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: A solid agent engineering write-up that distills hard-won lessons into a reusable '7 Questions' framework and open-sources it — directly useful for practitioners building agent workflows. Score held back because the post doesn't disclose the 2B-token experiment details, and it...