## PM Agent Architecture Redesign ### Auto-Activation System - **pm-agent-auto-activation.md**: Behavior-based auto-activation architecture - 5 activation layers (Session Start, Documentation Guardian, Commander, Post-Implementation, Mistake Handler) - Remove manual `/sc:pm` command requirement - Auto-trigger based on context detection ### Responsibility Cleanup - **pm-agent-responsibility-cleanup.md**: Memory management strategy and MCP role clarification - Delete `docs/memory/` directory (redundant with Mindbase) - Remove `write_memory()` / `read_memory()` usage (Serena is code-only) - Clear lifecycle rules for each memory layer ## MCP Integration Policy ### Core Definitions - **mcp-integration-policy.md**: Complete MCP server definitions and usage guidelines - Mindbase: Automatic conversation history (don't touch) - Serena: Code understanding only (not task management) - Sequential: Complex reasoning engine - Context7: Official documentation reference - Tavily: Web search and research - Clear auto-trigger conditions for each MCP - Anti-patterns and best practices ### Optional Design - **mcp-optional-design.md**: MCP-optional architecture with graceful fallbacks - SuperClaude works fully without any MCPs - MCPs are performance enhancements (2-3x faster, 30-50% fewer tokens) - Automatic fallback to native tools - User choice: Minimal → Standard → Enhanced setup ## Key Benefits **Simplicity**: - Remove `docs/memory/` complexity - Clear MCP role separation - Auto-activation (no manual commands) **Reliability**: - Works without MCPs (graceful degradation) - Clear fallback strategies - No single point of failure **Performance** (with MCPs): - 2-3x faster execution - 30-50% token reduction - Better code understanding (Serena) - Efficient reasoning (Sequential) 🤖 Generated with [Claude Code](https://claude.com/claude-code) 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.