Reasoning Effort Throttle

Stop paying for deep reasoning on easy turns by setting a modest default reasoning effort and escalating per task. Use when the user runs a reasoning model in an agent and the bill is dominated by output or thinking tokens, or asks about reasoning_effort, thinking budgets, or why a cheap model is still expensive to run.

neeeophytee Updated 81 repo stars
AI Cost-Cutter Skills. Cut your AI bill with proof, not vibes.

File contents

neeeophytee/ai-cost-cutter-skills commit 0ee7a632fd

Frequently asked questions

npx get-skill add neeeophytee/reasoning-effort-throttle