After burning 2B tokens, dev open-sources Leader.skill to turn vague human asks into agent task briefs
浪费20亿Token后,我开源了帮Agent定义目标的Leader.skill
Leader.skill uses a '7-goal-question' method to turn vague human requests into multi-hour agent task briefs covering purpose, completion state, anti-cheating, and boundaries. The author recommends Claude Fable 5 or Kimi K3 for planning, and GPT-5.6 Sol or GLM-5.2 for long-run execution. The project is open-sourced, but the post doesn't break down the 2B-token experiment or its cost.
Why it matters: After burning 2 billion tokens, the author open-sourced Leader.skill, using seven goal questions to turn a vague idea into a task brief an agent can run for hours, covering purpose, acceptance, anti-cheating and boundaries.