mirror of
https://github.com/SuperClaude-Org/SuperClaude_Framework.git
synced 2025-12-29 16:16:08 +00:00
d27c53fa1c
* feat: Add PM Agent (Project Manager Agent) for seamless orchestration Introduces PM Agent as the default orchestration layer that coordinates all sub-agents and manages workflows automatically. Key Features: - Default orchestration: All user interactions handled by PM Agent - Auto-delegation: Intelligent sub-agent selection based on task analysis - Docker Gateway integration: Zero-token baseline with dynamic MCP loading - Self-improvement loop: Automatic documentation of patterns and mistakes - Optional override: Users can specify sub-agents explicitly if desired Architecture: - Agent spec: SuperClaude/Agents/pm-agent.md - Command: SuperClaude/Commands/pm.md - Updated docs: README.md (15→16 agents), agents.md (new Orchestration category) User Experience: - Default: PM Agent handles everything (seamless, no manual routing) - Optional: Explicit --agent flag for direct sub-agent access - Both modes available simultaneously (no user downside) Implementation Status: - ✅ Specification complete - ✅ Documentation complete - ⏳ Prototype implementation needed - ⏳ Docker Gateway integration needed - ⏳ Testing and validation needed Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration) * feat: Add Agent Orchestration rules for PM Agent default activation Implements PM Agent as the default orchestration layer in RULES.md. Key Changes: - New 'Agent Orchestration' section (CRITICAL priority) - PM Agent receives ALL user requests by default - Manual override with @agent-[name] bypasses PM Agent - Agent Selection Priority clearly defined: 1. Manual override → Direct routing 2. Default → PM Agent → Auto-delegation 3. Delegation based on keywords, file types, complexity, context User Experience: - Default: PM Agent handles everything (seamless) - Override: @agent-[name] for direct specialist access - Transparent: PM Agent reports delegation decisions This establishes PM Agent as the orchestration layer while respecting existing auto-activation patterns and manual overrides. Next Steps: - Local testing in agiletec project - Iteration based on actual behavior - Documentation updates as needed * refactor(pm-agent): redesign as self-improvement meta-layer Problem Resolution: PM Agent's initial design competed with existing auto-activation for task routing, creating confusion about orchestration responsibilities and adding unnecessary complexity. Design Change: Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents complete tasks, focusing on: - Post-implementation documentation and pattern recording - Immediate mistake analysis with prevention checklists - Monthly documentation maintenance and noise reduction - Pattern extraction and knowledge synthesis Two-Layer Orchestration System: 1. Task Execution Layer: Existing auto-activation handles task routing (unchanged) 2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new) Files Modified: - SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design - Category: orchestration → meta - Triggers: All user interactions → Post-implementation, mistakes, monthly - Behavioral Mindset: Continuous learning system - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE - SuperClaude/Core/RULES.md: Agent Orchestration section updated - Split into Task Execution Layer + Self-Improvement Layer - Added orchestration flow diagram - Clarified PM Agent activates AFTER task completion - README.md: Updated PM Agent description - "orchestrates all interactions" → "ensures continuous learning" - Docs/User-Guide/agents.md: PM Agent section rewritten - Section: Orchestration Agent → Meta-Layer Agent - Expertise: Project orchestration → Self-improvement workflow executor - Examples: Task coordination → Post-implementation documentation - PR_DOCUMENTATION.md: Comprehensive PR documentation added - Summary, motivation, changes, testing, breaking changes - Two-layer orchestration system diagram - Verification checklist Integration Validated: Tested with agiletec project's self-improvement-workflow.md: ✅ PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases ✅ Complements (not competes with) existing workflow ✅ agiletec workflow defines WHAT, PM Agent defines WHO executes it Breaking Changes: None - Existing auto-activation continues unchanged - Specialist agents unaffected - User workflows remain the same - New capability: Automatic documentation and knowledge maintenance Value Proposition: Transforms SuperClaude into a continuously learning system that accumulates knowledge, prevents recurring mistakes, and maintains fresh documentation without manual intervention. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local> Co-authored-by: Claude <noreply@anthropic.com>
SuperClaude Documentation
🎯 Essential Understanding
SuperClaude is a Context Framework for Claude Code - it installs behavioral instruction files that Claude Code reads to enhance its capabilities.
How It Works
- Installation: Python CLI installs context files to
~/.claude/ - Commands: Type
/sc:analyze→ Claude Code readsanalyze.mdinstruction file - Behavior: Claude adopts behaviors defined in context files
- Result: Enhanced development workflows through context switching
🚀 Quick Start (5 Minutes)
New Users: Quick Start Guide →
# Recommended for Linux/macOS
pipx install SuperClaude && SuperClaude install
# Traditional method
pip install SuperClaude && SuperClaude install
# Then try: /sc:brainstorm "web app idea" in Claude Code
Having Issues: Quick Fixes → | Troubleshooting →
📚 Documentation Structure
🌱 Start Here (New Users)
| Guide | Purpose |
|---|---|
| Quick Start | Setup and first commands |
| Installation | Detailed setup instructions |
| Commands Guide | All 21 /sc: commands |
🌿 Daily Usage (Regular Users)
| Guide | Purpose | Use For |
|---|---|---|
| Commands Guide | Master all /sc: commands |
Daily development |
| Agents Guide | 14 domain specialists (@agent-*) |
Expert assistance |
| Flags Guide | Command behavior modification | Optimization |
| Modes Guide | 5 behavioral modes | Workflow optimization |
🌲 Reference & Advanced (Power Users)
| Guide | Purpose | Use For |
|---|---|---|
| Troubleshooting | Problem resolution | When things break |
| Examples Cookbook | Practical usage patterns | Learning workflows |
| MCP Servers | 6 enhanced capabilities | Advanced features |
🔧 Development & Contributing
| Guide | Purpose | Audience |
|---|---|---|
| Technical Architecture | System design | Contributors |
| Contributing | Development workflow | Developers |
🔑 Key Concepts
What Gets Installed
- Python CLI Tool - Manages framework installation
- Context Files -
.mdbehavioral instructions in~/.claude/ - MCP Configurations - Optional external tool settings
Framework Components
- 21 Commands (
/sc:*) - Workflow automation patterns - 14 Agents (
@agent-*) - Domain specialists - 5 Modes - Behavioral modification patterns
- 6 MCP Servers - Optional external tools
🚀 Quick Command Reference
In Your Terminal (Installation)
# Install framework (choose one)
pipx install SuperClaude # Recommended for Linux/macOS
pip install SuperClaude # Traditional method
npm install -g @bifrost_inc/superclaude # Cross-platform
# Configure and maintain
SuperClaude install # Configure Claude Code
SuperClaude update # Update framework
python3 -m SuperClaude --version # Check installation
In Claude Code (Usage)
/sc:brainstorm "project idea" # Start new project
/sc:implement "feature" # Build features
/sc:analyze src/ # Analyze code
@agent-python-expert "optimize this" # Manual specialist
@agent-security "review authentication" # Security review
📊 Framework vs Software Comparison
| Component | Type | Where It Runs | What It Does |
|---|---|---|---|
| SuperClaude Framework | Context Files | Read by Claude Code | Modifies AI behavior |
| Claude Code | Software | Your computer | Executes everything |
| MCP Servers | Software | Node.js processes | Provide tools |
| Python CLI | Software | Python runtime | Manages installation |
🔄 How Everything Connects
User Input → Claude Code → Reads SuperClaude Context → Modified Behavior → Enhanced Output
↓
May use MCP Servers
(if configured)
🆘 Getting Help
Quick Issues (< 2 min): Common Issues →
Complex Problems: Full Troubleshooting Guide →
Installation Issues: Installation Guide →
Command Help: Commands Guide →
Community Support: GitHub Discussions
🤔 Common Misconceptions Clarified
❌ "SuperClaude is an AI assistant"
✅ SuperClaude is a configuration framework that enhances Claude Code
❌ "I'm running SuperClaude"
✅ You're running Claude Code with SuperClaude context loaded
❌ "Claude Code executes; SuperClaude provides context my commands"
✅ Claude Code executes everything; SuperClaude provides the instructions
❌ "The .md files are documentation"
✅ The .md files ARE the framework - active instruction sets
Remember: SuperClaude enhances Claude Code through context - it doesn't replace it or run alongside it. Everything happens within Claude Code itself.