Compress Claude Code memory files into caveman format with backup.
npx skills add https://github.com/domattioli/DomI --skill caveman-compress-domattioli
Please help me install this Agent Skill. Skill: caveman-compress Source: https://github.com/domattioli/DomI/tree/main/plugins/caveman/caveman-compress Command: npx skills add https://github.com/domattioli/DomI --skill caveman-compress-domattioli
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to reduce per-session token costs. The compressed version overwrites the original file and a human-readable backup is saved as FILE.original.md.
Run caveman-compress on a memory file to overwrite it with a caveman-compressed version and save the original as a .original.md backup.
High-intent search queries and answers about installing and using this skill.
To reduce token usage for memory files, you can compress natural language documents like CLAUDE.md into a caveman format. This overwrites the working file with a smaller version to lower per-session token costs while preserving the original content in a .original.md backup.
Caveman format compression is a technique that condenses markdown memory files, such as todos and preferences, into a highly abbreviated syntax. This minimizes the token count loaded into Claude Code sessions, dramatically lowering per-session token costs.
You can compress markdown memory files while preserving original content by using a tool that saves a human-readable backup. The compression process overwrites the active file with the compressed version and automatically stores the original as a .original.md backup file.
Memory file compression enforces safety by refusing to process sensitive filenames. It also enforces a strict size limit and performs a two-step compression with validation, retrying up to two times to recover from partial failures and ensure safe file processing.
The best way to optimize memory files for token limits is to compress them into caveman format before loading. This approach overwrites the working file with a compressed version and preserves a human-readable backup, ensuring you stay within size limits while retaining original data.
giovannimnzCompress natural-language markdown memory files into caveman format with .original.md backups.
fableindigo-gifCompress natural language memory files into caveman format with backups.
Ikki-GroupCompress natural language memory files to reduce token usage.
joshuacookCompress session conversations into structured Markdown summaries for system memory.
