🚀 SuperClaude Framework

Transform Claude Code into a Structured Development Platform

Quick Start • Support • Features • Docs • Contributing

---

📊 Framework Statistics

Plugins	Agents	Modes	MCP Servers
3	16	7	8
Plugin Commands	Specialized AI	Behavioral	Integrations

Three core plugins: PM Agent (orchestration), Research (web search), Index (context optimization).

---

🎯 Overview

SuperClaude is a meta-programming configuration framework that transforms Claude Code into a structured development platform through behavioral instruction injection and component orchestration. It provides systematic workflow automation with powerful tools and intelligent agents.

Disclaimer

This project is not affiliated with or endorsed by Anthropic. Claude Code is a product built and maintained by Anthropic.

📖 For Developers & Contributors

Essential documentation for working with SuperClaude Framework:

Document	Purpose	When to Read
PLANNING.md	Architecture, design principles, absolute rules	Session start, before implementation
TASK.md	Current tasks, priorities, backlog	Daily, before starting work
KNOWLEDGE.md	Accumulated insights, best practices, troubleshooting	When encountering issues, learning patterns
CONTRIBUTING.md	Contribution guidelines, workflow	Before submitting PRs

💡 Pro Tip: Claude Code reads these files at session start to ensure consistent, high-quality development aligned with project standards.

⚡ Quick Installation

Plugin Installation - Auto-Activation with Hot Reload

SuperClaude v2.0+ uses TypeScript plugins for instant updates and auto-activation:

# Method 1: Plugin Marketplace (Recommended)
# Open Claude Code → /plugin marketplace → Search "pm-agent" → Install

# Method 2: Manual Installation
cd /Users/kazuki/github/superclaude
# Plugin auto-registers on session start via SessionStart hook

Key Features:

• ✅ Hot Reload: Edit TypeScript → Save → Instant reflection (no restart)
• ✅ Auto-Activation: PM Agent starts automatically on session start
• ✅ Zero Configuration: Works out of the box

Enhanced Performance (Optional MCPs)

For 2-3x faster execution and 30-50% fewer tokens, optionally install MCP servers:

# Recommended MCP servers (via airis-mcp-gateway):
# - Mindbase: Cross-session memory (automatic)
# - Serena: Session persistence (2-3x faster)
# - Sequential: Token-efficient reasoning (30-50% fewer tokens)
# - Tavily: Web search for Deep Research
# - Context7: Official documentation lookup

# Install via: https://github.com/airis-mcp-gateway

Performance Comparison:

• Without MCPs: Fully functional, standard performance ✅
• With MCPs: 2-3x faster, 30-50% fewer tokens ⚡

⚠️ IMPORTANT: Upgrading from SuperClaude V1.x (Slash Commands)

V2.0 introduces breaking changes - migration from slash commands to TypeScript plugins:

# 1. Remove old slash commands (if installed)
rm -rf ~/.claude/commands/sc/

# 2. Install new plugin
# Via Claude Code: /plugin marketplace → "pm-agent"
# Or clone repository to project directory

What's New in V2.0:

• ✅ TypeScript plugins (hot reload support)
• ✅ Auto-activation via SessionStart hook
• ✅ 3 core plugins: PM Agent, Research, Index
• ✅ Confidence-driven workflow (≥90% threshold, Precision/Recall 1.0)

Migration Notes:

• Old: /sc:pm, /sc:research, /sc:index-repo (27 commands)
• New: /pm, /research, /index-repo (3 plugin commands)
• Functionality improved with hot reload and auto-activation

💡 Troubleshooting PEP 668 Errors

# Option 1: Use pipx (Recommended)
pipx install SuperClaude

# Option 2: User installation
pip install --user SuperClaude

# Option 3: Force installation (use with caution)
pip install --break-system-packages SuperClaude

---

💖 Support the Project

Hey, let's be real - maintaining SuperClaude takes time and resources.

The Claude Max subscription alone runs $100/month for testing, and that's before counting the hours spent on documentation, bug fixes, and feature development. If you're finding value in SuperClaude for your daily work, consider supporting the project. Even a few dollars helps cover the basics and keeps development active.

Every contributor matters, whether through code, feedback, or support. Thanks for being part of this community! 🙏

☕ Ko-fi One-time contributions

🎯 Patreon Monthly support

💜 GitHub Flexible tiers

Your Support Enables:

Item	Cost/Impact
🔬 Claude Max Testing	$100/month for validation & testing
⚡ Feature Development	New capabilities & improvements
📚 Documentation	Comprehensive guides & examples
🤝 Community Support	Quick issue responses & help
🔧 MCP Integration	Testing new server connections
🌐 Infrastructure	Hosting & deployment costs

Note: No pressure though - the framework stays open source regardless. Just knowing people use and appreciate it is motivating. Contributing code, documentation, or spreading the word helps too! 🙏

---

🎉 What's New in V2.0

Version 2.0 brings architectural transformation: migration from 27 slash commands to 3 TypeScript plugins with hot reload and auto-activation.

🤖 Smarter Agent System 16 specialized agents with domain expertise: PM Agent ensures continuous learning through systematic documentation Deep Research agent for autonomous web research Security engineer catches real vulnerabilities Frontend architect understands UI patterns Automatic coordination based on context Domain-specific expertise on demand	🔥 TypeScript Plugins 3 core plugins with hot reload: PM Agent: Confidence-driven orchestration (≥90% threshold) Research: Deep web search with adaptive planning Index: 94% token reduction (58K → 3K) Auto-activation via SessionStart hook Edit → Save → Instant reflection (no restart)
🔧 MCP Server Integration 8 powerful servers (via airis-mcp-gateway): Tavily → Primary web search (Deep Research) Serena → Session persistence & memory Mindbase → Cross-session learning (zero-footprint) Sequential → Token-efficient reasoning Context7 → Official documentation lookup Playwright → JavaScript-heavy content extraction Magic → UI component generation Chrome DevTools → Performance analysis	🎯 Behavioral Modes 7 adaptive modes for different contexts: Brainstorming → Asks right questions Business Panel → Multi-expert strategic analysis Deep Research → Autonomous web research Orchestration → Efficient tool coordination Token-Efficiency → 30-50% context savings Task Management → Systematic organization Introspection → Meta-cognitive analysis
⚡ Optimized Performance Smaller framework, bigger projects: Reduced framework footprint More context for your code Longer conversations possible Complex operations enabled	📚 Documentation Overhaul Complete rewrite for developers: Real examples & use cases Common pitfalls documented Practical workflows included Better navigation structure

---

🔬 Deep Research Capabilities

Autonomous Web Research Aligned with DR Agent Architecture

SuperClaude v4.2 introduces comprehensive Deep Research capabilities, enabling autonomous, adaptive, and intelligent web research.

🎯 Adaptive Planning Three intelligent strategies: Planning-Only: Direct execution for clear queries Intent-Planning: Clarification for ambiguous requests Unified: Collaborative plan refinement (default)	🔄 Multi-Hop Reasoning Up to 5 iterative searches: Entity expansion (Paper → Authors → Works) Concept deepening (Topic → Details → Examples) Temporal progression (Current → Historical) Causal chains (Effect → Cause → Prevention)
📊 Quality Scoring Confidence-based validation: Source credibility assessment (0.0-1.0) Coverage completeness tracking Synthesis coherence evaluation Minimum threshold: 0.6, Target: 0.8	🧠 Case-Based Learning Cross-session intelligence: Pattern recognition and reuse Strategy optimization over time Successful query formulations saved Performance improvement tracking

Research Command Usage

# Basic research with automatic depth
/research "latest AI developments 2024"

# Controlled research depth (via options in TypeScript)
/research "quantum computing breakthroughs"  # depth: exhaustive

# Specific strategy selection
/research "market analysis"  # strategy: planning-only

# Domain-filtered research (Tavily MCP integration)
/research "React patterns"  # domains: reactjs.org,github.com

Research Depth Levels

Depth	Sources	Hops	Time	Best For
Quick	5-10	1	~2min	Quick facts, simple queries
Standard	10-20	3	~5min	General research (default)
Deep	20-40	4	~8min	Comprehensive analysis
Exhaustive	40+	5	~10min	Academic-level research

Integrated Tool Orchestration

The Deep Research system intelligently coordinates multiple tools:

• Tavily MCP: Primary web search and discovery
• Playwright MCP: Complex content extraction
• Sequential MCP: Multi-step reasoning and synthesis
• Serena MCP: Memory and learning persistence
• Context7 MCP: Technical documentation lookup

---

📚 Documentation

Complete Guide to SuperClaude

🚀 Getting Started	📖 User Guides	🛠️ Developer Resources	📋 Reference
📝 Quick Start Guide Get up and running fast 💾 Installation Guide Detailed setup instructions	🎯 Plugin Commands 3 core plugin commands 🤖 Agents Guide 15 specialized agents 🎨 Behavioral Modes 7 adaptive modes 🚩 Flags Guide Control behaviors 🔧 MCP Servers 7 server integrations 💼 Session Management Save & restore state	🏗️ Technical Architecture System design details 💻 Contributing Code Development workflow 🧪 Testing & Debugging Quality assurance	- 📓 [**Examples Cookbook**](docs/reference/examples-cookbook.md) *Real-world recipes* 🔍 Troubleshooting Common issues & fixes

---

🤝 Contributing

Join the SuperClaude Community

We welcome contributions of all kinds! Here's how you can help:

Priority	Area	Description
📝 High	Documentation	Improve guides, add examples, fix typos
🔧 High	MCP Integration	Add server configs, test integrations
🎯 Medium	Workflows	Create command patterns & recipes
🧪 Medium	Testing	Add tests, validate features
🌐 Low	i18n	Translate docs to other languages

---

⚖️ License

This project is licensed under the MIT License - see the LICENSE file for details.

---

⭐ Star History

---

🚀 Built with passion by the SuperClaude community

_{Made with ❤️ for developers who push boundaries}

Back to Top ↑