TokenDiet by Fortytude — free, open-source LLM-cost audit for your codebase. Type /tokendiet and your own agent finds where your code overpays for AI API calls (missing prompt caching, uncapped retries, prompt bloat, no batching) and hands you a concrete fix plan. Runs locally on your agent; nothing leaves your…
Audit your codebase for wasteful, expensive LLM API usage and get a concrete plan to cut the cost — cache, batching, model routing, retry caps, prompt bloat. Runs on your own agent, in your own repo. Free & open source. TokenDiet by Fortytude.
Audit this codebase for wasteful LLM API spend and hand back a concrete, honest fix plan — missing prompt caching, uncapped retries, prompt bloat, no batching, overpowered models. Describes technical waste and published provider rates only; never fabricates a dollar figure. Trigger on requests like "audit my LLM…
Instructions for Fortytude/TokenDiet: When you reason about LLM / token cost in this repo, apply the /tokendiet discipline — describe technical waste, never fabricate the dollars.
TokenDiet honesty contract for LLM cost. Apply whenever the conversation is about LLM API cost, spend, token usage, prompt caching, batching, model choice/downgrade, or "how much will this save." Enforces: describe technical waste + published provider rates only, NEVER a fabricated dollar total.