Loop/Prompt Library / Loops from builders on X
🔁 Task list with a strict reviewer
The AI takes the next task from a list, builds it with tests, and keeps fixing until a reviewer gives full marks. A separate simple step does the merge.
Use it when: You have a list of coding tasks and you're tired of copying review comments back and forth.
🛑 Stops when: Full marks and passing tests for each task, or [5] review rounds without full marks, then it stops and asks you.
Copy this loop
Take the next task from [task list file]. Make a new branch. Write the tests first, then the code. Tests and lint must pass before you ask for review. A separate reviewer scores your work from 1 to 5 against [checklist]. If it's below 5, fix each fair comment, and explain why you disagree with the rest. Repeat. You may never merge or touch the main branch yourself. When the score is 5 and tests pass, mark the task 'ready to merge' and move to the next one. If a task doesn't reach 5 in [5] rounds, stop and ask me. Stop after [3] tasks or when the list is empty.
Review every change the agent makes before you keep it. Set a budget or round limit — the prompt includes one.
Found on X · by @kunal_mugalkhod. 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.