claude-flow 2.0.0-alpha.60 → 2.0.0-alpha.62

package/src/cli/simple-commands/init/templates/CLAUDE.md

@@ -3,8 +3,9 @@
 ## 🚨 CRITICAL: PARALLEL EXECUTION AFTER SWARM INIT
 
 **MANDATORY RULE**: Once swarm is initialized with memory, ALL subsequent operations MUST be parallel:
+
 1. **TodoWrite** → Always batch 5-10+ todos in ONE call
-2. **Task spawning** → Spawn ALL agents in ONE message  
+2. **Task spawning** → Spawn ALL agents in ONE message
 3. **File operations** → Batch ALL reads/writes together
 4. **NEVER** operate sequentially after swarm init
 
@@ -13,6 +14,7 @@
 **ABSOLUTE RULE**: ALL operations MUST be concurrent/parallel in a single message:
 
 ### 🔴 MANDATORY CONCURRENT PATTERNS:
+
 1. **TodoWrite**: ALWAYS batch ALL todos in ONE call (5-10+ todos minimum)
 2. **Task tool**: ALWAYS spawn ALL agents in ONE message with full instructions
 3. **File operations**: ALWAYS batch ALL reads/writes/edits in ONE message
@@ -22,6 +24,7 @@
 ### ⚡ GOLDEN RULE: "1 MESSAGE = ALL RELATED OPERATIONS"
 
 **Examples of CORRECT concurrent execution:**
+
 ```javascript
 // ✅ CORRECT: Everything in ONE message
 [Single Message]:
@@ -40,6 +43,7 @@
 ```
 
 **Examples of WRONG sequential execution:**
+
 ```javascript
 // ❌ WRONG: Multiple messages (NEVER DO THIS)
 Message 1: TodoWrite { todos: [single todo] }
@@ -54,6 +58,7 @@ Message 6: Bash("npm install")
 ### 🎯 CONCURRENT EXECUTION CHECKLIST:
 
 Before sending ANY message, ask yourself:
+
 - ✅ Are ALL related TodoWrite operations batched together?
 - ✅ Are ALL Task spawning operations in ONE message?
 - ✅ Are ALL file operations (Read/Write/Edit) batched together?
@@ -69,6 +74,7 @@ If ANY answer is "No", you MUST combine operations into a single message!
 **ABSOLUTE RULE**: Claude Code performs ALL actual work:
 
 ### ✅ Claude Code ALWAYS Handles:
+
 - 🔧 **ALL file operations** (Read, Write, Edit, MultiEdit, Glob, Grep)
 - 💻 **ALL code generation** and programming tasks
 - 🖥️ **ALL bash commands** and system operations
@@ -81,6 +87,7 @@ If ANY answer is "No", you MUST combine operations into a single message!
 - 🔧 **ALL debugging** and troubleshooting
 
 ### 🧠 Claude Flow MCP Tools ONLY Handle:
+
 - 🎯 **Coordination only** - Planning Claude Code's actions
 - 💾 **Memory management** - Storing decisions and context
 - 🤖 **Neural features** - Learning from Claude Code's work
@@ -91,6 +98,7 @@ If ANY answer is "No", you MUST combine operations into a single message!
 ### 🚨 CRITICAL SEPARATION OF CONCERNS:
 
 **❌ MCP Tools NEVER:**
+
 - Write files or create content
 - Execute bash commands
 - Generate code
@@ -100,6 +108,7 @@ If ANY answer is "No", you MUST combine operations into a single message!
 - Do actual implementation work
 
 **✅ MCP Tools ONLY:**
+
 - Coordinate and plan
 - Store memory and context
 - Track performance
@@ -107,11 +116,13 @@ If ANY answer is "No", you MUST combine operations into a single message!
 - Provide intelligence insights
 
 ### ⚠️ Key Principle:
+
 **MCP tools coordinate, Claude Code executes.** Think of MCP tools as the "brain" that plans and coordinates, while Claude Code is the "hands" that do all the actual work.
 
 ### 🔄 WORKFLOW EXECUTION PATTERN:
 
 **✅ CORRECT Workflow:**
+
 1. **MCP**: `mcp__claude-flow__swarm_init` (coordination setup)
 2. **MCP**: `mcp__claude-flow__agent_spawn` (planning agents)
 3. **MCP**: `mcp__claude-flow__task_orchestrate` (task coordination)
@@ -121,6 +132,7 @@ If ANY answer is "No", you MUST combine operations into a single message!
 7. **MCP**: `mcp__claude-flow__memory_usage` (store results)
 
 **❌ WRONG Workflow:**
+
 1. **MCP**: `mcp__claude-flow__terminal_execute` (DON'T DO THIS)
 2. **MCP**: File creation via MCP (DON'T DO THIS)
 3. **MCP**: Code generation via MCP (DON'T DO THIS)
@@ -128,6 +140,7 @@ If ANY answer is "No", you MUST combine operations into a single message!
 5. **Claude Code**: Individual TodoWrite calls (DON'T DO THIS)
 
 ### 🚨 REMEMBER:
+
 - **MCP tools** = Coordination, planning, memory, intelligence
 - **Claude Code** = All actual execution, coding, file operations
 
@@ -150,6 +163,7 @@ If you need to do X operations, they should be in 1 message, not X messages
 ### 🚨 MANDATORY TODO AND TASK BATCHING
 
 **CRITICAL RULE FOR TODOS AND TASKS:**
+
 1. **TodoWrite** MUST ALWAYS include ALL todos in ONE call (5-10+ todos)
 2. **Task** tool calls MUST be batched - spawn multiple agents in ONE message
 3. **NEVER** update todos one by one - this breaks parallel coordination
@@ -158,6 +172,7 @@ If you need to do X operations, they should be in 1 message, not X messages
 ### 📦 BATCH TOOL EXAMPLES
 
 **✅ CORRECT - Everything in ONE Message:**
+
 ```javascript
 [Single Message with BatchTool]:
   // MCP coordination setup
@@ -167,22 +182,23 @@ If you need to do X operations, they should be in 1 message, not X messages
   mcp__claude-flow__agent_spawn { type: "analyst" }
   mcp__claude-flow__agent_spawn { type: "tester" }
   mcp__claude-flow__agent_spawn { type: "coordinator" }
-  
+
   // Claude Code execution - ALL in parallel
   Task("You are researcher agent. MUST coordinate via hooks...")
   Task("You are coder agent. MUST coordinate via hooks...")
   Task("You are analyst agent. MUST coordinate via hooks...")
   Task("You are tester agent. MUST coordinate via hooks...")
   TodoWrite { todos: [5-10 todos with all priorities and statuses] }
-  
+
   // File operations in parallel
   Bash "mkdir -p app/{src,tests,docs}"
-  Write "app/package.json" 
+  Write "app/package.json"
   Write "app/README.md"
   Write "app/src/index.js"
 ```
 
 **❌ WRONG - Multiple Messages (NEVER DO THIS):**
+
 ```javascript
 Message 1: mcp__claude-flow__swarm_init
 Message 2: Task("researcher agent")
@@ -196,6 +212,7 @@ Message 6: Write "package.json"
 ### 🎯 BATCH OPERATIONS BY TYPE
 
 **Todo and Task Operations (Single Message):**
+
 - **TodoWrite** → ALWAYS include 5-10+ todos in ONE call
 - **Task agents** → Spawn ALL agents with full instructions in ONE message
 - **Agent coordination** → ALL Task calls must include coordination hooks
@@ -203,16 +220,19 @@ Message 6: Write "package.json"
 - **NEVER** split todos or Task calls across messages!
 
 **File Operations (Single Message):**
+
 - Read 10 files? → One message with 10 Read calls
 - Write 5 files? → One message with 5 Write calls
 - Edit 1 file many times? → One MultiEdit call
 
 **Swarm Operations (Single Message):**
+
 - Need 8 agents? → One message with swarm_init + 8 agent_spawn calls
 - Multiple memories? → One message with all memory_usage calls
 - Task + monitoring? → One message with task_orchestrate + swarm_monitor
 
 **Command Operations (Single Message):**
+
 - Multiple directories? → One message with all mkdir commands
 - Install + test + lint? → One message with all npm commands
 - Git operations? → One message with all git commands
@@ -220,25 +240,30 @@ Message 6: Write "package.json"
 ## 🚀 Quick Setup (Stdio MCP - Recommended)
 
 ### 1. Add MCP Server (Stdio - No Port Needed)
+
 ```bash
 # Add Claude Flow MCP server to Claude Code using stdio
 claude mcp add claude-flow npx claude-flow@alpha mcp start
 ```
 
 ### 2. Use MCP Tools for Coordination in Claude Code
+
 Once configured, Claude Flow MCP tools enhance Claude Code's coordination:
 
 **Initialize a swarm:**
+
 - Use the `mcp__claude-flow__swarm_init` tool to set up coordination topology
 - Choose: mesh, hierarchical, ring, or star
 - This creates a coordination framework for Claude Code's work
 
 **Spawn agents:**
+
 - Use `mcp__claude-flow__agent_spawn` tool to create specialized coordinators
 - Agent types represent different thinking patterns, not actual coders
 - They help Claude Code approach problems from different angles
 
 **Orchestrate tasks:**
+
 - Use `mcp__claude-flow__task_orchestrate` tool to coordinate complex workflows
 - This breaks down tasks for Claude Code to execute systematically
 - The agents don't write code - they coordinate Claude Code's actions
@@ -246,11 +271,13 @@ Once configured, Claude Flow MCP tools enhance Claude Code's coordination:
 ## Available MCP Tools for Coordination
 
 ### Coordination Tools:
+
 - `mcp__claude-flow__swarm_init` - Set up coordination topology for Claude Code
 - `mcp__claude-flow__agent_spawn` - Create cognitive patterns to guide Claude Code
 - `mcp__claude-flow__task_orchestrate` - Break down and coordinate complex tasks
 
 ### Monitoring Tools:
+
 - `mcp__claude-flow__swarm_status` - Monitor coordination effectiveness
 - `mcp__claude-flow__agent_list` - View active cognitive patterns
 - `mcp__claude-flow__agent_metrics` - Track coordination performance
@@ -258,12 +285,14 @@ Once configured, Claude Flow MCP tools enhance Claude Code's coordination:
 - `mcp__claude-flow__task_results` - Review coordination outcomes
 
 ### Memory & Neural Tools:
+
 - `mcp__claude-flow__memory_usage` - Persistent memory across sessions
 - `mcp__claude-flow__neural_status` - Neural pattern effectiveness
 - `mcp__claude-flow__neural_train` - Improve coordination patterns
 - `mcp__claude-flow__neural_patterns` - Analyze thinking approaches
 
 ### GitHub Integration Tools (NEW!):
+
 - `mcp__claude-flow__github_swarm` - Create specialized GitHub management swarms
 - `mcp__claude-flow__repo_analyze` - Deep repository analysis with AI
 - `mcp__claude-flow__pr_enhance` - AI-powered pull request improvements
@@ -271,6 +300,7 @@ Once configured, Claude Flow MCP tools enhance Claude Code's coordination:
 - `mcp__claude-flow__code_review` - Automated code review with swarms
 
 ### System Tools:
+
 - `mcp__claude-flow__benchmark_run` - Measure coordination efficiency
 - `mcp__claude-flow__features_detect` - Available capabilities
 - `mcp__claude-flow__swarm_monitor` - Real-time coordination tracking
@@ -278,14 +308,17 @@ Once configured, Claude Flow MCP tools enhance Claude Code's coordination:
 ## Workflow Examples (Coordination-Focused)
 
 ### Research Coordination Example
+
 **Context:** Claude Code needs to research a complex topic systematically
 
 **Step 1:** Set up research coordination
+
 - Tool: `mcp__claude-flow__swarm_init`
 - Parameters: `{"topology": "mesh", "maxAgents": 5, "strategy": "balanced"}`
 - Result: Creates a mesh topology for comprehensive exploration
 
 **Step 2:** Define research perspectives
+
 - Tool: `mcp__claude-flow__agent_spawn`
 - Parameters: `{"type": "researcher", "name": "Literature Review"}`
 - Tool: `mcp__claude-flow__agent_spawn`
@@ -293,11 +326,13 @@ Once configured, Claude Flow MCP tools enhance Claude Code's coordination:
 - Result: Different cognitive patterns for Claude Code to use
 
 **Step 3:** Coordinate research execution
+
 - Tool: `mcp__claude-flow__task_orchestrate`
 - Parameters: `{"task": "Research neural architecture search papers", "strategy": "adaptive"}`
 - Result: Claude Code systematically searches, reads, and analyzes papers
 
 **What Actually Happens:**
+
 1. The swarm sets up a coordination framework
 2. Each agent MUST use Claude Flow hooks for coordination:
    - `npx claude-flow@alpha hooks pre-task` before starting
@@ -308,24 +343,29 @@ Once configured, Claude Flow MCP tools enhance Claude Code's coordination:
 5. Results are synthesized by Claude Code with full coordination history
 
 ### Development Coordination Example
+
 **Context:** Claude Code needs to build a complex system with multiple components
 
 **Step 1:** Set up development coordination
+
 - Tool: `mcp__claude-flow__swarm_init`
 - Parameters: `{"topology": "hierarchical", "maxAgents": 8, "strategy": "specialized"}`
 - Result: Hierarchical structure for organized development
 
 **Step 2:** Define development perspectives
+
 - Tool: `mcp__claude-flow__agent_spawn`
 - Parameters: `{"type": "architect", "name": "System Design"}`
 - Result: Architectural thinking pattern for Claude Code
 
 **Step 3:** Coordinate implementation
+
 - Tool: `mcp__claude-flow__task_orchestrate`
 - Parameters: `{"task": "Implement user authentication with JWT", "strategy": "parallel"}`
 - Result: Claude Code implements features using its native tools
 
 **What Actually Happens:**
+
 1. The swarm creates a development coordination plan
 2. Each agent coordinates using mandatory hooks:
    - Pre-task hooks for context loading
@@ -336,19 +376,23 @@ Once configured, Claude Flow MCP tools enhance Claude Code's coordination:
 5. All code is written by Claude Code with full coordination
 
 ### GitHub Repository Management Example (NEW!)
+
 **Context:** Claude Code needs to manage a complex GitHub repository
 
 **Step 1:** Initialize GitHub swarm
+
 - Tool: `mcp__claude-flow__github_swarm`
 - Parameters: `{"repository": "owner/repo", "agents": 5, "focus": "maintenance"}`
 - Result: Specialized swarm for repository management
 
 **Step 2:** Analyze repository health
+
 - Tool: `mcp__claude-flow__repo_analyze`
 - Parameters: `{"deep": true, "include": ["issues", "prs", "code"]}`
 - Result: Comprehensive repository analysis
 
 **Step 3:** Enhance pull requests
+
 - Tool: `mcp__claude-flow__pr_enhance`
 - Parameters: `{"pr_number": 123, "add_tests": true, "improve_docs": true}`
 - Result: AI-powered PR improvements
@@ -356,6 +400,7 @@ Once configured, Claude Flow MCP tools enhance Claude Code's coordination:
 ## Best Practices for Coordination
 
 ### ✅ DO:
+
 - Use MCP tools to coordinate Claude Code's approach to complex tasks
 - Let the swarm break down problems into manageable pieces
 - Use memory tools to maintain context across sessions
@@ -364,6 +409,7 @@ Once configured, Claude Flow MCP tools enhance Claude Code's coordination:
 - Leverage GitHub tools for repository management
 
 ### ❌ DON'T:
+
 - Expect agents to write code (Claude Code does all implementation)
 - Use MCP tools for file operations (use Claude Code's native tools)
 - Try to make agents execute bash commands (Claude Code handles this)
@@ -372,6 +418,7 @@ Once configured, Claude Flow MCP tools enhance Claude Code's coordination:
 ## Memory and Persistence
 
 The swarm provides persistent memory that helps Claude Code:
+
 - Remember project context across sessions
 - Track decisions and rationale
 - Maintain consistency in large projects
@@ -381,6 +428,7 @@ The swarm provides persistent memory that helps Claude Code:
 ## Performance Benefits
 
 When using Claude Flow coordination with Claude Code:
+
 - **84.8% SWE-Bench solve rate** - Better problem-solving through coordination
 - **32.3% token reduction** - Efficient task breakdown reduces redundancy
 - **2.8-4.4x speed improvement** - Parallel coordination strategies
@@ -392,6 +440,7 @@ When using Claude Flow coordination with Claude Code:
 Claude Flow includes powerful hooks that automate coordination:
 
 ### Pre-Operation Hooks
+
 - **Auto-assign agents** before file edits based on file type
 - **Validate commands** before execution for safety
 - **Prepare resources** automatically for complex operations
@@ -399,7 +448,8 @@ Claude Flow includes powerful hooks that automate coordination:
 - **Cache searches** for improved performance
 - **GitHub context** loading for repository operations
 
-### Post-Operation Hooks  
+### Post-Operation Hooks
+
 - **Auto-format code** using language-specific formatters
 - **Train neural patterns** from successful operations
 - **Update memory** with operation context
@@ -408,6 +458,7 @@ Claude Flow includes powerful hooks that automate coordination:
 - **Sync GitHub** state for consistency
 
 ### Session Management
+
 - **Generate summaries** at session end
 - **Persist state** across Claude Code sessions
 - **Track metrics** for continuous improvement
@@ -415,8 +466,9 @@ Claude Flow includes powerful hooks that automate coordination:
 - **Export workflows** for reuse
 
 ### Advanced Features (v2.0.0!)
+
 - **🚀 Automatic Topology Selection** - Optimal swarm structure for each task
-- **⚡ Parallel Execution** - 2.8-4.4x speed improvements  
+- **⚡ Parallel Execution** - 2.8-4.4x speed improvements
 - **🧠 Neural Training** - Continuous learning from operations
 - **📊 Bottleneck Analysis** - Real-time performance optimization
 - **🤖 Smart Auto-Spawning** - Zero manual agent management
@@ -425,7 +477,9 @@ Claude Flow includes powerful hooks that automate coordination:
 - **🔗 GitHub Integration** - Repository-aware swarms
 
 ### Configuration
+
 Hooks are pre-configured in `.claude/settings.json`. Key features:
+
 - Automatic agent assignment for different file types
 - Code formatting on save
 - Neural pattern learning from edits
@@ -453,6 +507,7 @@ See `.claude/commands/` for detailed documentation on all features.
 ### 🚨 CRITICAL INSTRUCTION: You are the SWARM ORCHESTRATOR
 
 **MANDATORY**: When using swarms, you MUST:
+
 1. **SPAWN ALL AGENTS IN ONE BATCH** - Use multiple tool calls in a SINGLE message
 2. **EXECUTE TASKS IN PARALLEL** - Never wait for one task before starting another
 3. **USE BATCHTOOL FOR EVERYTHING** - Multiple operations = Single message with multiple tools
@@ -461,10 +516,11 @@ See `.claude/commands/` for detailed documentation on all features.
 ### 🎯 AGENT COUNT CONFIGURATION
 
 **CRITICAL: Dynamic Agent Count Rules**
+
 1. **Check CLI Arguments First**: If user runs `npx claude-flow@alpha --agents 5`, use 5 agents
 2. **Auto-Decide if No Args**: Without CLI args, analyze task complexity:
    - Simple tasks (1-3 components): 3-4 agents
-   - Medium tasks (4-6 components): 5-7 agents  
+   - Medium tasks (4-6 components): 5-7 agents
    - Complex tasks (7+ components): 8-12 agents
 3. **Agent Type Distribution**: Balance agent types based on task:
    - Always include 1 coordinator
@@ -473,16 +529,17 @@ See `.claude/commands/` for detailed documentation on all features.
    - For quality tasks: more testers/reviewers
 
 **Example Auto-Decision Logic:**
+
 ```javascript
 // If CLI args provided: npx claude-flow@alpha --agents 6
-maxAgents = CLI_ARGS.agents || determineAgentCount(task)
+maxAgents = CLI_ARGS.agents || determineAgentCount(task);
 
 function determineAgentCount(task) {
   // Analyze task complexity
-  if (task.includes(['API', 'database', 'auth', 'tests'])) return 8
-  if (task.includes(['frontend', 'backend'])) return 6
-  if (task.includes(['simple', 'script'])) return 3
-  return 5 // default
+  if (task.includes(['API', 'database', 'auth', 'tests'])) return 8;
+  if (task.includes(['frontend', 'backend'])) return 6;
+  if (task.includes(['simple', 'script'])) return 3;
+  return 5; // default
 }
 ```
 
@@ -493,6 +550,7 @@ function determineAgentCount(task) {
 When you spawn an agent using the Task tool, that agent MUST:
 
 **1️⃣ BEFORE Starting Work:**
+
 ```bash
 # Check previous work and load context
 npx claude-flow@alpha hooks pre-task --description "[agent task]" --auto-spawn-agents false
@@ -500,6 +558,7 @@ npx claude-flow@alpha hooks session-restore --session-id "swarm-[id]" --load-mem
 ```
 
 **2️⃣ DURING Work (After EVERY Major Step):**
+
 ```bash
 # Store progress in memory after each file operation
 npx claude-flow@alpha hooks post-edit --file "[filepath]" --memory-key "swarm/[agent]/[step]"
@@ -512,6 +571,7 @@ npx claude-flow@alpha hooks pre-search --query "[what to check]" --cache-results
 ```
 
 **3️⃣ AFTER Completing Work:**
+
 ```bash
 # Save all results and learnings
 npx claude-flow@alpha hooks post-task --task-id "[task]" --analyze-performance true
@@ -539,6 +599,7 @@ REMEMBER: Coordinate with other agents by checking memory BEFORE making decision
 ### ⚡ PARALLEL EXECUTION IS MANDATORY
 
 **THIS IS WRONG ❌ (Sequential - NEVER DO THIS):**
+
 ```
 Message 1: Initialize swarm
 Message 2: Spawn agent 1
@@ -549,12 +610,13 @@ Message 6: TodoWrite (another single todo)
 ```
 
 **THIS IS CORRECT ✅ (Parallel - ALWAYS DO THIS):**
+
 ```
 Message 1: [BatchTool]
   // MCP coordination setup
   - mcp__claude-flow__swarm_init
   - mcp__claude-flow__agent_spawn (researcher)
-  - mcp__claude-flow__agent_spawn (coder)  
+  - mcp__claude-flow__agent_spawn (coder)
   - mcp__claude-flow__agent_spawn (analyst)
   - mcp__claude-flow__agent_spawn (tester)
   - mcp__claude-flow__agent_spawn (coordinator)
@@ -565,7 +627,7 @@ Message 2: [BatchTool - Claude Code execution]
   - Task("You are coder agent. MANDATORY: Run hooks pre-task, post-edit, post-task. Task: Implement REST endpoints")
   - Task("You are analyst agent. MANDATORY: Run hooks pre-task, post-edit, post-task. Task: Analyze performance")
   - Task("You are tester agent. MANDATORY: Run hooks pre-task, post-edit, post-task. Task: Write comprehensive tests")
-  
+
   // TodoWrite with ALL todos batched
   - TodoWrite { todos: [
       {id: "research", content: "Research API patterns", status: "in_progress", priority: "high"},
@@ -575,7 +637,7 @@ Message 2: [BatchTool - Claude Code execution]
       {id: "docs", content: "Create API documentation", status: "pending", priority: "low"},
       {id: "deploy", content: "Setup deployment", status: "pending", priority: "medium"}
     ]}
-  
+
   // File operations in parallel
   - Write "api/package.json"
   - Write "api/server.js"
@@ -591,12 +653,12 @@ When given ANY complex task with swarms:
 STEP 1: IMMEDIATE PARALLEL SPAWN (Single Message!)
 [BatchTool]:
   // IMPORTANT: Check CLI args for agent count, otherwise auto-decide based on task complexity
-  - mcp__claude-flow__swarm_init { 
-      topology: "hierarchical", 
+  - mcp__claude-flow__swarm_init {
+      topology: "hierarchical",
       maxAgents: CLI_ARGS.agents || AUTO_DECIDE(task_complexity), // Use CLI args or auto-decide
-      strategy: "parallel" 
+      strategy: "parallel"
     }
-  
+
   // Spawn agents based on maxAgents count and task requirements
   // If CLI specifies 3 agents, spawn 3. If no args, auto-decide optimal count (3-12)
   - mcp__claude-flow__agent_spawn { type: "architect", name: "System Designer" }
@@ -663,7 +725,7 @@ Dependencies: ↳ X deps | Actionable: ▶
   mcp__claude-flow__agent_spawn { type: "analyst", name: "DB Designer" }
   mcp__claude-flow__agent_spawn { type: "tester", name: "Test Engineer" }
   mcp__claude-flow__agent_spawn { type: "coordinator", name: "Lead" }
-  
+
   // Update ALL todos at once - NEVER split todos!
   TodoWrite { todos: [
     { id: "design", content: "Design API architecture", status: "in_progress", priority: "high" },
@@ -675,10 +737,10 @@ Dependencies: ↳ X deps | Actionable: ▶
     { id: "deploy", content: "Setup deployment pipeline", status: "pending", priority: "medium" },
     { id: "monitor", content: "Add monitoring", status: "pending", priority: "medium" }
   ]}
-  
+
   // Start orchestration
   mcp__claude-flow__task_orchestrate { task: "Build REST API", strategy: "parallel" }
-  
+
   // Store initial memory
   mcp__claude-flow__memory_usage { action: "store", key: "project/init", value: { started: Date.now() } }
 
@@ -687,7 +749,7 @@ Dependencies: ↳ X deps | Actionable: ▶
   Bash("mkdir -p test-app/{src,tests,docs,config}")
   Bash("mkdir -p test-app/src/{models,routes,middleware,services}")
   Bash("mkdir -p test-app/tests/{unit,integration}")
-  
+
   // Write ALL base files at once
   Write("test-app/package.json", packageJsonContent)
   Write("test-app/.env.example", envContent)
@@ -700,7 +762,7 @@ Dependencies: ↳ X deps | Actionable: ▶
   Read("test-app/package.json")
   Read("test-app/src/server.js")
   Read("test-app/.env.example")
-  
+
   // Run multiple commands
   Bash("cd test-app && npm install")
   Bash("cd test-app && npm run lint")
@@ -708,6 +770,7 @@ Dependencies: ↳ X deps | Actionable: ▶
 ```
 
 ### 🚫 NEVER DO THIS (Sequential = WRONG):
+
 ```javascript
 // ❌ WRONG: Multiple messages, one operation each
 Message 1: mcp__claude-flow__swarm_init
@@ -751,7 +814,7 @@ mcp__claude-flow__memory_usage
 1. **Batch Everything**: Never operate on single files when multiple are needed
 2. **Parallel First**: Always think "what can run simultaneously?"
 3. **Memory is Key**: Use memory for ALL cross-agent coordination
-4. **Monitor Progress**: Use mcp__claude-flow__swarm_monitor for real-time tracking
+4. **Monitor Progress**: Use mcp**claude-flow**swarm_monitor for real-time tracking
 5. **Auto-Optimize**: Let hooks handle topology and agent selection
 
 ### 🎨 VISUAL SWARM STATUS
@@ -780,18 +843,21 @@ Agent Activity:
 ### 🚨 MANDATORY BATCHING RULES FOR TODOS AND TASKS
 
 **TodoWrite Tool Requirements:**
+
 1. **ALWAYS** include 5-10+ todos in a SINGLE TodoWrite call
 2. **NEVER** call TodoWrite multiple times in sequence
 3. **BATCH** all todo updates together - status changes, new todos, completions
 4. **INCLUDE** all priority levels (high, medium, low) in one call
 
 **Task Tool Requirements:**
+
 1. **SPAWN** all agents using Task tool in ONE message
 2. **NEVER** spawn agents one by one across multiple messages
 3. **INCLUDE** full task descriptions and coordination instructions
 4. **BATCH** related Task calls together for parallel execution
 
 **Example of CORRECT TodoWrite usage:**
+
 ```javascript
 // ✅ CORRECT - All todos in ONE call
 TodoWrite { todos: [
@@ -809,6 +875,7 @@ TodoWrite { todos: [
 ```
 
 **Example of WRONG TodoWrite usage:**
+
 ```javascript
 // ❌ WRONG - Multiple TodoWrite calls
 Message 1: TodoWrite { todos: [{ id: "1", content: "Task 1", ... }] }
@@ -820,6 +887,7 @@ Message 3: TodoWrite { todos: [{ id: "3", content: "Task 3", ... }] }
 ## Claude Flow v2.0.0 Features
 
 Claude Flow extends the base coordination with:
+
 - **🔗 GitHub Integration** - Deep repository management
 - **🎯 Project Templates** - Quick-start for common projects
 - **📊 Advanced Analytics** - Detailed performance insights
@@ -835,4 +903,4 @@ Claude Flow extends the base coordination with:
 
 ---
 
-Remember: **Claude Flow coordinates, Claude Code creates!** Start with `mcp__claude-flow__swarm_init` to enhance your development workflow.
+Remember: **Claude Flow coordinates, Claude Code creates!** Start with `mcp__claude-flow__swarm_init` to enhance your development workflow.

package/src/cli/simple-commands/init/templates/claude-flow-universal

@@ -10,7 +10,7 @@
   const { spawn } = await import('child_process');
   const { resolve } = await import('path');
   const { fileURLToPath } = await import('url');
-  
+
   // Detect if we're running in ES module context
   let __dirname;
   try {
@@ -39,7 +39,7 @@
         }
       } catch {}
     },
-    
+
     // 2. Parent node_modules (monorepo)
     async () => {
       try {
@@ -50,11 +50,13 @@
         }
       } catch {}
     },
-    
+
     // 3. NPX with latest alpha version (prioritized over global)
     async () => {
-      return spawn('npx', ['claude-flow@2.0.0-alpha.27', ...process.argv.slice(2)], { stdio: 'inherit' });
-    }
+      return spawn('npx', ['claude-flow@2.0.0-alpha.27', ...process.argv.slice(2)], {
+        stdio: 'inherit',
+      });
+    },
   ];
 
   // Try each strategy
@@ -73,7 +75,7 @@
       }
     } catch {}
   }
-  
+
   console.error('Could not find claude-flow. Please install it with: npm install claude-flow');
   process.exit(1);
-})();
+})();

package/src/cli/simple-commands/init/templates/claude-md.js

@@ -646,4 +646,4 @@ NEVER create files unless they're absolutely necessary for achieving your goal.
 ALWAYS prefer editing an existing file to creating a new one.
 NEVER proactively create documentation files (*.md) or README files. Only create documentation files if explicitly requested by the User.
 `;
-}
+}