- Code Review is a multi-agent Claude Code tool to resolve any AI-generated code issues
- Token-based pricing typically results in a $15-25 fee, Anthropic says
- 84% of large pull requests had issues flagged, an average of 7.5 results
In response to ongoing investigations that question the accuracy of AI coding tools, particularly the security and privacy information of their output, Anthropic has launched a new tool to review code in GitHub pull requests.
Code Review for Claude Code uses multiple agents to maximize accuracy, searches for “logic errors, security vulnerabilities, broken edge cases, and subtle regressions” (via support documentation).
The tool will then highlight any findings as inline comments with a summary comment on the pull request to help developers more clearly identify any issues.
The article continues below
Code Review is Claude’s answer to unsafe AI-generated code
Anthropic also noted that the agents verify results and rank issues by severity to reduce false positives, while also cross-referencing with the entire codebase as context, not just the diff.
Pricing for the new tool is token-based, but Anthropic said a typical pull request will cost on average around $15-25 depending on size and complexity. A review will usually take about 20 minutes, but again, this is only a guide.
The timing of this new feature launch is also not insignificant – Anthropic says that code output per engineer has grown 200% in the past year with a significant increase in vibe coding and there is now a clear bottleneck in the review process.
Anthropic also claims to use Code Review for Claude Code on almost every pull request internally, and it has seen great success from the tool. Early data shows that 84% of large pull requests (1,000+ lines) contain results, averaging 7.5 issues, while small pull requests (under 50 lines) still average 0.5 issues, with 31% of them receiving comments.
The company emphasized the tool’s accuracy and also added that fewer than 1% of reported issues continue to be rejected by human developers.
Code Review is currently available as a research preview for Claude Teams and Enterprise plans – Anthropic didn’t share details about a wider rollout, but we expect that to come over time.
Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews and opinions in your feeds. Be sure to click the Follow button!
And of course you can too follow TechRadar on TikTok for news, reviews, video unboxings, and get regular updates from us on WhatsApp also.
