- Home
- Skills
- Code Quality & Review
- 🕸️ Codebase Graph
More screenshots
Works with the AI Agents you already use
🕸️ Codebase Graph
It parses your project's directory structure, imports, and configuration files to build a comprehensive dependency model.
$25
🕸️ Codebase Graph
Example session with this skill installed
Analyze this repository's structure to identify the main entry points, check for circular dependencies, and find any unused files or core architectural modules.
- Read your context and instructions
- Compiled the codebase graph
📦 Entry Points: src/main.ts
🔄 Cycles Detected: src/auth.ts -> src/user.ts -> src/auth.ts
⚠️ Dead Code: src/utils/legacy-formatter.ts (0 inbound refs)
🚀 Core Modules: src/app.ts (Centrality: 0.82)
Refactor: Split 'auth.ts' types to break the circular dependency with 'user.ts'.
Connects securely to your tools. The creator never sees your data.
About this skill
What it does
The Codebase Graph skill transforms complex, unfamiliar repositories into interactive visual maps and structured onboarding guides. It parses your project's directory structure, imports, and configuration files to build a comprehensive dependency model. Unlike manual inspection, it automatically identifies how data flows through your application, pinpointing where execution starts and where bottlenecks or technical debt reside.
Why use this skill
Onboarding a new developer or planning a major refactor can take days of manual code tracing. This skill automates that process by providing a high-fidelity graph that reveals hidden relationships between modules. It goes beyond simple file-tree views by detecting circular dependencies, identifying likely dead code, and ranking modules by their "centrality" to the architecture. It's an essential tool for developers who need to understand a large codebase quickly without getting lost in the weeds.
Supported tools
- Languages: Multi-language support including TypeScript, JavaScript, and Python.
- Parsing: Uses AST-based analysis and framework-native metadata (like package.json) for high accuracy.
- Visualization: Generates a standalone, interactive D3.js force-directed graph.
- Reports: Produces detailed Markdown summaries including entry points and refactor suggestions.
First run on large codebases (10k+ files) may take 30-60 seconds. Generated graph can be large; use filters to reduce complexity. Dynamic imports and reflection-based dependencies may be missed. Python's dynamic typing limits call graph accuracy.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 5 months ago
Requires
Permissions
File Scopes
Codebase Graph needs terminal access to run language parsers (esprima for JavaScript/TypeScript, tree-sitter for Python/Go/Java/Rust). These are read-only parsers that extract structural information from source files. File read access allows the skill to scan directories and read source code to analyze imports, exports, class inheritance, and function call dependencies. Only reads files with supported extensions; ignores binary files and node_modules. File write access creates HTML visualization files and markdown summaries in a `./code-graph/` directory. All output files are safe to gitignore. The skill never modifies source code. No browser, network, or environment variable access is required. The generated HTML graph is self-contained and runs locally.