other")
-   - Enhanced Task JSON always exported to session folder
-   - Allows plan refinement without re-selecting execution method
-
-### Task Management
-
-1. **Phase-Based Organization**: 5 distinct phases with clear transitions
-   - Phase 1: Analysis & Exploration (automatic)
-   - Phase 2: Clarification (conditional, interactive)
-   - Phase 3: Planning (automatic, adaptive)
-   - Phase 4: Confirmation (interactive, multi-dimensional)
-   - Phase 5: Execution Dispatch (automatic)
-
-2. **Flexible Task Counts**: Adapts to complexity
-   - Low: 3-5 tasks (focused)
-   - Medium: 5-7 tasks (detailed)
-   - High: 7-10 tasks (comprehensive)
-
-3. **Session Artifact Management**:
-   - All planning artifacts saved to dedicated session folder
-   - Enhanced Task JSON always exported for reusability
-   - Plan context passed to execution via memory and files
-   - Clean organization with session-based folder structure
-
-### Planning Standards
-
-1. **Context-Rich Planning**: Plans include all relevant context
-   - Exploration findings (structure, patterns, constraints)
-   - User clarifications (requirements, preferences, decisions)
-   - Complexity assessment (risks, dependencies, estimates)
-   - Execution recommendations (Direct vs CLI, specific tool)
-
-2. **Modification Support**: Iterative refinement
-   - User can request modifications in Phase 4
-   - Feedback incorporated into re-planning
-   - No restart from scratch
-   - Collaborative planning workflow
 
 ## Error Handling
 
-| Error | Cause | Resolution |
+| Error | Resolution |
-|-------|-------|------------|
+|-------|------------|
-| Phase 1 Exploration Failure | cli-explore-agent unavailable/timeout | Skip exploration, set `explorationContext = null`, continue with task description only |
+| Exploration agent failure | Skip exploration, continue with task description only |
-| Phase 2 Clarification Timeout | User no response > 5 minutes | Use exploration findings as-is, proceed to Phase 3 with warning |
+| Planning agent failure | Fallback to direct planning by Claude |
-| Phase 3 Planning Agent Failure | cli-lite-planning-agent unavailable/timeout | Fallback to direct planning by current Claude |
+| Clarification timeout | Use exploration findings as-is |
-| Phase 3 Planning Timeout | Planning > 90 seconds | Generate simplified plan, mark as "Quick Plan", continue |
+| Confirmation timeout | Save context, display resume instructions |
-| Phase 4 Confirmation Timeout | User no response > 5 minutes | Save context to temp var, display resume instructions, exit gracefully |
+| Modify loop > 3 times | Suggest breaking task or using /workflow:plan |
-| Phase 4 Modification Loop | User requests modify > 3 times | Suggest breaking task into smaller pieces or using `/workflow:plan` |
-
-## Session Folder Structure
-
-Each lite-plan execution creates a dedicated session folder to organize all artifacts:
-
-```
-.workflow/.lite-plan/{task-slug}-{short-timestamp}/
-├── exploration.json          # Exploration results (if exploration performed)
-├── plan.json                 # Planning results (always created)
-└── task.json                 # Enhanced Task JSON (always created)
-```
-
-**Folder Naming Convention**:
-- `{task-slug}`: First 40 characters of task description, lowercased, non-alphanumeric replaced with `-`
-- `{short-timestamp}`: YYYY-MM-DD-HH-mm-ss format
-- Example: `.workflow/.lite-plan/implement-user-auth-jwt-2025-01-15-14-30-45/`
-
-**File Contents**:
-- `exploration.json`: Complete explorationContext object (if exploration performed, see Data Structures)
-- `plan.json`: Complete planObject (always created, see Data Structures)
-- `task.json`: Enhanced Task JSON with all context (always created, see Data Structures)
-
-**Access Patterns**:
-- **lite-plan**: Creates folder and writes all artifacts during execution, passes paths via `executionContext.session.artifacts`
-- **lite-execute**: Reads artifact paths from `executionContext.session.artifacts` (see lite-execute.md for usage details)
-- **User**: Can inspect artifacts for debugging or reference
-- **Reuse**: Pass `task.json` path to `/workflow:lite-execute {path}` for re-execution
-
-
-## Data Structures
-
-### explorationContext
-
-Exploration findings from cli-explore-agent (Phase 1):
-
-```javascript
-{
-  project_structure: string,           // Overall architecture description
-  relevant_files: string[],            // File paths to be modified/referenced
-  patterns: string,                    // Existing patterns and conventions
-  dependencies: string,                // Dependencies and integration points
-  integration_points: string,          // Where this connects with existing code
-  constraints: string,                 // Technical constraints
-  clarification_needs: [               // Questions requiring user input
-    {
-      question: string,
-      context: string,
-      options: string[]
-    }
-  ]
-}
-```
-
-### planObject
-
-Implementation plan from Phase 3:
-
-```javascript
-{
-  summary: string,                     // 2-3 sentence overview
-  approach: string,                    // High-level implementation strategy
-  tasks: [                             // 3-10 structured task objects
-    {
-      title: string,                   // Task title
-      file: string,                    // Target file path
-      action: string,                  // Create|Update|Implement|Refactor|Add|Delete
-      description: string,             // What to implement (1-2 sentences)
-      implementation: string[],        // Step-by-step how-to (3-7 steps)
-      reference: {                     // What to reference
-        pattern: string,               // Pattern name
-        files: string[],               // Reference file paths
-        examples: string               // Specific guidance
-      },
-      acceptance: string[]             // Verification criteria (2-4 items)
-    }
-  ],
-  estimated_time: string,              // Total implementation time
-  recommended_execution: string,       // "Agent" (Low) or "Codex" (Medium/High)
-  complexity: string                   // "Low" | "Medium" | "High"
-}
-```
-
-### executionContext
-
-Context passed to lite-execute via --in-memory (Phase 5):
-
-```javascript
-{
-  planObject: {                        // Complete planObject (see above)
-    summary: string,
-    approach: string,
-    tasks: [...],
-    estimated_time: string,
-    recommended_execution: string,
-    complexity: string
-  },
-  explorationContext: {...} | null,    // See explorationContext above
-  clarificationContext: {...} | null,  // User responses from Phase 2
-  executionMethod: "Agent" | "Codex" | "Auto",
-  codeReviewTool: "Skip" | "Gemini Review" | "Agent Review" | string,
-  originalUserInput: string,           // User's original task description
-
-  // Session artifacts location (for lite-execute to access saved files)
-  session: {
-    id: string,                        // Session identifier: {taskSlug}-{shortTimestamp}
-    folder: string,                    // Session folder path: .workflow/.lite-plan/{session-id}
-    artifacts: {
-      exploration: string | null,      // exploration.json path (if exploration performed)
-      plan: string,                    // plan.json path (always present)
-      task: string                     // task.json path (always exported)
-    }
-  }
-}
-```
-
-### Enhanced Task JSON Export
-
-When user selects "Export JSON", lite-plan exports this structure:
-
-```json
-{
-  "id": "LP-{timestamp}",
-  "title": "Original task description",
-  "status": "pending",
-
-  "meta": {
-    "type": "planning",
-    "created_at": "ISO timestamp",
-    "complexity": "Low|Medium|High",
-    "estimated_time": "X minutes",
-    "recommended_execution": "Agent|Codex",
-    "workflow": "lite-plan"
-  },
-
-  "context": {
-    "requirements": ["Original task description"],
-    "plan": {
-      "summary": "2-3 sentence overview",
-      "approach": "High-level strategy",
-      "tasks": [/* Array of task objects */]
-    },
-    "exploration": {/* explorationContext */} | null,
-    "clarifications": {/* clarificationContext */} | null,
-    "focus_paths": ["src/auth", "tests/auth"],
-    "acceptance": ["Criteria from plan.tasks"]
-  }
-}
-```
-
-**Schema Notes**:
-- Aligns with Enhanced Task JSON Schema (6-field structure)
-- `context_package_path` omitted (not used by lite-plan)
-- `flow_control` omitted (handled by lite-execute)
-- `focus_paths` derived from `exploration.relevant_files`
-- `acceptance` derived from `plan.tasks`

.claude/workflows/cli-templates/schemas/explore-json-schema.json

@@ -0,0 +1,90 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "title": "Exploration Context Schema",
+  "description": "Code exploration results from cli-explore-agent for task context gathering",
+  "type": "object",
+  "required": [
+    "project_structure",
+    "relevant_files",
+    "patterns",
+    "dependencies",
+    "integration_points",
+    "constraints",
+    "clarification_needs",
+    "_metadata"
+  ],
+  "properties": {
+    "project_structure": {
+      "type": "string",
+      "description": "Overall architecture description: module organization, layer structure, component relationships"
+    },
+    "relevant_files": {
+      "type": "array",
+      "items": {"type": "string"},
+      "description": "File paths to be modified or referenced for the task"
+    },
+    "patterns": {
+      "type": "string",
+      "description": "Existing code patterns, conventions, and styles found in the codebase"
+    },
+    "dependencies": {
+      "type": "string",
+      "description": "External and internal module dependencies relevant to the task"
+    },
+    "integration_points": {
+      "type": "string",
+      "description": "Where this task connects with existing code: APIs, hooks, events, shared state"
+    },
+    "constraints": {
+      "type": "string",
+      "description": "Technical constraints and limitations affecting implementation"
+    },
+    "clarification_needs": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "required": ["question", "context", "options"],
+        "properties": {
+          "question": {
+            "type": "string",
+            "description": "The clarification question to ask user"
+          },
+          "context": {
+            "type": "string",
+            "description": "Background context explaining why this clarification is needed"
+          },
+          "options": {
+            "type": "array",
+            "items": {"type": "string"},
+            "description": "Available options for user to choose from (2-4 options)"
+          }
+        }
+      },
+      "description": "Ambiguities requiring user input before planning"
+    },
+    "_metadata": {
+      "type": "object",
+      "required": ["timestamp", "task_description", "source"],
+      "properties": {
+        "timestamp": {
+          "type": "string",
+          "format": "date-time",
+          "description": "ISO 8601 timestamp of exploration"
+        },
+        "task_description": {
+          "type": "string",
+          "description": "Original task description that triggered exploration"
+        },
+        "source": {
+          "type": "string",
+          "const": "cli-explore-agent",
+          "description": "Agent that performed exploration"
+        },
+        "duration_seconds": {
+          "type": "integer",
+          "description": "Exploration duration in seconds"
+        }
+      }
+    }
+  }
+}

.claude/workflows/cli-templates/schemas/plan-json-schema.json

@@ -0,0 +1,127 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "title": "Plan Object Schema",
+  "description": "Implementation plan from cli-lite-planning-agent or direct planning",
+  "type": "object",
+  "required": [
+    "summary",
+    "approach",
+    "tasks",
+    "estimated_time",
+    "recommended_execution",
+    "complexity",
+    "_metadata"
+  ],
+  "properties": {
+    "summary": {
+      "type": "string",
+      "description": "2-3 sentence overview of the implementation plan"
+    },
+    "approach": {
+      "type": "string",
+      "description": "High-level implementation strategy and methodology"
+    },
+    "tasks": {
+      "type": "array",
+      "minItems": 3,
+      "maxItems": 10,
+      "items": {
+        "type": "object",
+        "required": ["title", "file", "action", "description", "implementation", "reference", "acceptance"],
+        "properties": {
+          "title": {
+            "type": "string",
+            "description": "Task title (action verb + target)"
+          },
+          "file": {
+            "type": "string",
+            "description": "Target file path for this task"
+          },
+          "action": {
+            "type": "string",
+            "enum": ["Create", "Update", "Implement", "Refactor", "Add", "Delete", "Configure", "Test"],
+            "description": "Primary action type"
+          },
+          "description": {
+            "type": "string",
+            "description": "What to implement (1-2 sentences)"
+          },
+          "implementation": {
+            "type": "array",
+            "items": {"type": "string"},
+            "minItems": 3,
+            "maxItems": 7,
+            "description": "Step-by-step implementation guide"
+          },
+          "reference": {
+            "type": "object",
+            "required": ["pattern", "files", "examples"],
+            "properties": {
+              "pattern": {
+                "type": "string",
+                "description": "Pattern name to follow"
+              },
+              "files": {
+                "type": "array",
+                "items": {"type": "string"},
+                "description": "Reference file paths to study"
+              },
+              "examples": {
+                "type": "string",
+                "description": "Specific guidance or example references"
+              }
+            },
+            "description": "Reference materials for implementation"
+          },
+          "acceptance": {
+            "type": "array",
+            "items": {"type": "string"},
+            "minItems": 2,
+            "maxItems": 4,
+            "description": "Verification criteria for task completion"
+          }
+        }
+      },
+      "description": "Structured task breakdown (3-10 tasks)"
+    },
+    "estimated_time": {
+      "type": "string",
+      "description": "Total estimated implementation time (e.g., '30 minutes', '2 hours')"
+    },
+    "recommended_execution": {
+      "type": "string",
+      "enum": ["Agent", "Codex"],
+      "description": "Recommended execution method based on complexity"
+    },
+    "complexity": {
+      "type": "string",
+      "enum": ["Low", "Medium", "High"],
+      "description": "Task complexity level"
+    },
+    "_metadata": {
+      "type": "object",
+      "required": ["timestamp", "source", "planning_mode"],
+      "properties": {
+        "timestamp": {
+          "type": "string",
+          "format": "date-time",
+          "description": "ISO 8601 timestamp of planning"
+        },
+        "source": {
+          "type": "string",
+          "enum": ["cli-lite-planning-agent", "direct-planning"],
+          "description": "Planning source"
+        },
+        "planning_mode": {
+          "type": "string",
+          "enum": ["direct", "agent-based"],
+          "description": "Planning execution mode"
+        },
+        "duration_seconds": {
+          "type": "integer",
+          "description": "Planning duration in seconds"
+        }
+      }
+    }
+  }
+}