Compress natural language memory files into a compact caveman format.
npx skills add https://github.com/huangzida/skills --skill caveman-compress-huangzida
Please help me install this Agent Skill. Skill: caveman-compress Source: https://github.com/huangzida/skills/tree/main/caveman-compress Command: npx skills add https://github.com/huangzida/skills --skill caveman-compress-huangzida
Caveman-compress reduces per-session token costs by compressing natural language memory files (CLAUDE.md, todos, preferences) into a compact caveman format while preserving all essential content and structure. The compressed file overwrites the original and a human-readable backup is saved as <filename>.original.md.
Run caveman:compress on the target memory file to produce a compressed version and a backup.
High-intent search queries and answers about installing and using this skill.
To reduce token usage in Claude memory files, compress natural language content in CLAUDE.md and todos into a compact caveman format. This removes filler text while preserving essential content, code blocks, URLs, and structure to lower per-session token costs.
The best way to compress markdown memory files without losing code blocks and URLs is using deterministic compression steps that strip filler text while preserving headings, file paths, commands, and structural elements exactly as they appear in the original document.
Compressing project memory files creates a human-readable backup saved as <filename>.original.md before the compressed version overwrites the original, ensuring data integrity and safe rollback if needed.
You can use Claude CLI or API to validate memory file compression and retry on failure. The compression process requires validation checks and retries through Claude to ensure safe, deterministic compression of memory payloads.
You need tiktoken and anthropic dependencies to run caveman compression on memory payloads. These libraries support token counting and Claude-based validation checks required for deterministic compression and retries.
Claude session startup consumes too many tokens when memory files contain verbose natural language. Compressing these files into a compact format minimizes token consumption, enabling faster startups and lower costs while preserving readability.
Ikki-GroupCompress natural language memory files to reduce token usage.
jubalmManage Claude Code project memory with structured files and Python utilities.
mifunedevEstimate token savings by comparing baseline prose to compressed forms.
vvedantbCompress Markdown memory files into caveman format with backups.
