Do coding agents recommend Claude Code review?
Claude Code review is the most chosen code review tool, taking 26% of 290 judged code review sessions. Measured with Claude Code, Codex and Cursor.
Claude Code review is the most chosen code review tool, taking 26% of 290 judged code review sessions. It was also raised as a candidate in 4 further sessions without being chosen.
This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in code review inside a realistic codebase. Not what a chat assistant says about Claude Code review. What an agent actually installed.
The numbers
| Category | Code review |
| Sessions in the category | 290 |
| Sessions where Claude Code review was chosen | 76 |
| Install share | 26% |
| Rank in category | 1 of 10 |
| Codebases it won in | 9 |
| Raised as a candidate, not chosen | 4 |
| Chosen when considered | 95% |
| Site | anthropic.com |
By agent
The three agents treat Claude Code review very differently. Claude Code chose it in 76% of its sessions in this category and Codex in 0%, a spread of 76 points.
| Agent | Sessions | Chose Claude Code review | Share |
|---|---|---|---|
| Claude Code | 100 | 76 | 76% |
| Codex | 100 | 0 | 0% |
| Cursor | 90 | 0 | 0% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Codex, your real position here is 0%, not 26%.
By who was asking
Claude Code review performs similarly across the four kinds of buyer, from 22% to 34%. That is unusual: the category leader changed with the persona in 17 of the 21 categories we measured.
| Who is asking | Sessions | Chose Claude Code review | Share |
|---|---|---|---|
| Vibe coder | 58 | 20 | 34% |
| Junior developer | 116 | 26 | 22% |
| Senior engineer | 58 | 13 | 22% |
| Enterprise team | 58 | 17 | 29% |
What Claude Code review was up against
The full ranking in code review, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Claude Code review (this page) | 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% |
What this means
Leading a category is a position to defend rather than a result to celebrate. In our data, leaders lose ground in exactly two situations: when the person asking is an enterprise buyer with procurement constraints, and when a competitor's documentation is easier for an agent to integrate correctly.
The defence is unglamorous. Keep the quickstart running. Keep the version current on the page. Keep the names aligned. Stay in the templates.
Where these numbers come from
The 290 sessions in code review are part of a published set of 5,915, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every code review run can be replayed on the board.
If you work on Claude Code review: the judge recorded a reason for every session where it was raised and passed over. Those reasons are in the transcripts.
<!-- generated by scripts/write-data-pages.mjs -->
Common questions
Do coding agents recommend Claude Code review?
Yes. Claude Code review was chosen in 76 of the 290 judged sessions in code review, a 26% install share, ranking first in its category.
Does Claude Code recommend Claude Code review?
In 76 of the 100 sessions in code review run with Claude Code, which is 76%.
Do different coding agents treat Claude Code review differently?
Yes, and by a wide margin. Claude Code chose it in 76% of its runs and Codex in 0%.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 56 realistic codebases and asked to solve real tasks. A simulated project owner approved or questioned each recommendation before any code was written, and a judge from a model family that builds none of the agents read every session blind.
How often is Claude Code review considered but not chosen?
It was raised as a candidate in 4 sessions without being chosen, and chosen in 76. That is a 95% conversion from considered to chosen.
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.