Code review

An adversarial review move: instead of asking Claude if the code is correct, ask it to actively try to break the code — enumerate the inputs, timings, and conditions under which it fails. You're recruiting the model as a red team, not a rubber stamp.

A pattern where you hand Claude an explicit checklist of what to look for — correctness, edge cases, security, readability — and ask it to go category by category, instead of an open-ended 'review this code'. The checklist is the spec for the review.