“Code review”

Review code for bugs, security issues, best practices, and style.

Code-health audit — complexity, duplication, error handling, type invariants, patterns, naming, comment accuracy, dead/unutilized code.

Read a change carefully, identify concrete correctness, security, and maintainability risks, then prioritize findings.

系统性代码审查：正确性、可读性、性能与安全

Fetch, analyze, and address code reviews and comments on GitHub, or perform a code review on changes in the workspace.

Perform a structured code review of changes, checking for correctness, style, tests, and potential issues.

Use to review code changes with a two-stage process - first checking spec/requirements compliance, then code quality.

Run a comprehensive code review

Review code for actionable defects.

Automated code review with checklist and quality gates

Review changed code for naming, stale references, unnecessary complexity, and comment quality.

全面代码评审：code-reviewer + architect 双独立通道并行评审，严重度评级 + 架构状态（CLEAR/WATCH/BLOCK）+ 确定性合入门禁。用户说「review this code / code review / 帮我审代码」或合入 PR 前使用。

从固定点（commit、branch、tag 或 merge-base）开始，按 Standards（代码是否符合本仓库记录的编码标准？）和 Spec（代码是否符合来源 issue/spec 的要求？）两个轴线审查变更。两个审查会在并行子代理中运行，并并排报告。适用于用户想审查…

Use when user asks to review code for quality and security issues.

Run CodeRabbit CLI reviews, retrieve saved local or GitHub PR fix prompts, and interpret CodeRabbit authentication and review output.

Adversarial systems, concurrency, memory-model, and architecture code review protocol.

Multi-agent code review run as a debate.

Review code changes for material correctness, security, compatibility, and maintainability risks, grounded in the current repository and acceptance criteria.

Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before…

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding…

从固定点（commit、branch、tag 或 merge-base）开始，沿两条轴线审查变更——规范（代码是否遵循仓库文档化的编码规范？）和规格（代码是否与原始 issue/PRD 的要求一致？）。两条审查线在并行子 agent 中运行，并以并排方式报告结果。当用户想审查一个分支、PR、进行中的变更，或要求"从…

Code review by several models at once — Claude sub-agents, OpenAI Codex, and a cheap third reviewer via OpenCode — reconciled into one report.

Review code changes in the lcm repository.

Perform code reviews following Sentry engineering practices.