Caveman Compress Purpose Data leaves the machine. Compression sends the file's full text to the model provider that is configured for: the CLI, the Anthropic API, or an OpenAI-compatible endpoint. Files whose names look like secrets ( , , , , …) are refused before they are read. 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 , but NOT beside the source file — it lives in an out-of-tree data dir ( , or on Windows) s…