* The -i flag has been removed from the `_run_command_cross_platform` function in `setup/components/mcp.py`. * fix: Prevent installer from hanging during MCP installation The SuperClaude installer was hanging during the installation of MCP components on non-Windows systems. This was caused by the use of an interactive shell (`-i`) when executing the `claude mcp add` command. The interactive shell would attempt to read from standard input, causing the process to be suspended by the shell. This commit fixes the issue by removing the `-i` flag from the `_run_command_cross_platform` function in `setup/components/mcp.py`. This ensures that the installation process runs non-interactively and completes without hanging. * fix: Add 'cmd /c' for Windows and refactor shell execution This commit resolves an issue with `npx` command execution on Windows by prepending `cmd /c` to the command. It also refactors the shell command execution for non-Windows systems to use the `executable` argument in `subprocess.run` for a cleaner and more robust implementation. * fix: Add 'cmd /c' for Windows and refactor shell execution This commit resolves an issue with `npx` command execution on Windows by prepending `cmd /c` to the command. It also refactors the shell command execution for non-Windows systems to use the `executable` argument in `subprocess.run` for a cleaner and more robust implementation. * docs: Update Chrome DevTools MCP documentation This commit updates the documentation for the Chrome DevTools MCP server to be more comprehensive and consistent with the existing documentation structure. The file `SuperClaude/MCP/MCP_Chrome-DevTools.md` has been updated with detailed information about the server's purpose, triggers, and usage examples. * docs: Update documentation for Chrome DevTools MCP This commit updates the main README.md and the MCP servers user guide to include information about the new Chrome DevTools MCP server. The documentation has been updated to reflect the new server count and provide details about the new server's functionality. * chore: Bump version to 4.1.5 This commit updates the version number from 4.1.4 to 4.1.5 across the entire codebase. This includes updates to: - CHANGELOG.md - Documentation files - Configuration files (package.json, pyproject.toml) - Source code fallbacks - The main VERSION file --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
10 KiB
🚀 SuperClaude Quick Start Guide
Context Engineering Framework for Claude Code
💡 Key Insight: SuperClaude doesn't replace Claude Code - it configures and enhances it through behavioral context injection
How It Works • Instant Start • Components • Workflows • When to Use
📊 Framework Capabilities
| Commands | AI Agents | Behavioral Modes | MCP Servers |
|---|---|---|---|
| 21 | 14 | 6 | 6 |
/sc: triggers |
Domain specialists | Context adaptation | Tool integration |
🎯 How It Works
Framework Architecture Flow
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐
│ User Input │────>│ Claude Code │────>│ Context Files │
│ /sc:command │ │ Reads Context │ │ (.md behaviors)│
└─────────────────┘ └──────────────────┘ └─────────────────┘
│ │
▼ ▼
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐
│ Enhanced │<─────│ Behavioral │<────│ MCP Servers │
│ Response │ │ Activation │ │ (if configured) │
└─────────────────┘ └──────────────────┘ └─────────────────┘
The Magic: When you type /sc:brainstorm, Claude reads behavioral instructions from installed .md files and responds with enhanced capabilities
⚡ Instant Start
5-Minute Journey from Installation to First Command
| 📦 Step 1: Install (Terminal) | 💬 Step 2: Use (Claude Code) |
|---|---|
|
|
🎥 What Happens Behind the Scenes
- Context Loading: Claude Code imports behavioral
.mdfiles viaCLAUDE.md - Pattern Recognition: Recognizes
/sc:and@agent-trigger patterns - Behavioral Activation: Applies corresponding instructions from context files
- MCP Integration: Uses configured external tools when available
- Response Enhancement: Follows framework patterns for comprehensive responses
🔧 Core Components
Four Pillars of SuperClaude
📝 Commands21Slash Commands
Workflow automation |
🤖 Agents14AI Specialists
Domain expertise |
🎯 Modes6Behavioral Modes Brainstorming Context adaptation |
🔌 MCP6Server Integration Context7 (docs) Enhanced tools |
📚 Workflow Patterns
Complete Development Lifecycle
🌟 First Project Session
| Step | Command | What Happens |
|---|---|---|
| 1. Discovery | /sc:brainstorm "e-commerce app" |
Interactive requirements exploration |
| 2. Load Context | /sc:load src/ |
Import existing project structure |
| 3. Analysis | /sc:analyze --focus architecture |
Deep architectural review |
| 4. Planning | /sc:workflow "payment integration" |
Generate implementation roadmap |
| 5. Implementation | /sc:implement "Stripe checkout" |
Build with best practices |
| 6. Validation | /sc:test --coverage |
Comprehensive testing |
| 7. Save Session | /sc:save "payment-complete" |
Persist for next session |
🎨 Domain-Specific Workflows
| Domain | Trigger | Specialist Activation | MCP Server |
|---|---|---|---|
| Frontend | UI component request | @agent-frontend |
Magic |
| Backend | API endpoint creation | @agent-backend |
Sequential |
| Security | Auth implementation | @agent-security |
Context7 |
| Testing | E2E test scenarios | @agent-qa |
Playwright |
| DevOps | Deployment setup | @agent-devops |
Morphllm |
🎯 When to Use
SuperClaude vs Standard Claude Code
| ✅ Use SuperClaude | 💭 Use Standard Claude |
|---|---|
|
Perfect for:
Examples:
|
Better for:
Examples:
|
🎓 Learning Path
Your 4-Week Journey to Mastery
| Week | Focus | Skills | Milestone |
|---|---|---|---|
| 1 🌱 |
Core Commands |
• /sc:brainstorm• /sc:analyze• /sc:implement
|
Complete first project |
| 2 🌿 |
Behavioral Modes |
• Mode combinations • Flag usage • Context optimization |
Optimize workflows |
| 3 🌿 |
MCP Servers |
• Server configuration • Tool integration • Enhanced capabilities |
Full tool utilization |
| 4 🌲 |
Advanced Patterns |
• Custom workflows • Session management • Team patterns |
Framework mastery |
💡 Key Insights
Understanding SuperClaude's Value
🧠 Not SoftwareIt's a Framework SuperClaude is behavioral configuration, not standalone software. Everything runs through Claude Code. |
🔄 SystematicNot Ad-hoc Transforms random requests into structured workflows with quality gates and validation. |
🚀 ProgressiveNot Complex Start simple with basic commands. Complexity emerges naturally as needed. |
📖 Next Steps
Continue Your Learning Journey
| 🌱 Beginner | 🌿 Intermediate | 🌲 Advanced |
|---|---|---|
|
First Week: Start with |
Growing Skills: Explore mode combinations |
Expert Usage: Create custom workflows |
🎉 Ready to Transform Your Development Workflow?
Start now with /sc:brainstorm in Claude Code!
SuperClaude v4.1.5 - Context Engineering for Claude Code