Caveman Compress

Compresses markdown memory files into caveman-speak to cut token usage while preserving all code blocks, URLs, and technical terms exactly. Overwrites the original with compressed version and saves a readable backup as FILE.original.md. Removes articles, filler words, and verbose phrasing but keeps structure intact. The compression process runs through a Python CLI that validates output and retries on errors. Good for trimming bloated CLAUDE.md files or todo lists without losing technical substance. Works only on natural language files, never touches actual code.

install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.: 12
skills.sh installs: 428.9K
GitHub stars: 118.7K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add juliusbrussee/caveman --skill caveman-compress --agent claude-code

Installs into .claude/skills of the current project.

Files

Caveman Compress

Purpose

Data leaves the machine. Compression sends the file's full text to the model provider that scripts/compress.py is configured for: the claude CLI, the Anthropic API, or an OpenAI-compatible endpoint. Files whose names look like secrets (.env, credentials, secrets, .netrc, …) are refused before they are read, and a file whose text holds a credential (a private key block, or a cloud, Git host or model API token) is refused before anything is sent. Don't compress a file the provider shouldn't see.

Compress natural language files (CLAUDE.md, todos, preferences) into caveman-speak to reduce input tokens. Compressed version overwrites original. Human-readable backup saved as <filename>.original.md, but NOT beside the source file — it lives in an out-of-tree data dir ($XDG_DATA_HOME/caveman-compress/backups/<parent-dir-name>/, or %LOCALAPPDATA%\caveman-compress\backups\<parent-dir-name>\ on Windows) so skill auto-loaders don't re-ingest it as a live file.