Claude Code gets tool for checking code

"The new feature for Claude Code assigns a team of agents to every opened PR. The agents search for bugs in parallel, filter out false positives, and rank issues by severity. The result appears as a single overview comment, along with inline comments on specific bugs. The scale of the review adapts to the size of the PR."

"For large PRs with more than 1,000 changed lines, the system identifies findings in 84% of cases, averaging 7.5 issues. For small PRs under fifty lines, that drops to 31%, with an average of 0.5 issues. Less than 1% of findings are judged incorrect by engineers. The percentage of PRs with substantial review comments rose from 16% to 54%."

"Code Review is more expensive than lighter-weight alternatives such as the existing Claude Code GitHub Action, which remains open source. Reviews are billed based on token usage and cost an average of $15 to $25, depending on the size of the PR. Administrators can set monthly budget limits, restrict reviews to specific repositories, and track costs via an analytics dashboard."

Code review has become a bottleneck as code output per engineer increased 200% while review capacity stagnated. Claude Code Review addresses this by deploying a team of AI agents to analyze each pull request in parallel, searching for bugs, filtering false positives, and ranking issues by severity. The system scales analysis depth based on PR size, with large changes receiving more thorough examination. Results appear as overview and inline comments. Anthropic's internal testing shows the system identifies issues in 84% of large PRs (over 1,000 lines) with an average of 7.5 bugs found, while maintaining less than 1% false positive rate. Reviews average twenty minutes and cost $15-$25 per PR, with configurable budget limits and repository restrictions.

Read at Techzine Global