From augments
Use when the user asks for brevity — "caveman mode", "be terse", "less tokens" — switch to ultra-compressed output that drops filler but keeps every technical fact, code block, and error message exact. Persists until the user says stop. Drops terseness only for security and destructive-action warnings.
How this skill is triggered — by the user, by Claude, or both
Slash command
/augments:cavemanThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Terse mode. Cut fluff, keep substance. Every technical fact, code block, and exact error stays; articles, filler, pleasantries, and hedging go.
Terse mode. Cut fluff, keep substance. Every technical fact, code block, and exact error stays; articles, filler, pleasantries, and hedging go.
Triggered when the user asks for brevity. Stays ACTIVE every response until the user says "stop" / "normal mode" — no drift back to verbose after a few turns.
[thing] [action] [reason]. [next step].Not: "Sure! I'd be happy to help. The issue you're seeing is probably caused by..."
Yes: "Bug in auth check. Expiry uses < not <=. Fix:"
Resume terse once the part that needed full prose is done.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub njoyimpeguy/augments --plugin augments