Stop prompting
your agents.
Design the loops
that prompt them.
Copy-paste loop templates for AI coding agents — Claude Code, Codex and OpenClaw — each with a goal, a cron trigger, a verify step, an exit condition and a real token cost.
Agent loop templates
Every loop ships as a spec sheet plus runnable code. Read the verify step before you trust the loop — that's where the engineering is.
Content refresh loop
livePages that lost rank in Search Console are rewritten and re-indexed.
Test-fix loop
liveThe full test suite passes twice in a row.
Keyword discovery loop
liveThe content queue always holds at least 10 briefed keywords with search demand.
Dependency upgrade loop
liveAll dependencies are within one minor version of latest, with green CI.
Scrape-and-validate loop
liveEvery source is scraped, validated against schema, and loaded.
Issue triage loop
liveNo issue sits unlabeled for more than 15 minutes during work hours.
The loop engineering format — seven fields, one standard
Every loop on this site is written in the same seven-field format, so you can audit any loop in under a minute.
Goal
One sentence. What "done" means, stated so a model can judge it.
Trigger
Cron expression or event. When the loop wakes up.
Discover
Where tasks come from — a queue, a diff, an API, a board.
Act
The agent call. Model, tools, and the prompt the loop writes for it.
Verify
The automated check that gates every cycle. Tests, lint, rank data.
Persist
State that survives the run — markdown file, board, or table.
Exit
The condition that stops the loop. No exit, no loop — just a bill.
Running a loop we haven't catalogued?
Submit it in the seven-field format. We test-run every loop before it's listed, and credit you on the template page.