Codebase Digest — AI skill for Claude Code
🗜️ Codebase-digest is your AI-friendly codebase packer and analyzer.
How to install Codebase Digest
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open kamilstanuch/codebase-digest and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Codebase Digest does
🗜️ Codebase-digest is your AI-friendly codebase packer and analyzer. Features 60+ coding prompts and generates structured overviews with metrics. Ideal for feeding projects to LLMs like GPT-4, Claude, PaLM, and Gemini for code analysis and understanding.
Alternatives in AI
- Repomix — 📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file 22.7k ★
- Ccstatusline — by sirmalloc - A highly customizable status line formatter for Claude Code CLI that displays model info, git b 5.5k ★
- Gh PR Review — GitHub CLI extension that adds full inline PR review comment support — view, navigate, reply to, and resolve r 174 ★
README
Codebase Digest
[](https://badge.fury.io/py/codebase-digest) [](https://opensource.org/licenses/MIT)
Codebase Digest is a command-line tool written in Python that helps you analyze and understand your codebase. It provides a structured overview of your project's directory structure, file sizes, token counts, and even consolidates the content of all text-based files into a single output for easy analysis with Large Language Models (LLMs).

Table of Contents
- Features
- Installation
- Usage
- Configuration
- Ignore Functionality
- LLM Prompts for Enhanced Analysis
- Contributing
- License
Features
- 📊 Directory Tree Visualization: Generate a hierarchical view of your project structure
- 📈 Codebase Statistics: Calculate total files, directories, code size, and token counts
- 📄 File Content Consolidation: Combine all text-based files into a single output
- 🚫 Flexible Ignore System: Support for custom patterns, defaults, and
.gitignorefiles - 🎨 Multiple Output Formats: Choose between text, JSON, Markdown, XML, or HTML
- 🌈 Colored Console Output: Visually appealing and informative summaries
- 🧠 LLM Analysis Support: Comprehensive prompt library for in-depth codebase analysis
Installation
Via pip (Recommended)
pip install codebase-digest
From source
git clone https://github.com/kamilstanuch/codebase-digest.git
cd codebase-digest
pip install -r requirements.txt
Usage
Basic usage:
cdigest [path_to_directory] [options]
Examples:
Analyze a project with default settings:
cdigest /path/to/my_projectAnalyze wi
Related Skills
Yt Video Analyzer
A Claude Code skill that turns a YouTube video into a digest with timestamps and interface screenshots. Subtit
Video To LLM Context Extractor
Turn any video into a detailed, LLM-ready PDF document. Perfect for feeding visual and transcribed context int
Ideal AI Colleague
Onboard your AI agent like a new hire: a work agreement (CLAUDE.md) and output style for Claude Code, so it as
Searchstack Aeo
Searchstack — Open-source AEO/GEO/SEO tech stack for AI-native founders. Monitor your visibility across Google
SEO Geo
GEO and AI search specialist. Analyzes AI crawler accessibility, llms.txt compliance, passage-level citability
Octoroute
Smart HTTP router for local LLMs (Ollama, LM Studio, llama.cpp). Rule-based + LLM-powered routing, health chec
Related Agents
Narwhal Geo
GEO/LLMO specialist for the narwhal audit — visibility in AI answer engines (ChatGPT, Claude, Perplexity, Goog
SEO Geo
GEO and AI search specialist. Analyzes AI crawler accessibility, llms.txt compliance, passage-level citability
Search Issues
gh search issues --repo {owner/repo} "llms.txt OR AI-friendly OR LLM documentation OR AI context" --limit 20 g