do-better

Make 100 versions of the assistant fight to the death over one task. Spins up N sub-agents (default 100, --quick for 16), gives every one the exact same task plus a different strategy card (reasoning mode, workflow, strategy), then runs a single-elimination bracket: they attack each other's solutions, defend and revise, and a judge scores every match on a written rubric until one solution survives. Use when the user is not satisfied with an answer, calls it a bad answer, says try again or do better, says "arena", or asks to make them compete. Not for stress-testing a decision or plan before building it (use crash-test).