How to get picked for code review by coding agents
Claude Code review took 26% of 290 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 290 judged sessions with Claude Code, Codex and Cursor, spread across 10 realistic codebases, with every session read by a judge.
What coding agents choose for code review
Across 290 judged sessions, Claude Code review was chosen most often, in 26% of runs. Cursor Bugbot was second with 24%.
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Claude Code review | 76 | 26% |
| 2 | Cursor Bugbot | 71 | 24% |
| 3 | Codex code review | 37 | 13% |
| 4 | CodeRabbit | 34 | 12% |
| 5 | Qodo Merge | 24 | 8% |
| 6 | Built in-house (no product adopted) | 19 | 7% |
| 7 | Semgrep | 10 | 3% |
| 8 | GitHub Copilot code review | 9 | 3% |
| 9 | SonarQube | 6 | 2% |
| 10 | Greptile | 2 | 1% |
Full board, every run replayable: the code review leaderboard.
What the shape of this category means
The leader takes only 26% of runs. This category is genuinely open and the ordering can be moved.
With the top product at 26%, 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 the three agents we ran put different products first.
| Agent | Runs | Picked most often |
|---|---|---|
| Claude Code | 100 | Claude Code review (76) |
| Codex | 100 | Codex code review (37) |
| Cursor | 90 | Cursor Bugbot (71) |
That split decides where a vendor spends. Codex ran a web search in 53% of decision runs and Claude Code in 1.6%, so the pages you publish are live in half of Codex's code review sessions and almost none of Claude Code's. Taking Codex code review's position with Codex is a content problem. Taking Claude Code review's with Claude Code is a repository problem.
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 | 58 | Claude Code review |
| Junior developer | 116 | Cursor Bugbot |
| Senior engineer | 58 | CodeRabbit |
| Enterprise team | 58 | Claude Code review |
That is 3 different products winning code review for 4 kinds of buyer, out of the same 290 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 7% 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 Danger: on the table in 22 sessions, chosen in none.
| Product | Raised in | Chosen in |
|---|---|---|
| Danger | 22 sessions | 0 |
| reviewdog | 22 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 44 sessions is recorded in each transcript, one reason at a time.
What to do about it in code review
- Aim at second place first. Claude Code review holds 26% and Cursor Bugbot holds 24%. The gap between the default and the field is where the reachable sessions are.
- Report install share per persona, not as one number. In code review the leader changes with who is asking, so a blended figure averages markets that behave differently.
- Measure per agent. Claude Code put Claude Code review first, Codex put Codex code review first, Cursor put Cursor Bugbot 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 26% of sessions
- Do coding agents recommend Cursor Bugbot? — chosen in 24% of sessions
- Do coding agents recommend Codex code review? — chosen in 13% of sessions
- Do coding agents recommend CodeRabbit? — chosen in 12% of sessions
- Do coding agents recommend Qodo Merge? — chosen in 8% of sessions
- Do coding agents recommend Semgrep? — chosen in 3% of sessions
- Do coding agents recommend GitHub Copilot code review? — chosen in 3% of sessions
Where these numbers come from
290 judged sessions in code review across 10 codebases, part of a published set of 5,915. 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?
290 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 290 judged sessions, Claude Code review was chosen most often, in 26% of runs. Cursor Bugbot was second with 24%. 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 Codex code review, 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 7% 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?
Danger (raised in 22 sessions, chosen in none), reviewdog (raised in 22 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 5,915 judged sessions with Claude Code, Codex and Cursor inside 56 realistic codebases, and published every run. The numbers on this page come from that work.