Skip to main content
Deploy this agent to put a consistent review on every pull request before a human reads it. It works from the diff, sorts what it finds by whether it should stop the merge, and posts a comment per commit so each push is reviewed visibly. This page covers what it needs, how it is triggered, and where it stops.

What it does

On each push to a pull request, it reads the diff and reports what a maintainer needs to know before merging. Findings come back in three buckets, and each one names a file, a line, and the concrete consequence rather than a style preference: It comments once per commit rather than amending a single review, so the history of what was flagged and when stays readable on the pull request itself.

The verdict

The worst finding in the review decides the verdict, and the agent does not get to choose it — the buckets are what it produces, and the verdict follows from them: Finding nothing is a valid and common result. The review says so rather than padding itself with observations to look thorough.

What a review looks like

A comment with one Blocking and one Nit finding:
With nothing to report, the body is the summary followed by No blocking or should-fix findings.

What it reads

It reviews against its own rubric. There is no policy file to write and no repository convention to configure — which is the trade: consistent reviews everywhere, rather than reviews tuned per repository.

Before you deploy

The GitHub connection is required and gates the only path this agent has to GitHub. Without one it cannot read the pull request at all: it fails closed and returns a verdict saying so, rather than reviewing blind.
This agent is enabled per workspace. If it is not in your catalog, an account administrator can request it for your account.

How it is triggered

This is the one catalog agent you do not give a schedule. It is driven by the repositories bound to the review workflow, so a pull request arriving is what starts a run — there is no cron trigger to set in the wizard, and the Triggers step has nothing to collect.

Defaults and limits

The time budget degrades rather than fails: past it, the agent reports the findings it already has rather than abandoning the review.

In a workflow

It is the review step itself rather than a specialist another agent delegates to. A pull request opens or is pushed to, the step runs, and the comment lands on the pull request — the workflow’s output is visible in GitHub rather than only in the console.

What it will not do

It never casts a GitHub approval. Its verdict is reported in its own comment — “Looks good” is a verdict, not an approving review — so it cannot satisfy a branch-protection rule that requires one, and it never merges. A maintainer still reviews and merges. Posting that comment is the only thing it writes. It does not push, branch, or change a file.
A review the clock stopped never comes back as approve. Where the time budget cut a review short, an otherwise-empty result is downgraded to Comment and says plainly that it is incomplete — so “no findings” from a partial review cannot be mistaken for “nothing wrong”.
It also reviews only what the diff shows. A change that is wrong because of something in a file it did not touch is outside what the review can see — the review is a filter in front of a human, not a replacement for one.

Next steps

GitHub Agent

The same repositories, read to find the code behind an incident.

Built-in integrations

Create the GitHub connection this agent needs.

Runs & evidence

Read the reasoning behind a finding.

Agent catalog

Every catalog agent, side by side.