SuperClaude Framework 🤖 Agent Free

What it does

SuperClaude is a configuration framework that adds a structured development process to Claude Code. It installs a family of /sc: slash commands, specialist agents and behavioural modes that steer how Claude plans, researches, implements and tests, so a session follows a more repeatable workflow than free-form prompting. The project states that it is not affiliated with Anthropic.

What is inside / how it works

The current stable release (v4.x) ships 30 slash commands covering the lifecycle from brainstorming to deployment, including /sc:brainstorm, /sc:implement, /sc:test, /sc:research and /sc:pm, plus /sc to list them all. Twenty agents add domain focus, such as a PM agent that documents lessons learned, a deep research agent, a security engineer and a frontend architect. Seven behavioural modes change Claude's approach for brainstorming, multi-expert business analysis, deep research, orchestration, token efficiency, task management and introspection. The deep research feature plans multi-hop web searches and scores source confidence. Everything works through injected instructions and command files rather than a separate runtime.

Works with

Claude Code. The framework can optionally install up to eight MCP servers to extend it: Tavily for web search, Context7 for documentation, Sequential Thinking, Serena, Playwright, Magic, Morphllm Fast Apply and Chrome DevTools.

How to install or start

The recommended route is the Python package, then the command installer:

pipx install superclaude
superclaude install
superclaude mcp --list
superclaude doctor

Restart Claude Code afterwards. A git clone plus ./install.sh also works. A Claude Code plugin-marketplace install is announced for v5.0 but is not available yet, so ignore older docs that describe it.

Pricing

Free and open source under the MIT licence, with optional donations through Ko-fi, Patreon and GitHub Sponsors. Some optional MCP servers, such as Tavily, are third-party services with their own accounts and limits.

Who should use it

Claude Code users who want ready-made workflows and commands instead of building their own. The trade-off is added context from the injected instructions, and some features now overlap with Claude Code's native skills, subagents and plan mode, so it suits people who prefer an opinionated, all-in-one setup.