Add Lang

This is a heavy automation for extending codegraph's language support. It walks through the entire pipeline: finding a tree-sitter grammar, health-checking it for ABI corruption issues, wiring it into the type system and extractor maps, writing tests, then benchmarking extraction quality and retrieval value on three real repos it picks automatically. The workflow is surprisingly concrete, right down to which files need edits and how to debug when extraction fails. It even handles edge cases like vendoring custom WASM builds when the off-the-shelf grammar is broken. You run it with `/add-lang lua` and it does everything except the final commit, leaving you a complete implementation to review. Useful if you're maintaining codegraph or a similar tool that needs repeatable language onboarding.

skills.sh installs: 1.2K
GitHub stars: 77.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add colbymchenry/codegraph --skill add-lang --agent claude-code

Installs into .claude/skills of the current project.

Files

Add a language to CodeGraph

Wire a new tree-sitter language into codegraph's extraction pipeline, prove it extracts real symbols on popular repos, and prove it beats no-codegraph for an agent. Runs fully autonomously — pick repos, benchmark, update docs, then report. Never commit, push, publish, or tag (house rule); leave all changes for the user to review.

The argument is the language token used throughout the Language union, e.g. lua, elixir, zig. If none was given, ask which language. Use the lowercase single-token form everywhere (csharp, not c#).

Prerequisites

Run from the codegraph repo root. node, git, gh, and a logged-in claude CLI (the benchmark spawns real claude -p runs).
The benchmark uses the local dev build — Step 8 builds + links it on PATH.