Codex Goals: A 6-Component Framework for Autonomous Agent Tasks

Claire Vo (ChatPRD) walks through Codex /goal in depth with real examples: a 5h45m autonomous run eliminating hundreds of Sentry errors, and a 4-hour job that cleaned 3,900 emails down to 68. The six-component framework for writing Goals that work: (1) outcome — what should be true when done, (2) verification — how to test it, (3) constraints — what can't regress, (4) boundaries — what tools/files to use, (5) iteration policy — how to decide what to try next, (6) stopping conditions — when to ask for help. Goals differ from prompts fundamentally: a prompt says what to do; a Goal describes what a good outcome looks like and how to verify it.