reasoning-effort-throttle

SKILLWorkflowcommunity
v0.0.0NeeeophyteeNOASSERTIONUpdated 1mo agoSource →

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 st

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
18Repo stars
1Clients
1Formats
1mo agoLast update
Skill
AuthorNeeeophytee
Version0.0.0
LicenseNOASSERTION
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor
Copilot
ChatGPT
Gemini
About

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.

Keywords
skillclaude