Loop/Prompt Library / Planning & second-opinion review
🔁 Done means proven
Writes down every requirement and the proof needed before starting, so half-done work is never reported as done.
Use it when: A long AI task could look finished when it is not, like a PR that never reached production.
🛑 Stops when: Every requirement has fresh, solid proof. Otherwise the work stays open.
Copy this loop
Before starting [task], list every required outcome and the proof each needs (e.g. 'PR merged: link', 'live site shows X: screenshot'). After each step, mark each item proven, weak, missing, or contradicted. Only call the task done when every item is proven. Work in at most [10] steps. Otherwise stop as blocked or out of budget. Finish with a requirement-to-proof table and the next action.
Review every change the agent makes before you keep it. Set a budget or round limit — the prompt includes one.
Idea from Forward Future's Loop Library · by 3goblack (@Dis_Trackted). Prompt rewritten in plain English by FixKit AI.
More loops like this
Turn an idea into a clear plan
Interviews you about a rough idea, then writes two files: what to build, and how the AI should build and check it.
Make the plan buildable
Fills gaps in a new project's planning docs until two reviewers would build the same thing from them.
Spec review rounds
Writes a spec for one ticket, has a tough reviewer check it against a rubric, and keeps fixing until it is approved.
Devil's advocate review
Has one AI argue your design is wrong, logs every objection, and makes the builder fix or justify each one with proof.
Two AIs must agree
Takes turns having AIs from two different companies review your work until both approve the exact same version.
Builder + tough reviewer (Claude and Codex)
Claude builds and opens a pull request, Codex reviews it harshly, Claude fixes, and they repeat until it passes.