caveman-compress

Name: caveman-compress
Availability: InStock
Author: shirulot

Compress natural language in Markdown files while preserving code blocks and file paths.

Updated Jul 6, 2026

Search Tags:#markdown #optimization #claude #efficiency #compression #tokens

Ready to run

npx skills add https://github.com/shirulot/codex-skill --skill caveman-compress-shirulot

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: caveman-compress
Source: https://github.com/shirulot/codex-skill/tree/main/caveman-compress
Command: npx skills add https://github.com/shirulot/codex-skill --skill caveman-compress-shirulot

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires tiktoken, anthropic, and includes scripts (resource) components.

What problem does it solve?

This skill addresses the high token cost of large project memory files like CLAUDE.md that are loaded into every AI session, reducing context overhead by compressing natural language while preserving technical integrity.

Core Features & Use Cases

Intelligent Compression: Uses caveman-speak to reduce token usage by approximately 46% while keeping instructions, code, and structure intact.
Safety-First Validation: Automatically validates compressed output against the original to ensure headings, code blocks, URLs, and file paths remain unchanged.
Use Case: If your project documentation or todo lists are growing too large, use this skill to compress them into a smaller, token-efficient format that maintains the exact same instructions for the AI.

Quick Start

Run the caveman-compress skill on your CLAUDE.md file to reduce its token footprint while keeping a human-readable backup.

Frequently Asked Questions about caveman-compress

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I reduce token usage in my markdown memory files during AI sessions?▼

You can reduce markdown token usage by compressing natural language into a concise caveman format. This minimizes input token consumption during AI sessions while preserving code blocks, file paths, and technical structure.

What is the best way to compress project documentation without losing technical structure?▼

Compressing project documentation via a multi-stage validation process ensures headings, code blocks, URLs, and file paths remain unchanged. This caveman-speak conversion achieves approximately 46% token reduction without losing technical structure.

Does compressing markdown files to save tokens affect code blocks and file paths?▼

Compressing markdown files to save tokens does not affect code blocks and file paths. The process strictly preserves technical integrity, automatically validating compressed output against the original to ensure structural elements remain identical.

How do I safely compress a CLAUDE.md file without losing original instructions?▼

To safely compress a CLAUDE.md file, run a caveman-speak compression skill that provides automated backups for all modified files. It validates compressed output against the original, ensuring instructions remain exactly the same for the AI.

Can I use tiktoken to optimize markdown efficiency for large project memory files?▼

You can use tools leveraging tiktoken and anthropic dependencies to optimize markdown efficiency for large project memory files. They target project documentation, reducing context overhead by approximately 46% while maintaining automated backups.