How to get picked for code review by coding agents
Claude Code review took 19% of 526 judged code review sessions. What the numbers say a vendor in this category should do.
If you sell code review tools, this page is the part of the market no dashboard shows you: what a coding agent does when a developer asks for code review and never compares vendors.
The numbers come from 526 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code, spread across 10 realistic codebases, with every session read by a judge.
What coding agents choose for code review
Across 526 judged sessions, Claude Code review was chosen most often, in 19% of runs. Cursor Bugbot was second with 17%.
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Claude Code review | 102 | 19% |
| 2 | Cursor Bugbot | 91 | 17% |
| 3 | CodeRabbit | 88 | 17% |
| 4 | Qodo Merge | 55 | 10% |
| 5 | Codex code review | 44 | 8% |
| 6 | Built in-house (no product adopted) | 40 | 8% |
| 7 | GitHub Copilot code review | 31 | 6% |
| 8 | Semgrep | 22 | 4% |
| 9 | SonarQube | 18 | 3% |
| 10 | reviewdog | 13 | 2% |
Full board, every run replayable: the code review leaderboard.
What the shape of this category means
The leader takes only 19% of runs. This category is genuinely open and the ordering can be moved.
With the top product at 19%, code review is decided in the moment, from what the agent reads and what it finds in the repository. Nothing is locked in, which is the best situation a vendor can be in and the one where the work pays fastest.
The order here is set by the quality of what an agent can read and by whether your product is already present in the codebase. Both are things you can change.
The agents do not agree with each other
In this category Claude Code, Codex and Cursor did not put the same product first.
Grok Build CLI (30 sessions) and Muse Code (86 sessions) join this table with fewer runs, so read their rows as indicative.
| Agent | Runs | Picked most often |
|---|---|---|
| Claude Code | 130 | Claude Code review (101) |
| Codex | 160 | CodeRabbit (46) |
| Cursor | 120 | Cursor Bugbot (91) |
| Grok Build CLI | 30 | Qodo Merge (10) |
| Muse Code | 86 | CodeRabbit (17) |
That split decides where a vendor spends. In this category Codex ran a web search in 100% of its sessions and Claude Code in 32%, so what you publish reaches nearly all of Codex's code review sessions and about a third of Claude Code's. Taking CodeRabbit's position with Codex is mostly a content problem. Taking Claude Code review's with Claude Code leans more on the repository.
Who is asking changes the answer
Every request in this experiment was written as a specific kind of person. In this category the leader changes with the person.
| Who is asking | Runs | Picked most often |
|---|---|---|
| Vibe coder | 106 | Claude Code review |
| Junior developer | 164 | Cursor Bugbot |
| Senior engineer | 106 | CodeRabbit |
| Enterprise team | 150 | Qodo Merge |
That is 4 different products winning code review for 4 kinds of buyer, out of the same 526 sessions. Nobody here is winning code review. They are each winning one kind of buyer.
If you sell to more than one of them, you need pages for each. See how to win the enterprise persona.
What you are really competing against
In 8% of runs the agent wrote the code itself rather than adopting a product. That is low enough that your competition is other vendors, but high enough to be worth watching.
Considered, and never chosen
Because the judge records every product an agent raised and not only the one it picked, this board also shows who kept reaching the shortlist and losing. In code review the clearest case is Codacy: on the table in 20 sessions, chosen in none.
| Product | Raised in | Chosen in |
|---|---|---|
| Codacy | 20 sessions | 0 |
Being rejected is a better position than being unknown, and a cheaper one to fix. The product is already in the agent's head and on the list. Whatever ended those 20 sessions is recorded in each transcript, one reason at a time.
What to do about it in code review
- Treat the ordering as movable. The leader holds 19%, so agents are deliberating rather than defaulting, and the inputs they use can change the answer. This is the most winnable shape a category comes in.
- Pick which buyer you are for. The same code review need written as a vibe coder landed on Claude Code review, and written as an enterprise team landed on Qodo Merge. Those are two markets, and the enterprise one needs pages containing the constraint words: audit log, data residency, retention, single sign-on. See how to win the enterprise persona.
- Measure per agent. Claude Code put Claude Code review first, Codex put CodeRabbit first, Cursor put Cursor Bugbot first, Grok Build CLI put Qodo Merge first, Muse Code put CodeRabbit first. A blended number for code review describes a market that does not exist.
The work that applies to every category rather than to this one is written up separately: audit your documentation, write a quickstart an agent can follow, and how to measure install share.
Every code review tool on this board
One page per product, with its install share, the per-agent split, and how often it was raised without being chosen.
- Do coding agents recommend Claude Code review? — chosen in 19% of sessions
- Do coding agents recommend Cursor Bugbot? — chosen in 17% of sessions
- Do coding agents recommend CodeRabbit? — chosen in 17% of sessions
- Do coding agents recommend Qodo Merge? — chosen in 10% of sessions
- Do coding agents recommend Codex code review? — chosen in 8% of sessions
- Do coding agents recommend GitHub Copilot code review? — chosen in 6% of sessions
- Do coding agents recommend Semgrep? — chosen in 4% of sessions
- Do coding agents recommend SonarQube? — chosen in 3% of sessions
- Do coding agents recommend reviewdog? — chosen in 2% of sessions
- Do coding agents recommend Cursor SDK? — chosen in 0% of sessions
Where these numbers come from
526 judged sessions in code review across 10 codebases, part of a published set of 15,051. Real coding agents at pinned versions, in sandboxes, inside realistic codebases, with a simulated project owner in the loop and a blind judge on every session. The full method is on one page: how we measured this.
Every code review run can be replayed on the board.
<!-- generated by scripts/write-data-pages.mjs -->
Common questions
How many codebases is this based on?
526 judged sessions across 10 realistic codebases. A category only runs on repositories where its seam is open, so coverage differs: some categories ran on more than ten codebases and some on two.
What code review tool do coding agents choose?
Across 526 judged sessions, Claude Code review was chosen most often, in 19% of runs. Cursor Bugbot was second with 17%. The result changes by agent and by who is asking.
Do Claude Code and Codex pick the same code review tool?
No. Claude Code picked Claude Code review, Codex picked CodeRabbit, Cursor picked Cursor Bugbot. Measuring one agent tells you about part of the market only.
How often do agents build code review themselves instead of installing something?
In 8% of runs the agent wrote the code itself rather than adopting a product.
How can a vendor improve its position here?
Make the quickstart run when pasted, state the current version on the documentation page, use one name across product, package and import, write pages for the symptoms users describe rather than only the category name, and get into the repository through templates and framework integrations.
Which code review tools do agents consider but never choose?
Codacy (raised in 20 sessions, chosen in none). Being considered and not chosen is a different problem from being unknown, and it is usually fixable.
Where this comes from
Armature ran 15,051 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 92 realistic codebases, and published every run. The numbers on this page come from that work.