Claude Code Review in Production: How Our Review Rules Evolved Over Five Months

说明与用途

Claude 代码审查从单一提示演变为包含六个专门代理和验证器的 playbook，消除了误报，仅审查更改行，并确保每个发现引用规则。

问题

Automated code review produced false positives, reviewed unchanged code, and lacked rule citations, leading to noisy feedback and blocking legitimate changes.

结果

The evolved workflow reduced false positives, prevented reviews of legacy code, ensured every finding cited a rule, and introduced a verifier to drop unprovable findings, improving trust and precision.

工作流

• Listen for PR events or @claude comment
• Load only rule documents relevant to changed file paths
• Review only added or modified lines
• Assign severity based on rule type (BLOCKING, WARNING, SUGGESTION)
• Route each file to its specialist reviewer
• Collect findings in fixed format
• Verifier checks file existence, code quote proximity, diff inclusion, and rule validity
• Post findings as inline comments and GitHub review (request changes if any BLOCKING)

证据

Claude Code review started at my company as a single prompt in a GitHub workflow, and five months later it is a playbook, six specialist agents and a verifier that throws out any finding it cannot prove.

来源

The next rewrite introduced three ideas that are still the backbone of the system.

来源

The verifier is the Claude Code review agent I would copy first. For every finding it checks four things, and rejects the finding if any fails: ... false positives are far worse than false negatives

来源