Give your agent this
Paste one of these into any AI assistant — ChatGPT, Claude, Grok, Copilot, whatever you already use. Both point at the same instructions.
Read https://ratchet.babzlabz.com/agents.md and help me fill in the Ratchet Loop Generator for this project: <describe your project>
If your assistant cannot browse the web, paste the contents of
/agents.md into the conversation instead.
What it tells them
The document is written for a machine, so it is blunt and specific. It covers:
- All six fields — what each needs, what format, and which are optional.
- The formatting that changes behaviour. More than about three bullet points in the goal makes the tool pick the most expensive tier, which is right for a big multi-part project and wasteful for a small one.
- Reference rules learned the hard way. Direct image files beat gallery pages, because galleries lazy-load and screenshot as blank thumbnails. Some sites serve a bot check instead of the page, which screenshots perfectly and is worthless. A gallery folder often returns “not found” while the images inside it work fine.
- How to write the one check that is yours. One property per entry, never two joined with “and”, and something binary beats something subjective.
- What a token cap really does — fewer improvements, not a half-built thing.
- An output format, so what comes back is ready to paste rather than an essay.
Why this exists
The generator has six fields and most of them are optional, which makes it easy to fill in badly. The expensive mistakes are not obvious ones: a reference that looks fine but returns a bot-check page, an invariant that quietly tests two things at once, a bulleted goal that buys ten times the machinery the project needs.
Those are exactly the mistakes an assistant can catch for you, if it knows the rules. So the rules are written down in one place, in a form a machine can read.
One thing to tell it about references
An agent that cannot reach the web will happily invent plausible-looking URLs. Ask it to say which references it actually verified, and treat the rest as guesses. The generator will now tell you when a capture came back as a bot check or a missing page — the reference shows as “not the page” rather than quietly succeeding — but it is cheaper to catch that before you start a run than after.