An agent saying "done" is the least reliable part of the run. What do you check ?

I kept hitting the same thing: a coding agent finishes, says it's done, and the tests were either never run or still red. The summary was confident either way. So the actual work wasn't writing code — it was checking up on it.

foolscap is what came out of that. You give it a task, GPT-6 Astra plans it and dispatches Claude Code, Codex or OpenCode on your machine, then a deterministic evidence engine — not a model — reads what the test command actually printed and decides whether the run passed. Two rules that do most of the work:

• repairs are capped (two for implementation, one after review), so it can't grind forever

• the review is dispatched to a different agent family, read-only, because an agent shouldn't sign off on its own work

A run from yesterday: implement failed 1 test → one repair → 1 passed → independent review on Codex → complete. Six turns, eight cents, every step on the record.

Honest limits: the desktop build is Linux-only right now (macOS and Windows run it with npx foolscap), and the cloud version is a waitlist, not a product.

What I actually want to know: when an agent tells you it's finished, what do you look at first? Test output, the diff, git status, or do you just re-run it yourself? I'd like to know whether the check I automated is the one other people are doing by hand.