GreenPT Docs
Token compression

Caveman

A coding-agent skill that makes the agent talk like a caveman — cutting output prose tokens while keeping full technical accuracy.

Cavemanwhy use many token when few do trick. A coding-agent skill/plugin that makes the agent talk like a caveman: cuts ~75% of output tokens while keeping full technical accuracy. Brain still big. Mouth small.

Repository: github.com/JuliusBrussee/caveman

Works with Claude Code, Codex, Gemini, Cursor, Windsurf, Cline, Copilot, and 30+ more. See the repo's full install guide.

Before / after

Normal (69 tokens):

"The reason your React component is re-rendering is likely because you're creating a new object reference on each render cycle. When you pass an inline object as a prop, React's shallow comparison sees it as a different object every time, which triggers a re-render. I'd recommend using useMemo to memoize the object."

Caveman (19 tokens):

"New object ref each render. Inline object prop = new ref = re-render. Wrap in useMemo."

Same technical content, a third of the tokens.

On this page