Get a Second Opinion From a Different Model Family

A second session with fresh context reviews better than the one that wrote the code. A second model family reviews differently again. This is a pattern from the power-user community, not a measured result, but the logic behind it holds up.

Plugins let another model's CLI run inside Claude Code as a slash command, so a review can come from something with a different training distribution and different failure modes.

The value isn't that one model is better. It's that two models trained differently are plausibly wrong about different things, so the overlap of what neither flags is, in theory, smaller than either's blind spot alone.

Worth trying on the changes where being wrong is expensive. Treat it as a cheap second opinion, not a guarantee.