Works with the AI Agents you already use
Repo Map (Context Saver)
Instantly generate an AST-based map of a Python codebase. Saves massive context tokens and stops the agent from hallucinating file paths.
$9
Repo Map (Context Saver)
Example session with this skill installed
I just cloned a new Python backend. Run the mapper on "C:\dev\backend-service" so I can see how it's structured.
- Read your context and instructions
- Compiled the repo map context
I have scanned the repository at C:\dev\backend-service using the AST mapper. Here is the structural map of the identified Python files, classes, and functions.
Repository Map
File: api/auth.py
class Authenticator(line 14)def validate_token(line 32)async def refresh_session(line 58)
File: api/routes.py
def health_check(line 10)async def get_user_profile(line 25)async def update_settings(line 42)
File: core/database.py
class DBConnection(line 8)def connect(line 20)def execute_query(line 45)
File: core/models.py
class User(line 5)class Permission(line 28)
File: utils/helpers.py
def format_timestamp(line 12)def sanitize_input(line 24)
Next steps
- Identify which classes or functions listed above relate to your current task.
- Use the provided line numbers to jump directly to the code in your editor.
- Request a full file read for only the specific modules you need to modify.
Connects securely to your tools. The creator never sees your data.
About this skill
Python codebases quickly become too large for context windows, forcing developers to manually hunt through directories. This skill maps the entire repository structure using Abstract Syntax Trees to provide a high-level overview without consuming massive token counts.
What it does AST Parsing scans Python files to identify structural elements without reading raw text. Class Mapping identifies every class definition and its exact line number. Function Discovery* lists all standard and asynchronous function definitions. Context Optimization* provides a complete repo overview while keeping the context window clear for actual coding tasks.
How it works
- Initialize the process by providing the absolute path to your local Python repository. 2.Execute the mapper script to trigger the AST traversal across all subdirectories. 3.Review the generated Markdown map to identify the file locations of relevant logic. 4.Target specific files for deeper analysis based on the class and function coordinates provided.
Frameworks & tools
The tool uses Python and the ast standard library to parse source files into tree structures.
Why this beats prompting it yourself Manual directory listing misses the internal structure of files, while asking an LLM to read every file is expensive and slow. This tool extracts specific metadata at the syntax level, giving you a precise map in seconds without the token overhead.
Use cases
- Map a new repository to understand where core logic resides.
- Locate specific function definitions during a refactoring task.
- Audit a codebase for class distribution and file density.
- Onboard onto a complex Python project by visualizing the API surface.
Known limitations This skill only supports Python files and does not scan non-Python assets or internal file contents.
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). Does not read file contents, only AST nodes (classes and functions). Requires an absolute file path to the repository.
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 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
The map is generated locally and printed to stdout — nothing is uploaded. For repos over ~50 files, use the AST version ($19) which adds call-graph edges and per-section token budgets. This $9 version is file-level only.