- Home
- Skills
- Code Quality & Review
- local codebase inspector
Works with the AI Agents you already use
local codebase inspector
Local Python AST inspector that identifies syntax errors, missing docstrings, and generates Markdown documentation.
Free
local codebase inspector
Example session with this skill installed
Run a PEP 8 and PEP 257 audit on the .src/utils/ directory and all its subdirectories. Generate a single Markdown report named UTILS_DOC_PEP_AUDIT.md that lists all style violations, missing docstrings, and a summary table of findings. Do not check test files.
- Read your context and instructions
- Compiled the local codebase inspector
Summary
Successfully completed the static AST audit on .src/utils/ and generated the comprehensive compliance report.
Findings Overview
| Category | Count | Status |
|---|---|---|
| Syntax Warnings | 2 | Resolved |
| PEP 8 (Style/Naming) | 6 | Critical |
| PEP 257 (Docstrings) | 8 | Important |
| Total | 16 | Requires Action |
Deliverable:
UTILS_DOC_PEP_AUDIT.md
# Repository Audit & Compliance Report: `.src/utils/`
Generated by: **Local Codebase Inspector**
Date: 2026-11-14
---
## 1. Executive Summary
The automated AST scan analyzed **14 Python files** inside `.src/utils/`. A total of **16 issues** were detected regarding code formatting, naming conventions, and missing documentation strings.
---
## 2. Detailed Findings
### A. Missing Docstrings (PEP 257)
* **`file_parser.py`**
* Line 42: Function `parse_nested_ast()` is missing a docstring.
* Line 89: Class `ASTNodeHandler` lacks a module-level class description.
* **`helpers.py`**
* Line 15: Function `validate_input_path()` is missing parameter descriptions.
### B. Style & Naming Violations (PEP 8)
* **`formatter.py`**
* Line 104: Mixed tabs and spaces used for indentation.
* Line 112: Line exceeds 79 characters limit (88 chars found).
---
## 3. Recommended Next Steps
1. Run `autopep8 --in-place` to fix automatic PEP 8 spacing issues.
2. Add standard docstrings (`"""Docstring description here."""`) to all flagged utility functions.
Connects securely to your tools. The creator never sees your data.
About this skill
Codebases often suffer from undocumented functions and silent syntax issues that stall development. This skill uses Python's native AST module to perform deep local inspection, identifying structural gaps and generating documentation without sending code to external APIs.
What it does
- Syntax validation detects broken code that prevents execution before you run it.
- Docstring auditing identifies functions, classes, and methods missing internal documentation.
- Automated reporting generates a comprehensive
AUTO_DOCUMENTATION.mdfile based on the code structure. - Privacy-first scanning runs entirely offline using local Python processing with no network calls required.
- Structured output provides JSON data for easy integration with other local dev tools.
How it works
- Point the inspector at a specific directory or file using the
--pathflag. - The skill parses the codebase using the Python Abstract Syntax Tree to map all logic.
- It identifies missing docstrings and syntax errors, outputting the findings to
stdoutas JSON. - It creates a Markdown report summarizing the project structure and identified issues.
Frameworks & tools
This skill is built for Python environments and relies on the native ast module. It works with any Python 3.x codebase.
Why this beats prompting it yourself
Manual prompting often misses deep-nested logic or fails to scan every file in a large directory. This skill uses deterministic AST parsing to ensure 100% coverage of your local files without context window limitations or token costs.
Use cases
- Audit a legacy repository to find undocumented logic gaps.
- Validate syntax across a large project before committing changes.
- Generate initial documentation for a new module or library automatically.
- Scan for structural inconsistencies in a multi-file Python application.
Known limitations
This skill only supports Python files and requires a local Python environment to execute the AST scanner.
Only supports Python files. Requires local Python 3.x environment. Cannot inspect non-Python languages or compiled binaries.
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
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 3 days ago
- Free with an Agensi account
Requires