Loop/Prompt Library / Loops from builders on X
🔁 Same instructions, fresh start, repeat
Runs the same instructions over and over, starting the AI fresh each time, with progress saved in files instead of in the chat.
Use it when: A long job keeps running out of memory or getting confused in one long chat.
🛑 Stops when: The to-do list is empty and checked, or the round limit is hit.
Copy this loop
Before we start, write three files: [PLAN.md] (the goal and the plan), [TODO.md] (a checklist of small tasks, each with 'done when'), and [NOTES.md] (what you learned). Each round, start fresh: read all three files, pick the next unchecked task, do it, check it, tick it off, and add any lesson to NOTES.md. Then end the round. If a task fails twice, mark it 'stuck' with a reason and move on. Never merge, deploy, or delete anything. Stop when every task is ticked or marked stuck, or after [20] rounds. If you run low on memory mid-round, update the files first so the next round can pick up.
Review every change the agent makes before you keep it. Set a budget or round limit — the prompt includes one.
Found on X · by @TylerReedAI. 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.