FixKit AI

Loop/Prompt Library / Loops from builders on X

๐Ÿ” Keep my work moving while I'm away

Every so often the AI checks your current work: it finishes open tasks, answers review comments, fixes failing checks, and cleans up when nothing else is waiting.

Use it when: You're stepping away and want your coding agent to keep handling the small stuff on one branch.

๐Ÿ›‘ Stops when: Your time window ends, or nothing is left to do. Loops also end when you close the session.

Copy this loop

Every [15] minutes, check my current branch [branch name]. In order: 1) finish any unfinished task in [TODO file]; 2) answer or fix new review comments; 3) fix failing checks; 4) fix merge conflicts. If all of that is clear, look for one small bug or cleanup and fix it. Make small changes, run the tests after each one, and never merge, deploy, or force-push. Keep a short log of what you did each round. If you get stuck on the same thing twice, write it down for me and move on. Stop after [4] hours or [16] rounds, or when there's nothing to do two rounds in a row. Leave me a summary.

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 @Kevein57257922. 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.