Mex — persistent project memory for AI coding agents

Mex maps your code, turns what agents learn into structured Markdown, and keeps that knowledge connected to the implementation it describes. Every coding session starts with relevant architectural context instead of another full-repository scan.

When to use this skill

• Setting up a new project scaffold for an AI-assisted codebase (mex setup)
• Building a symbol-grounded living wiki tied to exact source locations
• Establishing a ROUTER.md to guide agent context selection per task
• Keeping architectural notes, decisions, and conventions synchronized with code
• Running drift detection (mex check) to catch stale documentation
• Syncing the wiki back to code after meaningful changes (mex sync)
• Using mex as an MCP server to expose project memory to Claude Code or agents
• Migrating an existing project into a structured memory scaffold
• Grounding wiki claims to exact code graph nodes and fingerprints