Loop/Prompt Library / Loops from builders on X
๐ Make the AI run your checks
Writes down the checks you normally do by hand, so the AI runs them after every change and must fix any failure before it moves on.
Use it when: You keep catching the same mistakes by hand after the AI says it's done.
๐ Stops when: All your checks pass after the latest change, or it gets stuck on the same failure twice.
Copy this loop
Here are the checks I usually run by hand after a change: [build, tests, type check, open the page and look at X]. Turn each one into a command or step you can run yourself. Add them to [project instructions file or hooks] so they run after every change you make. From now on, after each change: run every check. If one fails, fix it before doing anything else. Do not skip, weaken, or delete a check to make it pass. If the same check fails twice in a row for the same reason, stop and show me the error. Stop when all checks pass, or after [10] fix rounds. Show me the list of checks you set up.
Review every change the agent makes before you keep it. Set a budget or round limit โ the prompt includes one.
Found on X ยท by @ClaudeDevs. Prompt rewritten in plain English by FixKit AI.
More loops like this
One useful thing every night
You give the AI a short mission, and each night it picks one task that moves you closer and leaves it for you to check in the morning.
Two watchers keep your agent healthy
Two separate AI helpers read your main agent's logs, find what broke, and must both agree on a fix before it is used.
Weekly skill cleanup
Once a week, the AI grades every saved skill or saved prompt it uses, removes the dead ones, and merges the repeats.
Overnight drafts that learn from results
Each night the AI drafts tomorrow's post from your content plan, and reads your notes about what worked before it writes the next one.
Split the work, keep only what passes
Splits a big job across several AI helpers working side by side, checks each one's work, and keeps only the work that passes.
Practice a website task until it's reliable
The AI tries a website chore, learns from each failed try, and keeps adjusting until it has steps that work every time.
