ccsetup 1.0.8 → 1.1.0

package/README.md

@@ -5,7 +5,7 @@
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![npm downloads](https://img.shields.io/npm/dm/ccsetup.svg)](https://www.npmjs.com/package/ccsetup)
 
-Quick setup for Claude Code projects with built-in agents, ticket system, planning tools and agent orchestration workflow.
+Quick setup for Claude Code projects with built-in 50+ agents, ticket system, planning tools and agent orchestration workflow.
 
 ## Installation
 
@@ -32,15 +32,17 @@ Options:
   --agents        Interactive agent selection mode
   --all-agents    Include all agents without prompting
   --no-agents     Skip agent selection entirely
+  --browse-agents Copy all agents to /agents folder for browsing
   --help, -h      Show help message
 
 Examples:
-  ccsetup                    # Create in current directory
-  ccsetup my-project         # Create in new directory
-  ccsetup . --force          # Overwrite files in current directory
-  ccsetup my-app --dry-run   # Preview changes without creating files
-  ccsetup --agents           # Interactive agent selection only
-  ccsetup my-app --all-agents # Include all agents automatically
+  ccsetup                      # Create in current directory
+  ccsetup my-project           # Create in new directory
+  ccsetup . --force            # Overwrite files in current directory
+  ccsetup my-app --dry-run     # Preview changes without creating files
+  ccsetup --agents             # Interactive agent selection only
+  ccsetup my-app --all-agents  # Include all agents automatically
+  ccsetup --browse-agents      # Copy all agents for manual selection
 ```
 
 ## What's Included
@@ -56,6 +58,7 @@ The boilerplate template creates:
 ## Key Features
 
 - 🎯 **Interactive Agent Selection** - Choose which agents to include during setup
+- 📚 **Browse Mode** - Copy all 50+ agents to explore and manually select later
 - 🔄 **Agent Orchestration Workflows** - Pre-defined workflows that automatically coordinate multiple agents for complex tasks
 - 🔒 **Smart Conflict Resolution** - Handle existing files with skip/rename/overwrite options
 - 📁 **.claude Directory Support** - Automatic creation of Claude Code directory structure
@@ -97,22 +100,45 @@ When running in the current directory (`npx ccsetup .`), it will check for Claud
 
 ## Using Agents
 
-The boilerplate includes several specialized agents in the `agents/` directory:
+The boilerplate includes 50+ specialized agents covering all aspects of development:
 
+### Core Development Agents
 - **planner.md** - Strategic planning and task breakdown
 - **coder.md** - Implementation and development
 - **checker.md** - Testing and quality assurance
 - **researcher.md** - Research and information gathering
-- **blockchain.md** - Web3 and smart contract development
-- **frontend.md** - UI/UX and frontend development
-- **backend.md** - API design and server-side development
-- **shadcn.md** - shadcn/ui component development
+
+### Language Specialists
+- **python-pro.md**, **golang-pro.md**, **rust-pro.md**, **javascript-pro.md**, **c-pro.md**, **cpp-pro.md**, **sql-pro.md**
+
+### Infrastructure & Operations
+- **devops-troubleshooter.md**, **cloud-architect.md**, **terraform-specialist.md**, **database-admin.md**, **network-engineer.md**
+
+### Quality & Security
+- **code-reviewer.md**, **security-auditor.md**, **test-automator.md**, **performance-engineer.md**
+
+### And Many More!
+Over 50 specialized agents for frontend, backend, blockchain, ML/AI, business analysis, and more!
+
+📖 **[View all agents with detailed descriptions →](https://github.com/MrMarciaOng/ccsetup/blob/main/template/agents/README.md)**
 
 ### Interactive Agent Selection
 
-During setup, ccsetup will prompt you to select which agents to include:
+During setup, ccsetup will prompt you to either:
+
+1. **Browse Mode** - Get all 50+ agents to explore later
+2. **Select Specific Agents** - Choose from curated list
 
 ```bash
+🤖 How would you like to set up agents for your Claude Code project?
+
+Use arrow keys to navigate, Enter to select
+
+> Browse Mode - Copy all 50+ agents to /agents folder (explore later)
+  Select Agents - Choose specific agents to include now
+  Skip - Don't include any agents
+
+# If you choose "Select Agents":
 🤖 Select agents to include in your Claude Code project
 
 Use arrow keys to navigate, space to select/deselect, 'a' to toggle all
@@ -145,6 +171,43 @@ npx ccsetup my-project --no-agents
 npx ccsetup --agents
 ```
 
+### Browse Mode - New Feature! 📚
+
+With 50+ specialized agents available, browse mode lets you explore all agents at your leisure:
+
+```bash
+# Copy all agents to /agents folder for browsing
+npx ccsetup my-project --browse-agents
+```
+
+In browse mode:
+- All 50+ agents are copied to your project's `/agents` folder
+- You can read through each agent to understand their capabilities
+- Manually copy the ones you want to `~/.claude/agents` when ready
+- No overwhelming selection process during setup!
+
+Example workflow:
+```bash
+# 1. Create project with browse mode
+npx ccsetup my-project --browse-agents
+
+# 2. Explore agents
+cd my-project/agents
+ls  # See all available agents
+
+# 3. Read agent descriptions
+cat code-reviewer.md
+
+# 4. Copy desired agents to activate them
+cp code-reviewer.md ~/.claude/agents/
+cp python-pro.md ~/.claude/agents/
+```
+
+This approach is perfect when you:
+- Want to explore all available agents
+- Prefer to choose agents based on your project needs as they arise
+- Don't want to be overwhelmed with 50+ choices during setup
+
 ### Conflict Resolution
 
 When existing files are detected, ccsetup offers smart conflict resolution:
@@ -313,7 +376,7 @@ After setting up your project with `ccsetup`:
 
 ### Core Features
 - ✅ Pre-configured project structure for Claude Code
-- 🤖 Multiple specialized agents for different tasks
+- 🤖 50+ specialized agents from the [wshobson/agents](https://github.com/wshobson/agents) collection - [view all →](https://github.com/MrMarciaOng/ccsetup/blob/main/template/agents/README.md)
 - 🎫 Built-in ticket and planning system
 - 📋 Ready-to-use boilerplate with best practices
 - 📁 Automatic .claude directory integration
@@ -340,6 +403,8 @@ The template includes `docs/agent-orchestration.md` which defines workflows for:
 
 Born from our discussions in TechOverflow with [vichannnnn](https://github.com/vichannnnn) and [nasdin](https://github.com/nasdin)
 
+The 44 specialized agents collection is from [wshobson/agents](https://github.com/wshobson/agents) - an amazing collection of Claude Code subagents for every development need!
+
 ## License
 
 MIT

package/bin/create-project.js

@@ -12,7 +12,8 @@ const flags = {
   help: false,
   allAgents: false,
   noAgents: false,
-  agents: false
+  agents: false,
+  browseAgents: false
 };
 
 let projectName = '.';
@@ -32,6 +33,8 @@ for (let i = 0; i < args.length; i++) {
     flags.noAgents = true;
   } else if (arg === '--agents') {
     flags.agents = true;
+  } else if (arg === '--browse-agents') {
+    flags.browseAgents = true;
   } else if (!arg.startsWith('-')) {
     projectName = arg;
   }
@@ -48,15 +51,17 @@ Options:
   --agents        Interactive agent selection mode
   --all-agents    Include all agents without prompting
   --no-agents     Skip agent selection entirely
+  --browse-agents Copy all agents to /agents folder for browsing
   --help, -h      Show this help message
 
 Examples:
-  ccsetup                    # Create in current directory
-  ccsetup my-project         # Create in new directory
-  ccsetup . --force          # Overwrite files in current directory
-  ccsetup my-app --dry-run   # Preview changes without creating files
-  ccsetup --agents           # Interactive agent selection only
-  ccsetup my-app --all-agents # Include all agents automatically
+  ccsetup                      # Create in current directory
+  ccsetup my-project           # Create in new directory
+  ccsetup . --force            # Overwrite files in current directory
+  ccsetup my-app --dry-run     # Preview changes without creating files
+  ccsetup --agents             # Interactive agent selection only
+  ccsetup my-app --all-agents  # Include all agents automatically
+  ccsetup --browse-agents      # Copy all agents for manual selection
 `);
   process.exit(0);
 }
@@ -83,6 +88,11 @@ if (flags.allAgents && flags.noAgents) {
   process.exit(1);
 }
 
+if (flags.browseAgents && (flags.allAgents || flags.noAgents || flags.agents)) {
+  console.error('Error: --browse-agents cannot be used with other agent flags');
+  process.exit(1);
+}
+
 // Validate the project name
 if (projectName !== '.') {
   try {
@@ -658,19 +668,60 @@ async function main() {
   if (flags.noAgents) {
     selectedAgentFiles = [];
     console.log('\n⏭️  Skipping agent selection (--no-agents flag)');
+  } else if (flags.browseAgents) {
+    selectedAgentFiles = [];
+    console.log('\n📚 Browse mode enabled - all agents will be copied to /agents folder');
+    console.log('   You can manually copy desired agents to ~/.claude/agents later');
   } else if (flags.allAgents) {
     selectedAgentFiles = availableAgents.map(a => a.file).filter(validateAgentFile);
     console.log(`\n✅ Including all ${selectedAgentFiles.length} agents (--all-agents flag)`);
   } else if (!flags.dryRun) {
+    // Interactive mode selection
+    console.log('\n🤖 How would you like to set up agents for your Claude Code project?\n');
+    console.log('Use arrow keys to navigate, Enter to select\n');
+    
     // Close readline interface before using inquirer
     if (rl) {
       rl.close();
       rl = null;
     }
     
-    // Interactive selection
-    selectedAgentFiles = await selectAgents(availableAgents);
-    console.log(`\n✅ Selected ${selectedAgentFiles.length} agent${selectedAgentFiles.length === 1 ? '' : 's'}`);
+    // Import select for mode selection
+    const selectModule = await import('@inquirer/select');
+    const select = selectModule.default;
+    
+    const agentMode = await select({
+      message: 'Choose your setup mode:',
+      choices: [
+        {
+          name: 'Browse Mode - Copy all 50+ agents to /agents folder (explore later)',
+          value: 'browse'
+        },
+        {
+          name: 'Select Agents - Choose specific agents to include now',
+          value: 'select'
+        },
+        {
+          name: 'Skip - Don\'t include any agents',
+          value: 'skip'
+        }
+      ]
+    });
+    
+    if (agentMode === 'browse') {
+      flags.browseAgents = true;
+      selectedAgentFiles = [];
+      console.log('\n📚 Browse mode selected - all agents will be copied to /agents folder');
+      console.log('   You can manually copy desired agents to ~/.claude/agents later');
+    } else if (agentMode === 'skip') {
+      flags.noAgents = true;
+      selectedAgentFiles = [];
+      console.log('\n⏭️  Skipping agent selection');
+    } else if (agentMode === 'select') {
+      // Interactive selection
+      selectedAgentFiles = await selectAgents(availableAgents);
+      console.log(`\n✅ Selected ${selectedAgentFiles.length} agent${selectedAgentFiles.length === 1 ? '' : 's'}`);
+    }
     
     // Recreate readline interface after agent selection
     if (!flags.force && !flags.dryRun) {
@@ -681,7 +732,8 @@ async function main() {
     }
   } else {
     // In dry-run mode, show what would happen
-    console.log(`\nWould prompt for agent selection from ${availableAgents.length} available agents`);
+    console.log(`\nWould prompt for agent selection mode`);
+    console.log(`Would then prompt for agent selection from ${availableAgents.length} available agents`);
     selectedAgentFiles = availableAgents.map(a => a.file).filter(validateAgentFile); // Include all for scanning purposes
   }
 
@@ -724,8 +776,13 @@ async function main() {
             dirConflicts.push(relativePath || '.');
           }
           
-          // Add selected agent files
-          for (const agentFile of selectedAgentFiles) {
+          // In browse mode, add ALL agent files
+          const agentFilesToProcess = flags.browseAgents 
+            ? availableAgents.map(a => a.file).filter(validateAgentFile)
+            : selectedAgentFiles;
+          
+          // Add agent files
+          for (const agentFile of agentFilesToProcess) {
             // Additional validation before processing
             if (!validateAgentFile(agentFile)) {
               console.warn(`⚠️  Skipping invalid agent file: ${agentFile}`);
@@ -1014,7 +1071,13 @@ async function main() {
     if (renamedCount > 0) console.log(`  📄 ${renamedCount} template files ${flags.dryRun ? 'would be' : ''} saved with -ccsetup suffix`);
     if (overwrittenCount > 0) console.log(`  ♻️  ${overwrittenCount} files ${flags.dryRun ? 'would be' : ''} replaced with template versions`);
     if (!flags.noAgents && !flags.dryRun) {
-      console.log(`  🤖 ${selectedAgentFiles.length} agent${selectedAgentFiles.length === 1 ? '' : 's'} ${flags.dryRun ? 'would be' : ''} included in /agents`);
+      if (flags.browseAgents) {
+        const agentCount = availableAgents.length;
+        console.log(`  📚 ${agentCount} agent${agentCount === 1 ? '' : 's'} ${flags.dryRun ? 'would be' : ''} copied to /agents for browsing`);
+      } else if (selectedAgentFiles.length > 0) {
+        console.log(`  🤖 ${selectedAgentFiles.length} agent${selectedAgentFiles.length === 1 ? '' : 's'} ${flags.dryRun ? 'would be' : ''} included in /agents`);
+        console.log(`  📝 Remember to update agent-orchestration.md with workflows for your agents`);
+      }
     }
     if (claudeInitResult && claudeInitResult.createdItems.length > 0) {
       console.log(`  📁 ${claudeInitResult.createdItems.length} items created in .claude directory`);
@@ -1034,7 +1097,17 @@ async function main() {
     }
     console.log('  1. Edit CLAUDE.md to add your project-specific instructions');
     console.log('  2. Update docs/ROADMAP.md with your project goals');
-    console.log('  3. Start creating tickets in the tickets/ directory');
+    console.log('  3. Update docs/agent-orchestration.md to define agent workflows');
+    console.log('  4. Start creating tickets in the tickets/ directory');
+    
+    if (flags.browseAgents) {
+      console.log('\n📚 Agent Browse Mode:');
+      console.log('  - All available agents have been copied to the /agents folder');
+      console.log('  - Browse through them to understand their capabilities');
+      console.log('  - Copy desired agents to ~/.claude/agents to activate them');
+      console.log('  - Example: cp agents/code-reviewer.md ~/.claude/agents/');
+      console.log('  - Remember to update agent-orchestration.md with your custom workflows');
+    }
     
     if (renamedCount > 0) {
       console.log('\n💡 Tip: Review the -ccsetup files to see template examples');

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "ccsetup",
-  "version": "1.0.8",
-  "description": "Boilerplate for Claude Code projects with agents, tickets, plans and agent orchestration workflow",
+  "version": "1.1.0",
+  "description": "Boilerplate for Claude Code projects with 50+ agents, tickets, plans, agent orchestration, and browse mode",
   "bin": {
     "ccsetup": "bin/create-project.js"
   },
@@ -33,7 +33,8 @@
     "node": ">=14.0.0"
   },
   "dependencies": {
-    "@inquirer/checkbox": "^4.0.4"
+    "@inquirer/checkbox": "^4.0.4",
+    "@inquirer/select": "^4.0.4"
   },
   "devDependencies": {
     "jest": "^30.0.5"

package/template/CLAUDE.md

@@ -68,6 +68,14 @@ After adding the agents you want to in `./claude/agents` folder, setup the workf
 
 See @tickets/README.md for ticket format and management approach
 
+### Ticket Management
+- **Ticket List**: Maintain @tickets/ticket-list.md as a centralized index of all tickets
+- **Update ticket-list.md** whenever you:
+  - Create a new ticket (add to appropriate priority section)
+  - Change ticket status (update emoji and move if completed)
+  - Complete a ticket (move to completed section with date)
+- **Status Emojis**: 🔴 Todo | 🟡 In Progress | 🟢 Done | 🔵 Blocked | ⚫ Cancelled
+
 ## Plans
 
 See @plans/README.md for planning documents and architectural decisions
@@ -87,6 +95,7 @@ Before starting any task:
 3. **Create planning documents**: Before implementing any code or features, create a markdown file documenting the approach
 4. **Use plans directory**: When discussing ideas or next steps, create timestamped files in the plans directory (e.g., `plans/next-steps-YYYY-MM-DD-HH-MM-SS.md`) to maintain a record of decisions
 5. **No code comments**: Never add comments to any code you write - code should be self-documenting
+6. **Maintain ticket list**: Always update @tickets/ticket-list.md when creating, updating, or completing tickets to maintain a clear project overview
 
 ## Additional Notes
 

package/template/agents/README.md

@@ -1,35 +1,189 @@
-# Agents
+# Agents Directory
 
-This directory contains custom agents for specialized tasks.
+This directory contains specialized AI agents for Claude Code, designed to enhance development workflows with domain-specific expertise.
 
-## Overview
-Agents are specialized prompts or tools that help Claude perform specific tasks more effectively.
+## Credits
 
-## Creating a New Agent
-1. Create a new markdown file in this directory
-2. Name it descriptively (e.g., `code-reviewer.md`, `test-generator.md`)
-3. Define the agent's purpose, capabilities, and instructions
+This collection includes:
+- **8 original agents** created for ccsetup
+- **44 specialized agents** from [wshobson/agents](https://github.com/wshobson/agents) - an amazing collection of Claude Code subagents
 
-## Example Agent Structure
+## Available Agents (52 total)
+
+### Original ccsetup Agents
+These 8 agents were created specifically for the ccsetup boilerplate:
+
+- **[backend](backend.md)** - Backend development specialist for API design, database architecture, and server-side optimization
+- **[blockchain](blockchain.md)** - Blockchain and Web3 expert for smart contracts, DeFi protocols, and blockchain architecture
+- **[checker](checker.md)** - Quality assurance and code review specialist for testing, security analysis, and validation
+- **[coder](coder.md)** - Expert software developer for implementing features, fixing bugs, and optimizing code
+- **[frontend](frontend.md)** - Frontend development specialist for UI/UX, responsive design, and modern web frameworks
+- **[planner](planner.md)** - Strategic planning specialist for breaking down complex problems and creating implementation roadmaps
+- **[researcher](researcher.md)** - Research specialist for both online sources and local codebases, gathering comprehensive information
+- **[shadcn](shadcn.md)** - shadcn/ui component library expert for building beautiful, accessible React interfaces
+
+### wshobson/agents Collection (44 agents)
+
+The following 44 specialized agents are from the excellent [wshobson/agents](https://github.com/wshobson/agents) repository:
+
+#### Development & Architecture
+- **[backend-architect](backend-architect.md)** - Design RESTful APIs, microservice boundaries, and database schemas
+- **[frontend-developer](frontend-developer.md)** - Build React components, implement responsive layouts, and handle client-side state management
+- **[mobile-developer](mobile-developer.md)** - Develop React Native or Flutter apps with native integrations
+- **[graphql-architect](graphql-architect.md)** - Design GraphQL schemas, resolvers, and federation
+- **[architect-review](architect-review.md)** - Reviews code changes for architectural consistency and patterns
+
+#### Language Specialists
+- **[python-pro](python-pro.md)** - Write idiomatic Python code with advanced features and optimizations
+- **[golang-pro](golang-pro.md)** - Write idiomatic Go code with goroutines, channels, and interfaces
+- **[rust-pro](rust-pro.md)** - Write idiomatic Rust with ownership patterns, lifetimes, and trait implementations
+- **[c-pro](c-pro.md)** - Write efficient C code with proper memory management and system calls
+- **[cpp-pro](cpp-pro.md)** - Write idiomatic C++ code with modern features, RAII, smart pointers, and STL algorithms
+- **[javascript-pro](javascript-pro.md)** - Master modern JavaScript with ES6+, async patterns, and Node.js APIs
+- **[sql-pro](sql-pro.md)** - Write complex SQL queries, optimize execution plans, and design normalized schemas
+
+#### Infrastructure & Operations
+- **[devops-troubleshooter](devops-troubleshooter.md)** - Debug production issues, analyze logs, and fix deployment failures
+- **[deployment-engineer](deployment-engineer.md)** - Configure CI/CD pipelines, Docker containers, and cloud deployments
+- **[cloud-architect](cloud-architect.md)** - Design AWS/Azure/GCP infrastructure and optimize cloud costs
+- **[database-optimizer](database-optimizer.md)** - Optimize SQL queries, design efficient indexes, and handle database migrations
+- **[database-admin](database-admin.md)** - Manage database operations, backups, replication, and monitoring
+- **[terraform-specialist](terraform-specialist.md)** - Write advanced Terraform modules, manage state files, and implement IaC best practices
+- **[incident-responder](incident-responder.md)** - Handles production incidents with urgency and precision
+- **[network-engineer](network-engineer.md)** - Debug network connectivity, configure load balancers, and analyze traffic patterns
+- **[dx-optimizer](dx-optimizer.md)** - Developer Experience specialist that improves tooling, setup, and workflows
+
+#### Quality & Security
+- **[code-reviewer](code-reviewer.md)** - Expert code review for quality, security, and maintainability
+- **[security-auditor](security-auditor.md)** - Review code for vulnerabilities and ensure OWASP compliance
+- **[test-automator](test-automator.md)** - Create comprehensive test suites with unit, integration, and e2e tests
+- **[performance-engineer](performance-engineer.md)** - Profile applications, optimize bottlenecks, and implement caching strategies
+- **[debugger](debugger.md)** - Debugging specialist for errors, test failures, and unexpected behavior
+- **[error-detective](error-detective.md)** - Search logs and codebases for error patterns, stack traces, and anomalies
+- **[search-specialist](search-specialist.md)** - Expert web researcher using advanced search techniques and synthesis
+
+#### Data & AI
+- **[data-scientist](data-scientist.md)** - Data analysis expert for SQL queries, BigQuery operations, and data insights
+- **[data-engineer](data-engineer.md)** - Build ETL pipelines, data warehouses, and streaming architectures
+- **[ai-engineer](ai-engineer.md)** - Build LLM applications, RAG systems, and prompt pipelines
+- **[ml-engineer](ml-engineer.md)** - Implement ML pipelines, model serving, and feature engineering
+- **[mlops-engineer](mlops-engineer.md)** - Build ML pipelines, experiment tracking, and model registries
+- **[prompt-engineer](prompt-engineer.md)** - Optimizes prompts for LLMs and AI systems
+
+#### Specialized Domains
+- **[api-documenter](api-documenter.md)** - Create OpenAPI/Swagger specs and write developer documentation
+- **[payment-integration](payment-integration.md)** - Integrate Stripe, PayPal, and payment processors
+- **[quant-analyst](quant-analyst.md)** - Build financial models, backtest trading strategies, and analyze market data
+- **[risk-manager](risk-manager.md)** - Monitor portfolio risk, R-multiples, and position limits
+- **[legacy-modernizer](legacy-modernizer.md)** - Refactor legacy codebases and implement gradual modernization
+- **[context-manager](context-manager.md)** - Manages context across multiple agents and long-running tasks
+
+#### Business & Marketing
+- **[business-analyst](business-analyst.md)** - Analyze metrics, create reports, and track KPIs
+- **[content-marketer](content-marketer.md)** - Write blog posts, social media content, and email newsletters
+- **[sales-automator](sales-automator.md)** - Draft cold emails, follow-ups, and proposal templates
+- **[customer-support](customer-support.md)** - Handle support tickets, FAQ responses, and customer emails
+
+## Usage
+
+### Installation
+
+When using ccsetup, agents can be:
+1. **Selected interactively** during setup (curated list of 8 agents)
+2. **Copied in browse mode** (all 52 agents copied to /agents folder)
+3. **Included automatically** with --all-agents flag
+
+To activate agents, copy them to `~/.claude/agents/`:
+```bash
+# Example: Activate the code-reviewer agent
+cp agents/code-reviewer.md ~/.claude/agents/
+
+# Activate multiple agents
+cp agents/{python-pro,test-automator,security-auditor}.md ~/.claude/agents/
+```
+
+### Invoking Agents
+
+#### Automatic Invocation
+Claude Code will automatically delegate to the appropriate agent based on the task context.
+
+#### Explicit Invocation
+Mention the agent by name in your request:
+```
+"Use the code-reviewer to check my recent changes"
+"Have the security-auditor scan for vulnerabilities"
+"Get the performance-engineer to optimize this bottleneck"
+```
+
+## Agent Format
+
+Each agent follows this structure:
 ```markdown
-# Agent Name
+---
+name: agent-name
+description: When this agent should be invoked
+tools: tool1, tool2  # Optional - defaults to all tools
+---
 
-## Purpose
-[What this agent does]
+System prompt defining the agent's role and capabilities
+```
 
-## Capabilities
-- [Capability 1]
-- [Capability 2]
+## Common Agent Workflows
 
-## Instructions
-[Detailed instructions for the agent]
+### Feature Development
 ```
+planner → coder → checker
+```
+
+### API Development
+```
+backend-architect → backend → api-documenter → checker
+```
+
+### Frontend Development
+```
+frontend → shadcn → checker
+```
+
+### Full Stack Development
+```
+planner → backend-architect → backend → frontend → checker
+```
+
+### Bug Fixing
+```
+researcher → debugger → coder → checker
+```
+
+### Performance Optimization
+```
+performance-engineer → database-optimizer → coder → checker
+```
+
+### Security Review
+```
+security-auditor → code-reviewer → coder (for fixes) → checker
+```
+
+## Tips for Using Agents
+
+1. **Let Claude Code choose** - Often Claude will automatically select the right agent
+2. **Be specific** - The more specific your request, the better the agent selection
+3. **Combine agents** - Many tasks benefit from multiple agents working together
+4. **Review agent output** - Agents provide specialized expertise but should be reviewed
+5. **Iterate** - Use agent feedback to refine your approach
+
+## Contributing
+
+To add a new agent:
+1. Create a new `.md` file in this directory
+2. Follow the agent format (frontmatter + system prompt)
+3. Use lowercase, hyphen-separated names
+4. Write clear descriptions for when the agent should be used
+
+## Learn More
 
-## Available Agents
-- **planner** - Strategic planning specialist for breaking down complex problems and creating implementation roadmaps
-- **coder** - Expert software developer for implementing features, fixing bugs, and optimizing code
-- **checker** - Quality assurance and code review specialist for testing, security analysis, and validation
-- **researcher** - Research specialist for both online sources and local codebases, gathering comprehensive information from multiple sources
-- **blockchain** - Blockchain and Web3 expert for smart contracts, DeFi protocols, and blockchain architecture
-- **frontend** - Frontend development specialist for UI/UX, responsive design, and modern web frameworks
-- **shadcn** - shadcn/ui component library expert for building beautiful, accessible React interfaces
+- [ccsetup Documentation](https://github.com/MrMarciaOng/ccsetup)
+- [wshobson/agents Repository](https://github.com/wshobson/agents)
+- [Claude Code Documentation](https://docs.anthropic.com/en/docs/claude-code)
+- [Subagents Documentation](https://docs.anthropic.com/en/docs/claude-code/sub-agents)

package/template/agents/ai-engineer.md

@@ -0,0 +1,31 @@
+---
+name: ai-engineer
+description: Build LLM applications, RAG systems, and prompt pipelines. Implements vector search, agent orchestration, and AI API integrations. Use PROACTIVELY for LLM features, chatbots, or AI-powered applications.
+---
+
+You are an AI engineer specializing in LLM applications and generative AI systems.
+
+## Focus Areas
+- LLM integration (OpenAI, Anthropic, open source or local models)
+- RAG systems with vector databases (Qdrant, Pinecone, Weaviate)
+- Prompt engineering and optimization
+- Agent frameworks (LangChain, LangGraph, CrewAI patterns)
+- Embedding strategies and semantic search
+- Token optimization and cost management
+
+## Approach
+1. Start with simple prompts, iterate based on outputs
+2. Implement fallbacks for AI service failures
+3. Monitor token usage and costs
+4. Use structured outputs (JSON mode, function calling)
+5. Test with edge cases and adversarial inputs
+
+## Output
+- LLM integration code with error handling
+- RAG pipeline with chunking strategy
+- Prompt templates with variable injection
+- Vector database setup and queries
+- Token usage tracking and optimization
+- Evaluation metrics for AI outputs
+
+Focus on reliability and cost efficiency. Include prompt versioning and A/B testing.

package/template/agents/api-documenter.md

@@ -0,0 +1,31 @@
+---
+name: api-documenter
+description: Create OpenAPI/Swagger specs, generate SDKs, and write developer documentation. Handles versioning, examples, and interactive docs. Use PROACTIVELY for API documentation or client library generation.
+---
+
+You are an API documentation specialist focused on developer experience.
+
+## Focus Areas
+- OpenAPI 3.0/Swagger specification writing
+- SDK generation and client libraries
+- Interactive documentation (Postman/Insomnia)
+- Versioning strategies and migration guides
+- Code examples in multiple languages
+- Authentication and error documentation
+
+## Approach
+1. Document as you build - not after
+2. Real examples over abstract descriptions
+3. Show both success and error cases
+4. Version everything including docs
+5. Test documentation accuracy
+
+## Output
+- Complete OpenAPI specification
+- Request/response examples with all fields
+- Authentication setup guide
+- Error code reference with solutions
+- SDK usage examples
+- Postman collection for testing
+
+Focus on developer experience. Include curl examples and common use cases.