token-budget-advisor
Offers the user an informed choice about how much response depth to consume before answering. Use this skill when the user explicitly wants to control response length, depth, or token budget. TRIGGER when: "token budget", "token count", "token usage", "token limit", "response length", "answer depth", "short version", "brief answer", "detailed answer", "exhaustive answer", "respuesta corta vs larga", "cuántos…
- installs 8w
- 1,586
- 30-day movement
- starts with the next reading
- Related entries
- 6
- Connections
- 0
An agent skill that intercepts requests before the agent answers, estimates prompt tokens and expected response size with heuristics, and offers depth options (short through exhaustive) for the user to pick. It distinguishes token-budget requests from unrelated uses of the word 'token' and shows a disclaimer since it has no real tokenizer (~85-90% accuracy, ±15% variance).
Use it when you want to decide how much of the model's response budget to spend before it answers.
Use it to
- Trigger it with phrases like 'give me the short version' or 'respond at 50% depth'
- Compare short, detailed, and exhaustive response sizes before committing
- Skip the question by stating your preferred level upfront
- Avoid firing it when 'token' means auth or payment tokens
For Users who want explicit control over response length and token usage
- Host repository
- affaan-m/ECC
- Installs, lifetime
- 2,900
- Installs, 8 weeks
- 1,586
- Host stars
- 259k
- Host language
- JavaScript