🚀 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

Project-Local Plugin (Recommended)

SuperClaude v2.0+ uses TypeScript plugins with project-local auto-detection:

# Clone repository
git clone https://github.com/SuperClaude-Org/SuperClaude_Framework.git
cd SuperClaude_Framework

# Start Claude Code in this directory
claude

That's it! .claude-plugin/ is auto-detected and PM Agent activates on session start.

Key Features:

✅ Zero Install: No copying, no configuration
✅ Hot Reload: Edit TypeScript → Save → Instant reflection
✅ Auto-Activation: PM Agent starts automatically (SessionStart hook)
✅ Safe Development: Separate sandbox from global Claude Code

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. Use new plugin (project-local)
cd SuperClaude_Framework
claude  # .claude-plugin/ auto-detected

What's New in V2.0:

✅ TypeScript plugins (hot reload support)
✅ Project-local detection (zero install)
✅ 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)
Installation: Global ~/.claude/commands/ → Project-local .claude-plugin/
Just cd to project directory and run claude

💡 Troubleshooting

Plugin not loading?

# Verify you're in the project directory
pwd  # Should show: /path/to/SuperClaude_Framework

# Check .claude-plugin/ exists
ls .claude-plugin/plugin.json

# Restart Claude Code in this directory
claude

Commands not working (/pm, /research, /index-repo)?

Ensure you started claude from the SuperClaude_Framework directory
Check for errors in Claude Code output
Verify .claude-plugin/plugin.json has correct structure

Hot reload not working?

Edit .claude-plugin/pm/index.ts
Save file
Changes should reflect immediately (no restart needed)

Development mode (for contributors):

# Install Python package for testing
make install
make verify
uv run pytest

💖 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 ↑

Name		Name	Last commit message	Last commit date
Latest commit History 297 Commits
.claude		.claude
.github		.github
docs		docs
plugins/superclaude		plugins/superclaude
scripts		scripts
skills/confidence-check		skills/confidence-check
src/superclaude		src/superclaude
.env.example		.env.example
.gitignore		.gitignore
.pre-commit-config.yaml		.pre-commit-config.yaml
AGENTS.md		AGENTS.md
CHANGELOG.md		CHANGELOG.md
CLAUDE.md		CLAUDE.md
CODEOWNERS		CODEOWNERS
CODE_OF_CONDUCT.md		CODE_OF_CONDUCT.md
CONTRIBUTING.md		CONTRIBUTING.md
DELETION_RATIONALE.md		DELETION_RATIONALE.md
LICENSE		LICENSE
MANIFEST.in		MANIFEST.in
Makefile		Makefile
PARALLEL_INDEXING_PLAN.md		PARALLEL_INDEXING_PLAN.md
PLUGIN_INSTALL.md		PLUGIN_INSTALL.md
PROJECT_INDEX.json		PROJECT_INDEX.json
PROJECT_INDEX.md		PROJECT_INDEX.md
PR_DOCUMENTATION.md		PR_DOCUMENTATION.md
QUALITY_COMPARISON.md		QUALITY_COMPARISON.md
README-ja.md		README-ja.md
README-kr.md		README-kr.md
README-zh.md		README-zh.md
README.md		README.md
SECURITY.md		SECURITY.md
TEST_PLUGIN.md		TEST_PLUGIN.md
VERSION		VERSION
package.json		package.json
pyproject.toml		pyproject.toml
setup.py		setup.py

License

Spantree/SuperClaude_Framework

Folders and files

Latest commit

History

Repository files navigation