codegraph
Supercharges code exploration with a pre-indexed semantic knowledge graph.
Skill by tainn03
Chalk Labs
Need help deploying codegraph?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/tainn03-codegraph
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/codegraph
What's inside
- Skill name
codegraph- Description
- Supercharges code exploration with a pre-indexed semantic knowledge graph. 94% fewer tool calls, 77% faster exploration. 100% local SQLite graph DB with tree-sitter parsing for 19+ languages.
- License
- MIT
- Instructions
- 357 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# CodeGraph - Semantic Code Intelligence
## Overview
CodeGraph builds a semantic knowledge graph of codebases — symbol relationships, call graphs, and code structure — so agents query the graph instantly instead of scanning files with grep/glob/read.
```
Github Copilot CLI
│
│
Sisyphus Agent
│
┌─────────────┼─────────────┐
Explore Agent Explore Agent Explore Agent
│ │ │
└─────────────┼─────────────┘
▼
CodeGraph MCP Server
┌─────┬─────┬──────┬──────┐
Search Callers Callees Impact
└─────┴─────┴──────┴──────┘
▼
SQLite Graph DB
• 1000s of symbols, edges
• Instant lookups
• OS file watcher → auto-sync
```
## When to Use
- **Every session start** — Load `.codegraph/config.json`, check `codegraph_status`
- **Code exploration** — Instead of grep/glob/Read, use `codegraph_search`, `codegraph_context`
- **Before editing** — Use `codegraph_impact` to check what's affected
- **Trace call flow** — Use `codegraph_callers` / `codegraph_callees`
- **Understanding systems** — Delegate to Explore agents with `codegraph_explore` as primary tool
## Architecture
### How It Works
1. **Extraction** — tree-sitter parses source code into ASTs. Language-specific queries extract nodes (functions, classes, methods) and edges (calls, imports, extends, implements)
2. **Storage** — Everything goes into a local SQLite database (`.codegraph/codegraph.db`) with FTS5 full-text search
3. **Resolution** — After extraction, references are resolved: function calls → definitions, imports → source files, class inheritance, and framework-specific patterns
4. **Auto-Sync** — The MCP server watches your project using native OS file events. Changes are debounced (2-second quiet window), filtered to source files only, and incrementally synced
### File Structure
```
<project-root>/
└── .codegraph/
├── codegraph.db # SQLite graph database
└── config.json # Indexing configuration
```
## Installation & Setup
### Quick Install
```bash
npx @colbymchenry/codegraph
```
### Manual Setup
```bash
npm install -g @colbymchenry/codegraph
```
Add to `~/.mcp.json`:
```json
{
"mcpServers": {
"codegraph": {
"type": "stdio",
"command": "codegraph",
"args": ["serve", "--mcp"]
}
}
}
```
### Initialize Projects
```bash
cd your-project
codegraph init -i # Interactive init + index
```
That's it. When `.codegraph/` exists, CodeGraph tools are available.
## MCP Tools Reference
| Tool | Purpose | Use In |
|------|---------|--------|
| `codegraph_search` | Find symbols by name across the codebase | Main session (lightweight) |
| `codegraph_context` | Build relevant code context for a task | Explore agent (primary) |
| `codegraph_callers` | Find what calls a function | Main session (lightweight) |
| `codegraph_callees` | Find what a function calls | Main session (lightweight) |
| `codegraph_impact` | Analyze what's affected by changing a symbol | Main session before edits |
| `codegraph_node` | Get details about a specific symbol (optionally with source code) | Main session (lightweight) |
| `codegraph_files` | Get indexed file structure (faster than filesystem scanning) | Main session (lightweight) |
| `codegraph_status` | Check index health and statistics | Session start |
## CLI Reference
```bash
codegraph # Run interactive installer
codegraph install # Run installer (explicit)
codegraph init [path] # Initialize in a project (--index to also index)
codegraph uninit [path] # Remove CodeGraph (--force to skip prompt)
codegraph index [path] # Full index (--force to re-index, --quiet for less output)
codegraph sync [path] # Incremental update
codegraph status [path] # Show statistics
codegraph query <search> # Search symbols (--kind, --limit, --json)
codegraph files [path] # Show file structure (--format, --filter, --max-depth, --json)
codegraph context <task> # Build context for AI (--format, --max-nodes)
codegraph affected [files...] # Find test files affected by changes
codegraph serve --mcp # Start MCP server
```From tainn03/oh-my-copilot, MIT.
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 17, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/tainn03/oh-my-copilot
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from tainn03
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get codegraph running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
codegraph skill. Agent Mart. https://agentmart.dev/skills/tainn03-codegraph (last updated 2026-10-24)