Caveman

Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

mvanhorn Updated
Caveman Learn report: TLDR summary and savings cards on the left; ranked token sinks with an expanded fix and a session context depth histogram on the right

File contents

mvanhorn/caveman commit bd22d86b32

Frequently asked questions

npx get-skill add mvanhorn/caveman-2