python-repomix
🥈Silverpython-repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, and Gemini.
154170Updated 3mo ago
Intermediate30min to implementautomation
Saves ~120 min per use
Quick InstallView Source
git clone https://github.com/AndersonBY/python-repomix.gitWorks with:
Claude
Overview
About This Skill
python-repomix is a Python tool that consolidates your entire repository into a single, structured file designed for consumption by Large Language Models. It handles multiple directories, respects .gitignore and .repomixignore files, and includes built-in security scanning to detect sensitive information. The tool provides token counting via tiktoken, supports code compression, and offers multiple output formats including markdown and JSON. It works with local directories, remote repositories, and specific Git branches, making it ideal for developers who need to share codebases with AI systems or integrate repository context into AI-powered development workflows.
How to Use
[{"step":1,"action":"Install python-repomix in your project environment: `pip install python-repomix`","tip":"Ensure you're in the root directory of your project before running the tool."},{"step":2,"action":"Run python-repomix to generate the combined file. Use flags to exclude unnecessary files: `python-repomix --output combined_codebase.txt --exclude tests/ .venv/ *.log`","tip":"Use `--verbose` to see which files are being processed in real-time."},{"step":3,"action":"Review the generated file for sensitive data (e.g., API keys, passwords). Use the prompt template to analyze the file for entry points, dependencies, and issues.","tip":"For large projects, split the analysis into chunks (e.g., by module) to avoid token limits in AI tools."},{"step":4,"action":"Refactor the codebase based on the analysis. Address any hardcoded secrets or deprecated functions before sharing the file with an LLM.","tip":"Use `grep -r \"TODO\" combined_codebase.txt` to find areas needing improvement."},{"step":5,"action":"Share the cleaned file with your AI tool for further analysis, debugging, or documentation generation.","tip":"If using Claude, upload the file directly or paste its contents into the chat."}]
Use Cases
Feed entire codebases to Claude, ChatGPT, or Gemini for code analysis and generation
Prepare repository snapshots for AI code review and documentation generation
Package multiple project directories for LLM-based refactoring and architecture planning
Create compressed, AI-optimized exports of remote repositories without cloning
Setup & Installation
Quick Install
No install command available. Check the GitHub repository for manual installation instructions.
Alternative Install (Git Clone)
git clone https://github.com/AndersonBY/python-repomixRequirements
- Claude Code or compatible AI agent
- Works with: Claude
Quick Start Guide
1
Install the Skill
Copy the install command above and run it in your terminal.
2
Open Your AI Agent
Launch Claude Code, Cursor, or your preferred AI coding agent.
3
Try It Out
Use the prompt template or examples below to test the skill.
4
Customize
Adapt the skill to your specific use case and workflow.
Usage Examples
Prompt Template
Use python-repomix to combine the entire codebase of [PROJECT_NAME] into a single file. Include all Python files, configuration files (e.g., requirements.txt, pyproject.toml), and documentation (e.g., README.md). Exclude [FILES_TO_EXCLUDE, e.g., test files, large binary assets, or virtual environment folders]. After generating the file, analyze it to identify: 1) the main entry points of the project, 2) key dependencies, and 3) any potential issues like hardcoded secrets or deprecated functions. Save the output as [OUTPUT_FILENAME].
Example Output
```
# python-repomix generated file for project 'data-pipeline' (v1.2.0)
# Generated on 2024-05-15 | Excluded: tests/, .venv/, *.log
## Project Structure Summary
- **Main Entry Points**: `src/main.py` (CLI), `src/api/server.py` (FastAPI)
- **Key Dependencies**: pandas==2.0.3, fastapi==0.95.2, sqlalchemy==2.0.15
- **Critical Files**: `config.yaml` (DB credentials masked), `src/utils/helpers.py`
## File Contents
### src/main.py
```python
import sys
from src.pipeline import run_pipeline
from src.api.server import start_server
def main():
if '--serve' in sys.argv:
start_server()
else:
run_pipeline(config_path='config.yaml')
if __name__ == '__main__':
main()
```
### src/pipeline/transform.py
```python
import pandas as pd
from src.utils.helpers import validate_schema
def transform_data(raw_df: pd.DataFrame) -> pd.DataFrame:
"""Standardize and clean raw data."""
# Hardcoded threshold (TBD: move to config)
threshold = 0.85
return raw_df[raw_df['quality_score'] > threshold]
```
### config.yaml
```yaml
# Database credentials (masked for AI review)
# REAL VALUE: db_password: "s3cr3t!"
db_password: "[REDACTED]"
```
## Analysis Results
1. **Entry Points**: CLI (`main.py`) and API (`server.py`) are clearly defined.
2. **Dependencies**: All critical packages are pinned in `requirements.txt`.
3. **Issues Detected**:
- `transform.py` hardcodes a quality threshold (0.85). Suggest moving to `config.yaml`.
- `config.yaml` contains a placeholder `[REDACTED]` for a password. Recommend using environment variables.
## Recommendations
- Refactor `transform.py` to read thresholds from config.
- Replace hardcoded secrets with `os.getenv()` calls.
```Apply to these tools
Browse all tools
Gemini
Google's multimodal AI model and assistant
Claude
AI assistant built for thoughtful, nuanced conversation
Microsoft Teams
Get more done every day with Microsoft Teams – powered by AI
GPT for work
Automate your spreadsheet tasks with AI power
Respell
Agentic AI Workflow platform
Notion
Connected workspace for docs, wikis, and projects
Compatible MCP servers
Browse all MCP servers
Find the right skills for your stack
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan