* feat: add Loops component type with referenced components
Introduce "loops" as a new first-class component type — autonomous
agentic workflows (goal + interval + stop condition) inspired by Loop
Engineering and the Forward Future Loop Library. A loop references other
components (agents, skills, hooks, commands) and the dashboard renders
those references as clickable cards on the loop detail page.
- Add 10 starter loops under cli-tool/components/loops/
(engineering, evaluation, operations)
- Catalog generator: scan loops + write per-component content files
- Dashboard: new type in icons/types/data, /loops page, and a
"Referenced Components" section on the loop detail page
- CLI: --loop flag installs the loop to .claude/loops/ and
auto-installs its referenced components
- Docs: CLAUDE.md and cli-tool rule updated
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01T9ynMiCHt8JwdMd8KjCkES
* feat: add 8 more loops (goal/loop/schedule patterns)
Expand the loops catalog to 18, drawing ideas from community "Loop
Engineering" patterns. Adds loops across the three trigger verbs
(/goal, /loop, /schedule) and emphasizes the verifier-in-the-loop and
budget / anti-spin guardrails:
- engineering/five-minute-maintainer-loop
- engineering/build-test-fix-loop
- engineering/anti-spin-build-loop
- engineering/completion-contract-loop (goal)
- engineering/goal-refiner-loop (goal)
- engineering/adversarial-review-loop (cross-model)
- operations/overnight-pr-routine-loop (schedule)
- evaluation/human-approval-loop (human-in-the-loop)
All referenced components verified to exist; catalog regenerated.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01T9ynMiCHt8JwdMd8KjCkES
---------
Co-authored-by: Claude <noreply@anthropic.com>
Analytics Dashboard (Phase 1 + Phase 2):
- Replace 8663-line vanilla JS monolith with Astro static build
- New bento-grid layout with Geist design system (dark/light themes)
- ECharts (offline, tree-shaken) replaces Chart.js CDN dependency
- React island with KPI cards, token timeline, activity heatmap, agent BarList
- WebSocket client with reconnect backoff; polling fallback when WS disconnects
- API client with 30s cache; normalizes backend field names (inputTokens→totalInput)
- Build source in analytics-ui/, output committed to src/analytics-web/
- Fix: /api/activity now uses in-memory cache (was re-scanning all files on each request)
- Fix: remove duplicate /api/agents route (dead code since Express uses first match)
- Fix: /api/data and /api/fast-update no longer mutate this.data.conversations in place
TUI Modernization:
- Add src/tui.js with @clack/prompts-powered banner and helpers
- Replace inline showBanner() in bin/create-claude-config.js with tui.showBanner()
- Migrate showMainMenu() in src/index.js to @clack select() (replaces inquirer)
- Add @clack/prompts ^1.5.1 and gradient-string ^2.0.2 to dependencies
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds a new local web dashboard to visualize Claude Code team sessions:
- Express server on port 3338 with JSONL parsing from ~/.claude/projects/
- SVG flow diagram showing agent hierarchy and communication edges
- Click-to-open detail panel with accordion sections (interactions, messages, tasks, tools)
- Smart agent name resolution from task assignment payloads
- Team session detection filtering (TeamCreate/SendMessage protocol only)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add --2025 option to launch Year-in-Review visualization
- Support --tunnel flag with --2025 for remote access
- Track analytics dashboard usage for 2025 page
- Update allowed bash commands in local settings
Usage: cct --2025 [--tunnel]
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The --skills flag was conflicting with the existing --skills component installation command,
causing EADDRINUSE errors on port 3337. Changed Skills Dashboard to use --skills-manager instead.
Changes:
- bin/create-claude-config.js: --skills → --skills-manager
- src/index.js: options.skills → options.skillsManager
- SKILLS_DASHBOARD.md: Updated usage examples
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Implements a comprehensive Skills Dashboard accessible via `--skills` flag that visualizes
Claude Code's 3-level progressive context loading system according to official documentation.
Features:
- **Level 1: Metadata** - Always loaded (~100 tokens): name, description, allowed-tools from YAML
- **Level 2: Instructions** - When triggered (<5k tokens): SKILL.md body with workflows
- **Level 3+: Resources & Code** - As needed (unlimited): Additional markdown, scripts, templates
- Instructions: Additional .md files with specialized guidance
- Code: Executable scripts (.py, .js, .sh) run via bash without loading into context
- Resources: Reference materials (schemas, API docs, templates, examples)
Technical Implementation:
- Express.js server on port 3337 with RESTful API
- Real-time skill scanning from ~/.claude/skills and .claude/skills
- Progressive file categorization: alwaysLoaded, onDemand, progressive
- Modern UI with level cards, flow arrows, and resource categorization
- File type detection and proper context for markdown references vs executable code
Dashboard shows:
- Grid/list view of all installed skills
- Filter by source (Personal, Project, Plugin)
- Sort by name, file count, last modified
- Modal detail view with 3-level loading visualization
- Visual flow arrows between levels showing loading triggers
- Category descriptions matching official Skills documentation
Fixes context preservation issue in scanSupportingFiles() where `this` context
was lost in nested function, now using `const self = this` pattern.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* feat: add session sharing and cloning functionality
Implement complete session sharing system for Claude Code conversations:
Features:
- Share button in chats interface with QR code generation
- Upload sessions to x0.at (temporary file hosting)
- Clone sessions with --clone-session command
- Limit shared sessions to last 100 messages
- Security confirmation modal with service information
- Resume command display after cloning
Backend:
- New SessionSharing class for export/upload/download/install
- Integration with ConversationAnalyzer
- x0.at upload service (tested and working)
- JSONL format conversion for Claude Code compatibility
Frontend:
- Confirmation modal with x0.at security info
- Centered QR code display
- Improved button styling (Resume, Share, Search)
- Real-time upload progress indication
CLI:
- Added --clone-session <url> parameter
- Automatic session installation to ~/.claude/projects/
- Display resume command with conversation ID
Dependencies:
- Added qrcode package for QR generation
🤖 Generated with Claude Code (https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* feat: improve chats UI with project grouping and unified action buttons
Major improvements to chats interface:
Project Organization:
- Group conversations by project with collapsible sections
- Projects collapsed by default for cleaner interface
- Auto-expand projects during search with matching results
- Sticky project headers for better navigation
- Project avatars with gradients and conversation counts
Terminology Update:
- Changed "conversations" to "sessions" throughout UI
- Updated empty state messages
- Consistent terminology in headers and labels
Action Buttons Enhancement:
- Unified Resume, Share, and Search buttons in center header
- Replaced emojis with professional SVG icons
- Grouped design with orange accent border
- Individual hover states (green/blue/orange)
- Responsive button group with smooth transitions
Search Improvements:
- Fixed search to work with grouped project structure
- Search in both project names and session IDs
- Auto-collapse all projects when clearing search
- Proper filter clearing in advanced search
- Maintained state management across search operations
Visual Design:
- Orange accent border highlighting action buttons (2px)
- Subtle orange background for button group
- Consistent hover effects with color coding
- Enhanced visual hierarchy
- Better spacing and alignment
🤖 Generated with Claude Code (https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
- Add E2B sandbox component with Python launcher script
- Support CLI parameters for E2B and Anthropic API keys (--e2b-api-key, --anthropic-api-key)
- Add comprehensive error handling for file downloads
- Make dotenv import optional in launcher script
- Add complete blog post with sandbox usage guide
- Update component generation system to support sandbox category
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Updated hackathon-ai-strategist agent description and added tools for improved functionality.
- Revised llms-maintainer agent for proactive updates and enhanced tools.
- Introduced new model-evaluator agent for comprehensive AI model assessment and benchmarking.
- Enhanced prompt-engineer agent description for clarity on usage.
- Updated task-decomposition-expert agent to emphasize complex goal breakdown and tool selection.
- Expanded graphql-architect agent with detailed schema design and resolver optimization strategies.
- Created graphql-performance-optimizer agent for performance analysis and optimization of GraphQL APIs.
- Developed graphql-security-specialist agent focusing on security audits, authorization, and protection against vulnerabilities.
- Added security-auditor script to package.json for automated security audits.
🌍 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>
- Add 9 Settings components (telemetry, permissions, model, cleanup)
- Add 6 Hooks components (formatting, git integration, backups, testing)
- Implement CLI installation with --setting and --hook flags
- Add conflict detection that prompts user before overwriting
- Merge settings into .claude/settings.json with intelligent deep merge
- Update data-loader.js to handle new component types
- Add filter buttons for Settings and Hooks in web interface
- Generate components.json with new Settings and Hooks sections
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add Shopify-style cart sidebar with drag-from-right animation
- Implement Add to Stack buttons for all component cards
- Create dynamic command generation for agents, commands, and MCPs
- Add cart state management with localStorage persistence
- Implement notification system with auto-dismiss
- Add social sharing for X/Twitter and Threads
- Create overlay copy buttons for command text in cards and cart
- Optimize card layout grid system (4 columns desktop, 2 tablet, 1 mobile)
- Add cart floating button with item count badge
- Fix scroll prevention and notification persistence issues
- Remove quotes from agent parameters in generated commands
- Implement compact cart item design with Clear All repositioning
- Add comprehensive cart styling with responsive design
- Include share functionality with proper URL encoding
- Update CLI package version to 1.14.16 for npm compatibility
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
## 🔧 Workflow Builder Web Interface
- **Drag-and-Drop Canvas**: Visual workflow building with sortable steps
- **Component Library**: Browse and search all agents, commands, and MCPs
- **Real-time Preview**: Live workflow statistics and step management
- **Hash Generation**: Secure workflow encoding with CryptoJS
- **YAML Export**: Generate executable workflow files
- **Modal Interface**: Professional workflow generation dialog
## ⚡ CLI Workflow Installation
- **--workflow option**: Install workflows from hash (format: #hash)
- **Batch Installation**: Download all workflow components automatically
- **Silent Mode**: Clean output when installing multiple components
- **YAML Generation**: Create step-by-step execution files
- **Error Handling**: Comprehensive validation and user guidance
## 🎨 UI/UX Features
- **Responsive Design**: Works on desktop and mobile devices
- **Professional Styling**: Clean, modern interface with proper theming
- **Interactive Components**: Hover effects, drag feedback, and animations
- **Search Functionality**: Filter components by name and category
- **Navigation Integration**: Added workflows link to main header
## 🔗 Architecture
- **Modular Frontend**: Separate CSS and JS files for maintainability
- **GitHub Integration**: Dynamic component loading from organized categories
- **Local Storage**: Workflow state management for hash generation
- **Component Tracking**: Analytics integration for usage monitoring
## 🚀 Workflow Execution Flow
1. **Build**: Create workflows in drag-and-drop interface
2. **Generate**: Export hash and YAML configuration
3. **Install**: Use CLI with generated hash to download all components
4. **Execute**: Use YAML file with Claude Code for step-by-step automation
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
## 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>
* 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>
* feat: Enhance DataService with paginated conversations and improved error handling
- Added `getConversationsPaginated` method to fetch conversations with pagination support.
- Improved error handling in `cachedFetch` to provide clearer messages and fallback behavior.
- Updated WebSocket integration to handle connection failures with fallback polling.
- Reduced WebSocket auto-reconnect attempts and disabled auto-reconnect to minimize console noise.
- Added CORS middleware to the web server for better API accessibility.
- Implemented paginated conversations endpoint in the server.
- Added conversation messages endpoint to retrieve messages for a specific conversation.
- Enhanced conversation analysis to include detailed session data and compatibility with original dashboard.
* feat: Implement real-time conversation change handling and notifications
- Added handleConversationChange method to ClaudeAnalytics for processing updates to conversation files.
- Integrated WebSocket notifications for new messages in conversations.
- Enhanced setupFileWatchers to include conversation change callbacks.
- Updated conversation state API to calculate states for all conversations, improving performance and accuracy.
- Introduced pagination for conversation messages endpoint to support large message sets.
- Implemented cache management endpoint for clearing specific cache types.
- Enhanced DataCache and ConversationAnalyzer to support tool correlation in message parsing.
- Created ToolDisplay component for safe rendering of tool uses and results in the analytics dashboard.
- Added comprehensive documentation for Claude data structures and formats.
* feat: Enhance real-time messaging and dashboard features
- Improved logging for new messages in DataService to include message data.
- Increased WebSocket reconnection attempts for better reliability.
- Enabled auto-reconnect in WebSocketService for real-time updates.
- Updated conversation change handling in ClaudeAnalytics to include file path.
- Enhanced error handling and logging in ConversationAnalyzer and DataCache.
- Added new settings file for local permissions.
- Introduced a new Chats Dashboard option in the main menu.
- Created detailed architecture documentation for the analytics web application.
- Deprecated old main.js and Dashboard.js files in favor of a modular structure.
* feat: Implement real-time message handling and improve logging in DataService and AgentsPage
* feat: Implement comprehensive conversation state detection improvements
- Enhanced frontend message analysis for tool execution and content analysis.
- Introduced file activity detection to accurately identify user typing.
- Adopted a WebSocket-first approach for real-time state updates.
- Expanded state vocabulary with new contextual states and visual indicators.
- Improved state banner display with new CSS classes.
- Integrated system components for cohesive state management.
- Added health check feature to validate system requirements and configurations.
- Developed ConsoleBridge for web-based interaction with Claude Code processes.
- Created test script for ConsoleBridge to facilitate integration testing.
- Add Health Check as second menu option in CLI
- Comprehensive system validation:
* System requirements (OS, Node.js, memory, network)
* Claude Code setup (installation, auth, permissions)
* Project configuration (structure, settings files)
* Custom commands and hooks validation
* Settings.json analysis (user/project/local)
- Interactive UX with ora spinners and immediate results
- 3-second pacing between categories for better visual flow
- Detailed health score with actionable recommendations
- Settings validation with security checks and best practices
- Enhanced navigation flow returning to main menu
- Fix Project Setup flow from both health check and direct menu selection
- Update README documentation with Health Check feature
- Add CLI aliases: --health-check, --health, --check, --verify
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Remove automatic help output when no arguments provided
- Allow interactive welcome screen to show cleanly
- Users can still access help with --help flag
- Fixes clean onboarding experience
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added --command-stats CLI option to analyze existing Claude Code commands
- Created command-stats.js module with comprehensive analysis functions
- Displays command statistics in formatted table (name, size, lines, words, last modified)
- Calculates totals and provides project overview
- Interactive prompt for command optimization using Claude Code
- Generates intelligent optimization prompts based on project structure
- Integrates with existing CLI workflow and error handling
- Helps users optimize their .claude/commands for their specific project setup
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Fixed version command to show correct version (1.3.5)
- Changed bin/create-claude-config.js to read version from package.json
- Version 1.3.4 was published but showed wrong version number
- Now --version will show the actual published version
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Fix ASCII art to properly display "CLAUDE CODE TEMPLATES"
- Add back navigation functionality to CLI prompts
- Implement framework-specific configurations (React, Vue, Angular, Node.js)
- Mark Python, Rust, Go as "Coming Soon" for first release
- Fix .mcp.json file copying during installation
- Remove non-functional "additional features" prompts
- Translate all Spanish content to English for open-source publication
- Add comprehensive template synchronization system
- Enhance file operations with framework-specific command copying
- Update documentation and README files
- Add new command scanner and utility modules
- Create framework-specific example configurations
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Introduced CLAUDE.md with universal development guidelines, project structure, and best practices for JavaScript/TypeScript and Python.
- Created README.md files for common Claude Code templates, Go, JavaScript/TypeScript, and Python projects.
- Added specific command templates for JavaScript/TypeScript, including API endpoint, debug, lint, npm scripts, React component, refactor, test, and TypeScript migration commands.
- Implemented hooks for formatting and linting on save in JavaScript/TypeScript projects.
- Established settings.json for JavaScript/TypeScript projects with permissions and environment variables.
- Developed project structure guidelines for JavaScript/TypeScript and Python projects.
- Created example projects for React and Node.js APIs with corresponding CLAUDE.md files.
- Laid groundwork for future Rust and Go templates with placeholder README.md files.
- Set up package.json for test setup with React dependencies.
Daniel Avila