Loop/Prompt Library / Loops from builders on X
🔁 Wake up on an event, end with a ready-to-review change
Instead of chatting back and forth, something happening (a new issue, a failed check, an alert) starts the AI, and it ends by handing you one change to review.
Use it when: The same kinds of events keep needing the same kind of work from you.
🛑 Stops when: A change with evidence is ready for your review, or the try limit is hit and it writes up what it found.
Copy this loop
When [event, e.g. 'a new bug report is filed with the label X'] happens: read it, find the cause in the code, and show the evidence. Make a small fix on a new branch with a test that proves it. Open a change request (pull request) that explains the cause, the fix, and how you tested it. Score your own fix from 0 to 100 against [checklist]; if it's under [90], improve it, at most [5] tries. Never merge, deploy, or reply to users. Stop when the change request is open, or after 5 tries (then post your notes on the issue for me instead). Then wait for the next event.
Review every change the agent makes before you keep it. Set a budget or round limit — the prompt includes one.
Found on X · by @N01ennn. 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.