# codegraph

> codegraph — isink17-codegraph. Use this tool when you need to efficiently navigate and analyze large codebases, solve problems like symbol lookup and impact analysis, and discover related tests. Codegraph takes in source code from repositories and outputs a lightweight graph database, providing a simple interface for high-signal tools and semantic search. It is ideal for use in local development environments with Git-based workflows.

Canonical page: https://skillsregistry.net/skills/isink17-codegraph  
JSON: https://api.skillsregistry.net/v1/skills/isink17-codegraph

## Description

codegraph is a local-first code context engine and MCP server for repositories. It incrementally indexes source code into a lightweight SQLite graph, then exposes high-signal tools for symbol lookup, call graph traversal, impact analysis, related test discovery, and semantic search. Built in Go with a single-binary workflow, it is designed to work

## Trust

- **Trust score (0–1):** 0.88
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/isink17/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": "isink17-codegraph"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/isink17-codegraph` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/isink17-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