34 entries. Jake, Don, David on isolated piles, then a panel. This one was hard. A few of you built things that would have won a different competition, and you should hear which one. Every entry got feedback, link at bottom of post! 📋 What we actually judged The post asked for one folder a stranger can drop into a Claude project. identity.md, rules.md, examples.md, reference/, README.md. It reads something broken and says why. Not how to fix it. Four questions, from the post: 1. Does it diagnose? One cause. Not a list. Not a prescription. 2. Is the domain specific enough to be useful? 3. Does each file do one job? 4. Can a stranger figure it out? That is an outcome. Can a person who is not already in your head use this to see why something in their world broke. A lot of the field went further. Refusal paths. Verifiers. Blind runs. Preserved failures. Those are real, and they are extra. We did not pick a winner on the extra. We picked a winner on the ask. If the outcome had been different, the name on this post changes. 🥇 Winner: Colm Whelan — Inbox Autopsy https://github.com/RockfieldIT/inbox-autopsy A stranger holding a bounced invoice can drop the folder in and see why it bounced. That was the assignment. 🔄 Where someone else wins 🔧 If the outcome was "the instrument that can prove itself wrong" — Sergey Manevitch, Radix https://github.com/sergeymanevitch/Radix Why a machine failed in a plant that already has notifications, rounds, and historian trends. Fourteen cold runs. He left the breaks in his own claims standing. A plant engineer is holding something serious. 🧪 If the outcome was "every claim reproduced, including the one that failed" — Pemmy Broke, Visual Momentum https://github.com/hoodwanders/visual-momentum-diagnostician Why an AI explainer lost momentum. She published the run that broke her own doctrine, changed the rules, and the re-run abstained. That is the standard the rest of the field should steal from.