Cloud code review

Before you ship, it helps to have a second set of eyes — or a hundred. Cloud code review sends your branch off to a fleet of agents that hunt for real bugs in parallel, then reports what they found back to your terminal or desktop. It's a thorough, on-demand review of your changes that runs while you do something else, and it catches the kind of correctness mistakes that are easy to miss reading your own work.

Reading your own changes for bugs is hard — you already know what you meant, so your eye slides right past the mistake. Cloud code review brings in reinforcements: it bundles up your branch, hands it to a fleet of bug-hunting agents running in the cloud, and they comb through it in parallel looking for real correctness problems. The findings come back to your terminal or desktop as a list you can actually work through.

The everyday version is /code-review, which reports correctness bugs in the current diff. When you want the heavy artillery — a broad, multi-agent sweep — /code-review ultra (also claude ultrareview for CI and scripts) launches the cloud fleet and delivers its findings back automatically. Either way it runs off your machine, so you start it and carry on; you’re not stuck watching it.

Think of it as the review pass before the review pass: it won’t replace a teammate’s judgment, but it clears out the obvious-in-hindsight mistakes first, so the humans spend their attention on the things that actually need a human.

/code-review

/code-review ultra

claude ultrareview