From caveman
Compresses natural language memory files like CLAUDE.md, todos, and preferences into caveman format to save input tokens. Preserves code, URLs, paths, and structure exactly; overwrites original with backup.
How this skill is triggered — by the user, by Claude, or both
Slash command
/caveman:compressThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
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`.
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.
/caveman:compress <filepath> or when user asks to compress a memory file.
This SKILL.md lives alongside scripts/ in the same directory. Find that directory.
Run:
cd <directory_containing_this_SKILL.md> && python3 -m scripts <absolute_filepath>
backtick content)/src/components/..., ./config.yaml)npm install, git commit, docker build)$HOME, NODE_ENV)CRITICAL RULE:
Anything inside ... must be copied EXACTLY.
Do not:
Inline code (...) must be preserved EXACTLY.
Do not modify anything inside backticks.
If file contains code blocks:
Original:
You should always make sure to run the test suite before pushing any changes to the main branch. This is important because it helps catch bugs early and prevents broken builds from being deployed to production.
Compressed:
Run tests before push to main. Catch bugs early, prevent broken prod deploys.
Original:
The application uses a microservices architecture with the following components. The API gateway handles all incoming requests and routes them to the appropriate service. The authentication service is responsible for managing user sessions and JWT tokens.
Compressed:
Microservices architecture. API gateway route all requests to services. Auth service manage user sessions + JWT tokens.
npx claudepluginhub anthonystepvoy/caveman-opencode --plugin cavemanCompress natural language memory files (CLAUDE.md, todos) into caveman format to reduce token usage. Trigger with '/caveman-compress <filepath>'.
Compresses natural language memory files like CLAUDE.md, todos, and settings into primitive form to reduce input tokens, fully preserving code, URLs, technical terms, and Markdown structure. Overwrites original; saves readable backup as FILE.original.md.
Compresses LLM-facing Markdown files like CLAUDE.md and ARCHITECTURE.md for token efficiency using lossless structural optimization or lossy semantic rewriting.