Every time I asked Claude to review my branch, I got one of two answers: a cheerful "Looks good! 👍" or a vague list where I couldn't tell a real bug from a matter of taste. The model wants to please you. That's exactly the problem.
So I built Tribunal — a Claude skill that reviews your diff adversarially, in stages, where the honest signal comes from agents fighting each other instead of one polite model.
The idea: don't ask one model to be fair
A single model told to "be critical" still hedges — it's trained to be agreeable. So instead of one balanced reviewer, Tribunal runs one-sided roles that collide:
One agent per file, deliberately biased. It tears the diff apart as if a clueless amateur wrote it — focused only on what changed. But strictly on the merits: correctness, races, leaks, edge cases, security. No style nitpicks.
