Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Repo Map Generator (AST)

    1

    Stop letting your AI agent read every file in your repository just to find one function.

    $19

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Repo Map Generator (AST)

    Repo Map Generator (AST)

    Example session with this skill installed

    Generate a structural map for the repository at ./src/payment_gateway and save it to repo_structure.md so we can plan the API integration.

    • Read your context and instructions
    • Compiled the repo map generator

    Generated a high-level structural map of the Python codebase using AST parsing. The map includes all classes, functions, and their respective line numbers, now saved to repo_structure.md.

    Repo Map: ./src/payment_gateway

    File: src/payment_gateway/client.py

    • class PaymentClient (line 14)
    • def __init__ (line 18)
    • def create_charge (line 25)
    • def capture_payment (line 42)

    File: src/payment_gateway/models.py

    • class Transaction (line 5)
    • class Customer (line 22)

    File: src/payment_gateway/utils/crypto.py

    • def encrypt_payload (line 8)
    • def verify_signature (line 15)

    File: src/payment_gateway/exceptions.py

    • class GatewayError (line 4)
    • class AuthenticationError (line 8)

    Next steps

    1. Review repo_structure.md to identify which files require deep inspection.
    2. Use the line numbers to jump directly to target functions for refactoring.
    3. Keep this file updated as you add new modules to the source tree.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Stop letting your AI agent read every file in your repository just to find one function.

    The Repo Map Generator uses Python's Abstract Syntax Tree (ast) to scan a local folder and output a clean Markdown list of every file, class, and function (with line numbers).

    Why use it?

    Save Tokens: Reduce context usage by 90%.

    Stop Hallucinations: The agent knows the exact file and line number to open.

    Save to File: Use the --output flag to save the map directly to REPO_MAP.md so the agent can read it without blowing its context window.

    Perfect for Claude Code, Cursor, or any agent working on large codebases.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.

    Only supports Python files (.py). Required local execution access to the repository path. Does not parse logic inside functions or variable definitions.

    How to use

    1. 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. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    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 2 days ago

    Software
    Python

    Produces a full AST map: files, classes, function signatures, import chains, call-graph edges, and per-section token budgets. For smaller repos or a quick overview, the $9 Repo Map (Context Saver) is enough; this $19 version is for repos where the file-level map loses the call structure.

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listed2 days ago
    Updatedtoday

    What's inside

    Frequently Asked Questions

    By mapping the repository's structure via AST rather than raw text, the skill provides a condensed index of all classes and functions, allowing your agent to understand the architecture without consuming thousands of tokens on boilerplate code.

    This skill is designed to work with any AI agent or LLM that has access to your local file system, making it an ideal preprocessing step for tools like AutoGPT, Open Interpreter, or custom coding assistants.

    The skill specifically targets Python (.py) files using the native Abstract Syntax Tree library; it will skip configuration files, documentation, and code written in other languages like JavaScript or C++.

    The output is a structured Markdown file that acts as a "GPS" for your code, listing every class, method, and function along with their exact line numbers for quick navigation.

    Setup is minimal; as long as you have Python 3.x installed, you simply point the skill to your project directory to begin the automated scanning and indexing process.

    New in LLM Ops