Use Case
CodeGraph is a powerful AI agent skill that extends your assistant with new capabilities. Pre-indexed code knowledge graph for Claude Code, Codex, Cursor, Gemini, and other AI agents. Instead of repeatedly grepping and reading files, CodeGraph parses your codebase once into a structured map of functions, classes, imports, and call relationships β so agents navigate with fewer tool calls and far less token spend. Supports 19+ languages, works 100% locally, integrates via CLI, MCP, or Agent Skill. This guide walks you through installing CodeGraph, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install CodeGraph: npx clawhub@latest --dir ~/.claude/skills install codegraph
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to ai agent to trigger CodeGraph
Review the output and refine your prompt for better results
Combine CodeGraph with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing CodeGraph
Help me get started with CodeGraph
What can CodeGraph do for my ai agent workflow?
Show me an example of using CodeGraph
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install codegraphOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install codegraphβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/codegraph/π‘Extract and place the folder at the path above, then restart your agent.