token-sisyphus

Use when the user asks to "burn tokens", "consume tokens", "fill my KPI", "push the boulder", "sisyphus mode", or wants to burn a specific token count.

Burn LLM tokens toward a target count to satisfy corporate AI usage KPIs. Trigger when user says: burn tokens, consume tokens, fill KPI, push the boulder, sisyphus mode, or specifies a token target like "burn 100k tokens". Supports OpenAI, Claude, Gemini, and any OpenAI-compatible API.