Code Review Plugin
插件 活跃Automated code review for pull requests using multiple specialized agents with confidence-based scoring
To streamline the code review process by providing automated, high-signal feedback on pull requests, reducing manual effort and improving code quality.
功能
- Automated PR review with parallel agents
- Confidence-based scoring and filtering of issues
- CLAUDE.md compliance checking
- Bug detection and historical context analysis
- Option to post review as PR comment
使用场景
- Reviewing all non-trivial pull requests
- Ensuring guideline compliance before merging
- Identifying potential bugs and code quality issues early
- Integrating automated review into CI/CD workflows
非目标
- Performing deep security vulnerability scans beyond obvious bugs
- Catching all code style or pedantic issues
- Replacing human review entirely
- Reviewing trivial or already-reviewed pull requests
Documentation
- info:Configuration & parameter referenceThe README documents the command-line options and provides usage examples, but the confidence threshold adjustment is mentioned as a modification to a command file, not a direct configuration parameter.
License
- warning:License usabilityThe license is only mentioned in the README as '© Anthropic PBC. All rights reserved. Use is subject to Anthropic's Commercial Terms of Service', which is not a standard SPDX identifier and lacks a dedicated LICENSE file, making its exact legal status unclear for downstream use.
Trust
- warning:Issues Attention9462 issues opened vs. 22831 closed in the last 90 days, indicating a closure rate of approximately 71%, but the high number of open issues suggests potential maintainer bottleneck.
Code Execution
- info:ValidationThe command files describe the expected agent behavior and tool usage, but lack explicit mention of schema validation libraries for input arguments or structured output sanitization.
- info:LoggingThe README mentions outputting to the terminal by default or as a PR comment, but no explicit mention of a local audit file for destructive actions or outbound calls.
安装
请先添加 Marketplace
/plugin marketplace add anthropics/claude-code/plugin install code-review@claude-code-plugins质量评分
类似扩展
Agents Design Experience
99Agents for UI/UX design, accessibility, and user experience optimization
Plugin Development Toolkit
99Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.
Review Agent Governance
99Require a human approval signal before an AI agent can post PR reviews, comments, merges, or writes to CI config. Cedar-gated, receipt-signed, designed for the Hermes-style failure mode where a review bot posts without oversight.
Performance Testing Review
99Performance analysis, test coverage review, and AI-powered code quality assessment
Comprehensive Review
99Multi-perspective code analysis covering architecture, security, and best practices
Skill Improver
99Automatically reviews and fixes Claude Code skills through iterative refinement until they meet quality standards. Requires plugin-dev plugin.