- Created conventional-commits.py for commit message validation
- Created prevent-direct-push.py for protected branch enforcement
- Updated all hook JSONs to use Python scripts with proper JSON output
- All hooks now use permissionDecision: "deny" for proper blocking
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Update local settings and configurations
- Add Vertex AI Claude Code integration blog post
- Sync analytics components and documentation
- Remove test data files and update configurations
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Implement on_stdout/on_stderr callbacks for live output streaming
- Add progress indicators during long operations
- Remove unnecessary warning message for aitmpl.com API
- Create API endpoint for agents list at /docs/api/agents.json
- Update getAvailableAgentsFromGitHub to use aitmpl.com API fallback
- Improve user experience with visual feedback during execution
- Version bump to 1.21.5
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add visual separator and loading message after permissions check
- Show 'Executing Claude Code in secure cloud sandbox' message
- Include status indicators for processing, isolation, and output
- Improve user feedback during execution wait time
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add new statusline/context-monitor component with real-time context usage monitoring
- Implement automatic Python script download for statusline components
- Update installIndividualSetting to support additional files installation
- Add context-monitor.py with visual progress bars, color-coded alerts, and session analytics
- Modify generate_components_json.py to exclude .py files from component listings
- Use relative paths (.claude/scripts/) instead of hardcoded paths
- Support executable file permissions for Python scripts
- Version bump to 1.20.2
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
🚀 Released: Major new feature integrating Claude Code SDK
- Global agents accessible from anywhere with zero configuration
- Auto-detects project context and provides specialized AI assistance
- Complete CLI integration with create/list/update/remove commands
- Frontend integration with enhanced agent modals
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
🌍 Major new feature: Global AI Agents powered by Claude Code SDK
## New Features
- **Global Agent Creation**: `--create-agent <agent-name>`
- **Agent Management**: `--list-agents`, `--update-agent`, `--remove-agent`
- **Zero Configuration**: Agents install to /usr/local/bin (immediately available)
- **Auto Context Detection**: Smart project type detection and file context
- **Universal Access**: Works from any directory, in scripts, CI/CD, npm tasks
## Technical Implementation
- New global-agent-manager.js module with complete agent lifecycle
- Automatic PATH management across shell environments
- Executable script generation with Claude Code SDK integration
- Real-time loading indicators during AI processing
- Robust error handling and fallback mechanisms
## Frontend Integration
- Enhanced agent modals with Global Agent installation options
- New CSS styles for global agent sections
- Copy-to-clipboard functionality for all commands
- Usage examples and feature highlights
## User Experience
Before: Traditional project-based agent installation
After: `cct --create-agent security-auditor` → `security-auditor "prompt"` (anywhere)
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Remove accidentally created nested cli-tool/cli-tool directory
- Add simple tracking test script for local verification
- Confirmed tracking system works correctly with proper error handling
- Both database and telemetry endpoints are functional
- System gracefully handles local vs production differences
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Upgraded jest-watch-typeahead from ^2.2.2 to ^3.0.1
- Resolves dependency compatibility issues causing npm install failures
- Version 3.0.1 provides improved Node.js compatibility and resolves known security vulnerabilities
- Updated package-lock.json to reflect the new dependency tree
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
- Added mobile-first chats interface in Quick Start section
- Highlighted --tunnel option with Cloudflare installation requirements
- Updated Core Features with new mobile interface and tunnel support
- Added installation instructions for cloudflared across platforms
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Released with MCP installation deep merge fix
- Fixes MCP server configuration overwriting issues
- Published to npm registry
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Switch from Vercel to GitHub Pages tracking endpoint
- Use custom domain aitmpl.com for tracking requests
- Verified working with successful 200 responses
- Completely anonymous tracking through GitHub Pages infrastructure
- Add public telemetry endpoint that returns 1x1 GIF (like Google Analytics)
- Enable anonymous tracking via GET requests with no-cors mode
- Endpoint creates GitHub issues for existing analytics workflow
- Maintains full compatibility with current download-stats.json system
- No authentication required - completely anonymous tracking
- Replace GitHub repository dispatch with Vercel function
- Add vercel-tracking/ project with /api/track endpoint
- Enable completely anonymous tracking without user credentials
- Maintain same analytics data structure and GitHub issues creation
- Replace direct issue creation with repository dispatch events
- Add tracking-dispatch.yml workflow to handle tracking events
- Enable anonymous tracking without requiring user tokens
- Maintain same analytics data structure for compatibility
## Major Changes
### 🔄 GitHub Download System
- All templates now download directly from GitHub instead of local files
- Components (agents, commands, MCPs) download from `components/` directory
- Templates download from `templates/` directory
- Added download caching to avoid repeated requests
- Show clear GitHub URLs for transparency
### 🆕 New --template Parameter
- Added `--template` parameter as modern replacement for `--language`/`--framework`
- Maintains backward compatibility with deprecated `--language`/`--framework`
- Updated web interface to use new syntax: `npx claude-code-templates@latest --template=python --yes`
### 🎯 Component vs Template Separation
- `--agent=name`: Downloads individual component to `.claude/agents/`
- `--command=name`: Downloads individual component to `.claude/commands/`
- `--mcp=name`: Downloads individual component to `.mcp.json`
- `--template=name`: Downloads complete template with full configuration
### 📦 Web Interface Updates
- Updated installation commands to use `npx` with latest version
- Changed from `--language`/`--framework` to `--template` syntax
- Made global installation optional in step 1
- All template cards now show correct download commands
### ✅ Benefits
- Always up-to-date content from GitHub main branch
- No need to republish npm package for content updates
- Clear distinction between individual components and full templates
- Improved user experience with transparent download sources
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
### ✨ New Features
- **Custom Domain**: Documentation now available at https://aitmpl.com/docu/
- **Expert Agents System**: New agent-expert, command-expert, and mcp-expert for community contributions
- **Unified Component Cards**: Fixed "Add New" cards design and behavior consistency
### 📚 Documentation
- **Complete Docusaurus Site**: Comprehensive documentation with searchable content
- **Simplified READMEs**: Streamlined both root and cli-tool READMEs, directing to full docs
- **Expert Agent Workflows**: Detailed guides for creating agents, commands, and MCPs
### 🎨 UI/UX Improvements
- **Component Cards**: Fixed design inconsistencies in "Add New" template/component cards
- **Navigation**: All documentation links now point to custom domain
- **Responsive Design**: Better mobile experience for documentation site
### 🔧 Infrastructure
- **GitHub Pages**: Custom domain configuration with proper routing
- **Community Workflow**: Streamlined process for community contributions using expert agents
### 🤝 Community
- **Contribution System**: New expert agents enable easy community contributions
- **Component Creation**: Standardized workflow for creating agents, commands, and MCPs
- **Documentation Hub**: Centralized documentation for better developer experience
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* feat: add agents selection to interactive setup
- Add agents step to interactive setup flow in prompts.js
- Include React performance optimization and state management agents
- Include Django API security and database optimization agents
- Integrate agent selection with existing setup workflow
- Show agent count in confirmation step
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* chore: bump version to 1.12.2 for agents feature
---------
Co-authored-by: Claude <noreply@anthropic.com>
* feat: Enhanced analytics dashboard with custom tool modals
- Implemented custom modals for all Claude Code tools (Read, Edit, Write, Bash, Glob, Grep, TodoWrite)
- Added intelligent diff viewer for Edit tool with dual modes (By Lines vs Smart Diff)
- Enhanced tool parameter visualization with project-specific insights
- Improved modal consistency with unified design patterns
- Added comprehensive CSS styling for all tool modals
- Fixed modal functionality and error handling across all tools
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* feat: improve startup screen and fix framework structure
- Redesign compact ASCII art for better terminal usage
- Add version info and documentation links to startup screen
- Fix frameworks → examples directory structure consistency
- Update all code references to use examples/ instead of frameworks/
- Fix Jest configuration typo (moduleNameMapping → moduleNameMapper)
- Add new agents.js module for agent management
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* chore: bump version to 1.12.1 for release
---------
Co-authored-by: Claude <noreply@anthropic.com>
- Added a new SVG file `undraw_docusaurus_tree.svg` to the static images directory for enhanced visual representation.
- Introduced a new TypeScript configuration file `tsconfig.json` to improve editor experience and project structure.
- Implement comprehensive CSS variables theming system
- Add minimalist toggle switch with smooth animations
- Support both light and dark modes with terminal-style design
- Theme preference persists in localStorage
- Dynamic chart color adaptation for theme changes
- Responsive design for mobile devices
- Clean, icon-only switch without text labels
- Fix SessionTimer component initialization and remove debug logs
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Implement comprehensive unit tests for StateCalculator to validate conversation status detection and state management.
- Create unit tests for StateService covering state management, subscriber notifications, and error handling.
- Develop unit tests for WebSocketServer to ensure proper handling of WebSocket connections, message broadcasting, and heartbeat mechanisms.
- Include edge case handling and validation for all components to enhance robustness and reliability.
- Bump version in package.json from 1.5.12 to 1.5.14.
- Add CSS styles for improved layout and status indicators in the web dashboard.
- Introduce a new message type indicator for user and assistant messages with tooltips.
- Implement logic to determine message types (success, error, tool execution, pending) based on message content.
- Refactor message rendering to include message type indicators.
- Added dynamic column width calculation based on actual command names
- Implemented visual separators (│) between columns for better readability
- Command names are capped at 25 characters with ellipsis truncation
- Responsive table width that adapts to content
- Better alignment and spacing for all columns
- Cleaner, more professional table appearance
- Fixes deformed tables when command names are long
Example improvement:
Before: command-name-is-very-long1.2KB 25 180 350 7/9/2025
After: command-name-is-very-l... │ 1.2KB │ 25 │ 180 │ 350 │ 7/9/2025
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Changed 'Tokens' column header to 'Tokens (aprox)' for clarity
- Added promptSetupWhenNoCommands() function to offer setup when no commands exist
- Updated table width to accommodate longer header (97 characters)
- When no .claude/commands directory is found, offers to start Claude Code Templates setup
- Improved user experience by providing clear next steps
- Returns appropriate boolean values from displayCommandStats for flow control
- Seamless integration between command analysis and initial setup
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added estimateTokens() function for token estimation based on content analysis
- Considers markdown formatting, code blocks, and text complexity
- New 'Tokens' column in command analysis table with magenta color
- Updated table width and formatting to accommodate token data
- Shows total token count in summary (e.g., '~3,833 tokens total')
- Helps users understand command complexity in terms of Claude token usage
- Essential for managing prompt lengths and optimization decisions
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Removed duplicate language directories from repository root (common/, go/, javascript-typescript/, python/, rust/)
- Fixed nested cli-tool/cli-tool/ directory structure
- All templates now centralized in cli-tool/templates/ (single source of truth)
- Clean repository structure with no duplication
- CLI functionality verified and working correctly
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Updated validation prompt to include project structure analysis
- Claude now examines package.json, src/, and other project files
- Provides project-specific recommendations based on actual dependencies
- Compares installed configuration with real project setup
- Makes more targeted suggestions for improvement
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Fixed spawn command to properly execute 'claude "prompt"' format
- Changed from spawn('claude', [prompt]) to spawn('sh', ['-c', claudeCommand])
- Now correctly passes validation prompt to Claude Code CLI
- Post-installation validation now works as intended
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Dani