# codegraph

> codegraph — lzehrung-codegraph. Use this tool when you need to quickly understand a repository, assess the impact and risk of code changes, or navigate complex codebases. Codegraph provides fast answers to questions about the code and helps evaluate diff effects, making it ideal for development, review, and debugging processes. It integrates with git to analyze repositories and provide actionable insights.

Canonical page: https://skillsregistry.net/skills/lzehrung-codegraph  
JSON: https://api.skillsregistry.net/v1/skills/lzehrung-codegraph

## Description

CLI, MCP and TS library that turns source code into a map of files, symbols, references, and dependencies using tree-sitter.

## Trust

- **Trust score (0–1):** 0.63
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** other
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/lzehrung/codegraph)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "lzehrung-codegraph"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/lzehrung-codegraph` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/lzehrung-codegraph/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt