OS Reviewer
OS Reviewer is the final reviewer of an open-source contribution crew (scout, planner/orchestrator, coder). Every change the coder prepares comes to it before anything is pushed. It reads the diff and the linked issue, runs typecheck, lint and the relevant tests itself, compares failing tests against main, names the diff's blast radius and checks the repo's CONTRIBUTING rules: commit message, language, issue reference and commit author. Each verdict is either 'passt' or a short list of fixes, backed by evidence, written plainly and revised with unslop. It reviews behavior rather than implementation details and only trusts what it has proven works. It never pushes, opens PRs or comments on GitHub without the owner's explicit go, never merges and never handles secrets.
The creator's description, as published on the x.ai share page when last checked (2026-11-22). Not independently tested.
What its description mentions
Read automatically from the creator's own words and quoted below. Not a test: check the Bot's skills and routines before relying on any of it.
- Works with other Bots
OS Reviewer is the final reviewer of an open-source contribution crew (scout, planner/orchestrator, coder)
Editorial notes
From the public description, not a test. Written by Grok Bot Wiki from the share-page text; we have not run this Bot. Reviewed .
Best for
A maintainer running a multi-Bot open-source contribution setup who wants one last check before anything reaches a real pull request, catching failing tests and CONTRIBUTING violations a coder Bot might miss on its own.
Not for
Someone who wants a single all-purpose coding Bot, since this one is described as the last step in a crew with separate scout and planning Bots rather than something that works alone end to end.
What it does
Before anything is pushed, the Bot reads the proposed diff together with the issue it is meant to address, then runs its own typecheck, lint, and relevant tests rather than taking the coder Bot's word for it. It compares any failing tests against the main branch to tell a pre-existing failure from a new one, and names what its description calls the blast radius: how far the change actually reaches. It separately checks the repository's CONTRIBUTING rules, covering the commit message, language, issue reference, and author, and returns either a pass or a plain, evidence-backed list of fixes. Its description says it judges behavior rather than implementation choices, and that it never pushes, opens a pull request, comments on GitHub, or merges without the owner's explicit go-ahead.
First messages to try
- Here's the diff and the issue it's supposed to close. Run your checks and tell me if this is a pass or what needs fixing first.
- One of the failing tests might already be broken on main. Compare against main before deciding whether this diff caused it.
- Check this diff's commit message and author against our CONTRIBUTING file, and don't open anything on GitHub until I say go.
Apps and accounts
Its description mentions GitHub as where it would eventually push, open a pull request, or comment, but only with explicit approval, and it names typecheck and lint tooling it runs itself rather than a separate CI service. It does not mention handling secrets or credentials at any point.
Cautions
- A pass verdict reflects what the Bot could check automatically; a human should still skim anything touching security or data before it ships.
- Comparing failing tests against main only catches pre-existing breakage if main itself was passing; a flaky main branch can produce a misleading comparison.
Compare with: PR Reviewer by MustafaEngineering QA by Andre LeiboviciGitHub Steward by Lee Talley
Before you add it
Specific to this Bot, from what its description says:
- It describes coordinating other Bots. It can only work with Bots in your own account, so check which ones it expects and what each of them can do.
The standard checks for any shared Bot
Adding a shared Bot copies its profile, settings, enabled skills, routines, and avatar into your account. It does not copy the creator's computer, logins, conversation history, or memory. Everything it then does runs on your shared Agent Computer with your logins.
- Open the Bot's skills and routines first. Disable any routine before it fires on a schedule you did not choose.
- Check which apps it will try to sign into. Prefer plugins over browser logins, and keep sensitive accounts off the shared computer.
- Set an ask-first rule for anything that sends, posts, pays, or deletes. A listing here is not a test result.
- Give it one small bounded task and read the usage screen afterwards before scaling up.
Related reading: the shared computer permission boundaries the weekly meter
If it misbehaves: Bot not responding routines not running sign-in errors New to Grok Bot? what it is your first task
Attribution
This Bot belongs to its creator, 0xDaemon. Facts on this page (name, share link, creator, link status) were read from the public share page. The row was seeded from majiayu000/awesome-grok-bot, cs68614-hash/awesome-grokbot-templates and kydlikebtc/awesome-grokbot. Row metadata is CC0. Grok Bot Wiki is independent and not affiliated with SpaceXSI (formerly xAI).
Made this Bot? Add a “Listed on Grok Bot Wiki” badge
Optional and free. It links readers to this page and never affects how the Bot is listed. More badge styles ↗
Markdown (README)
[](https://www.grokbotwiki.com/bots/os-reviewer)
Or promote this template in the labelled Featured row, from $19.