The best test I know for agent written code: delete the implementation and see if the tests fail. If they still pass, they were never testing anything.
Agents love writing tests that only check the code runs and not that it is right. Add one rule to your rules file. Make every test prove a behavior, not an implementation detail.
That single rule has caught more broken agent code than anything else I have tried.
source & further reading
dev.to — original article
Algorithm of War: How Sensor Fusion and Autonomy Are Redefining the Battlefield
AGENTS.md, explained for teams that actually ship
Generating your agent rules from one file does not stop them drifting