claudekit / tools / code-review
[ Plugin · Development ]

Code Review

Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives.

anthropics/claude-plugins-official/tree/main/plugins/code-review ·updated
$ /plugin install code-review copy

Anthropic official marketplace plugin

What it does

Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives.

Features

  • Multiple independent agents for comprehensive review
  • Confidence-based scoring reduces false positives (threshold: 80)
  • CLAUDE.md compliance checking with explicit guideline verification
  • Automatic skipping of closed, draft, or already-reviewed PRs
  • Direct code links with full SHA and line ranges

Use cases

  1. Catch latent bugs and security issues in a change before opening the PR.
  2. Detect coding-convention violations automatically and propose fixes.
  3. Suggest readability improvements for complex logic.
§ 4

See also

same category · curated
[01]
[MCP] Mobile MCP · MCP server for mobile automation and scraping on iOS, Android, emulators, simulators and real devices. Agents interact with native apps through structured accessibility snapshots or coordinate-based taps based on screenshots.
tool · claudekit.io / tools / mobile-mcp
[02]
[Plugin] Ponytail · Makes your AI agent think like the laziest senior dev in the room. Before writing code the agent stops at the first rung that holds — does this need to exist, is it already in the codebase, does the stdlib do it — and never cuts validation, error handling, security, or accessibility.
tool · claudekit.io / tools / ponytail
[03]
[Tool] Paseo · Run any coding agent from your phone, desktop, or terminal. Self-hosted, multi-provider, open source. A local daemon runs the agents on your machine and every client — desktop, mobile, web, CLI — connects to it, with the native mobile app at full feature parity with desktop.
tool · claudekit.io / tools / paseo
§ 5

Frequently Asked Questions

frequently asked
§ 5.1
What is Code Review?
An Anthropic official marketplace plugin that analyzes code changes for potential bugs, performance issues, and security concerns. It uses multiple specialized agents with confidence-based scoring to filter false positives.
§ 5.2
Where does it run?
Claude Code.
§ 5.3
How do I install it?
In Claude Code, run `/plugin install code-review`.
§ 5.4
When should I use it?
Before opening a PR, to surface potential bugs and security issues, catch convention violations, and get readability improvement suggestions for complex logic.
§ 5.5
Does it replace human reviewers?
It's a pre-merge verification layer, not a replacement. Use it to handle obvious issues so human reviewers can focus on the high-judgment calls.