It runs locally, YOU review all the code locally, and feedback that to Claude.
Agents reviewing AI code always felt dirty to me, especially when working on production (non-disposable) code.
It leaves the comments as markdown files in ./.code-review, so I also have my `/review` agent set to output in the same format, so an LLM can be reviewing the same code I am, I can edit or dismiss the LLM's reviews, then send the whole thing back to the first agent to fix.
As in, if you have a large screen, a particularly-trained/prompted AI can organize the code changes in a "flowchart" with floating windows you can easily follow
Maybe in this UI, each code piece also comes with a summary from an agent that has already auto-reviewed the whole PR and creates a basic summary (instructed to be neutral but surface issues if it finds any).
Having said that, I don't review the code until going through a few iterations of reviews from Claude. Each round it does find some "obvious" issue, so as long as I'm not close to maxing my subscription for the week I let it run an audit -> validator checks the claims -> fix issues before I get to it.
TUI-based reviews on it's own are already interesting. I had never considered it, I guess.