This is an early release preview. You may encounter bugs.
Tool
SuperClaude logo
Unclaimed

development

SuperClaude

Adds 30 commands, 20 agents, 7 modes, and 8 MCP integrations to Claude Code.

C 64/100 GitHub score ? This grade is derived from GitHub signals — not user votes. Open for the full breakdown.
No votes yet

01 / About

About SuperClaude.

SuperClaude is a configuration framework layered on top of Claude Code (the project notes it is not affiliated with Anthropic). Rather than adding new model capabilities, it injects behavioral instructions and a library of reusable components so that Claude Code behaves like a more structured development platform, with named commands and specialized agent roles covering the workflow from brainstorming through design, implementation, testing, and project management. The current stable line (v4.x) is installed as a Python package and works through slash commands; a TypeScript plugin system is described as planned for a future v5.0.

Its building blocks are 30 slash commands (prefixed /sc:, e.g. /sc:brainstorm, /sc:implement, /sc:test, /sc:research, /sc:pm), 20 domain-specialized agents (such as a security engineer, frontend architect, deep-research agent, and project-management agent) that coordinate automatically based on context, and 7 behavioral modes that shift how the assistant works: Brainstorming, Business Panel, Deep Research, Orchestration, Token-Efficiency, Task Management, and Introspection.

It also integrates 8 optional MCP servers, installable via its CLI, which the framework uses to extend the base experience:

  • Tavily — primary web search for Deep Research
  • Context7 — official documentation lookup
  • Sequential-Thinking — multi-step reasoning
  • Serena — session persistence and memory
  • Playwright — cross-browser automation
  • Magic — UI component generation
  • Morphllm-Fast-Apply — context-aware code modifications
  • Chrome DevTools — performance analysis

The framework is fully functional without these servers; the project describes them as an optional performance enhancement.

02 / Discussion CREDIBILITY-GATED

Discussion · 0

Reading is open to everyone. Only verified humans or builders at GitHub B+ can post or vote — every thread carries its author's credibility.

  • No discussions yet — start the first thread.

03 / Build

Build with SuperClaude.

Browse the catalogue for frameworks, tools, and blueprints — each scored on real GitHub credibility.

Browse the catalogue