byneeeophytee· 18 skills
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.
$npx -y skills add neeeophytee/ai-cost-cutter-skills --skill reasoning-effort-throttleInstalls into the current project.
Run `npx skills use "https://github.com/neeeophytee/ai-cost-cutter-skills" --skill "neeeophytee/ai-cost-cutter-skills/reasoning-effort-throttle"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/neeeophytee/ai-cost-cutter-skills" that are relevant to the current task. Run `npx skills add "https://github.com/neeeophytee/ai-cost-cutter-skills"` and select the relevant skills, then follow their instructions.