Best Claude Code Review Skills & Tools in 2026

⚡

The best Claude Code Review Skills & Tools in 2026 is awesome-skills/code-review-skill (★ 2.2k, after testing 16 of 183 tools on Agent Skills Hub, 177 of 183 rated SAFE) — best for: developers who want a structured SKILL.md review checklist (matches raw Claude Code's 8/8 defect recall). Found all eight planted defects with no false alarm on the clean pull requests, in about a minute and under two findings per pull request. That equals Claude Code with nothing installed: it adds a written checklist and a fixed report format, not detection. See the test →

Claude code review skills and AI code review tools for Claude Code and Codex: PR review bots, local CLI reviewers, security review and multi-agent review. Every one is security-graded before you install it.

What is a Claude Code review skill?

A Claude Code review skill is an installable package of review instructions (usually a folder with a SKILL.md file, sometimes shipped as a plugin) that tells Claude Code what to check in a diff or pull request, how serious each finding is and how to report it. Other review tools are separate programs that bring their own model and run on every commit or in CI. In our test on the same 12 pull requests, Claude Code with nothing installed already found all 8 planted defects with no false alarm; the 13 tools we ran differed in noise and speed, not in what they caught.

Claude Code review tools, tested on the same 12 pull requests

On 2026-10-10 we ran 16 of these tools and 13 ran. Each reviewed the same 12 pull requests against a small Python service in a throwaway sandbox: 8 carry one planted defect (an off-by-one, an SQL injection, a card token in the logs, a missing permission check, a retry that never ends, a swallowed error, an inverted condition, a weakened test) and 4 are clean. Two numbers per tool, as in SWR-Bench: defects found, and blocking findings on the clean ones. A judge (gpt-6-astra, three passes) marked each review. Claude Code with no tool installed did the same job as a control.

Which one to install

  1. 🥇
    developers who want a structured SKILL.md review checklist (matches raw Claude Code's 8/8 defect recall): code-review-skill ★ 1,914
    Found all eight planted defects with no false alarm on the clean pull requests, in about a minute and under two findings per pull request. That equals Claude Code with nothing installed: it adds a written checklist and a fixed report format, not detection.
  2. 🥈
    If you want every commit reviewed without asking: roborev ★ 1,746
    It reviews in the background as you commit, and it found all eight even with a different model (gpt-6-astra) doing the reading, with under one finding per pull request. Slower: 13 minutes for the twelve.
  3. 🥉
    If you would rather wait than read noise: adamsreview ★ 243
    The quietest reviewer that missed nothing it finished: 0.5 findings per pull request, the defect found in all seven it completed. It ran out of our 30 minutes on the twelfth.

Blind spots in our 12-PR code-review test (what these tools miss): brooks-lint (design decay only; it passed a logged card token at 100/100); bug-hunter (ignores test files, so a weakened test goes through).

Whichever you pick, the hardest defect was not in the code: four of 13 reviewers passed a pull request that quietly weakened a test's assertion. Read test changes yourself.

Listed by defects found, then time. This set does not rank the tools at the top: Claude Code with no tool installed found all 8 planted defects in a minute with no false alarm, and six tools did the same. Tools that bring their own model reviewed with gpt-6-astra, the skills with Claude Opus 5.5, so a gap between those two groups may be the model.

What we found: No tool beat the control. Claude Code with nothing installed found all 8 defects in about a minute with no false alarm (1.8 findings per pull request); 6 tools matched it and none did better. What separates the tools is noise (0.5 to 7.2 findings per pull request) and time (1 to 30 minutes). The defect missed most was the weakened test: 4 of 13 let it through. See the control run →

#ToolDefects found (of 8)False alarms on 4 clean PRsFindings per PRTimeReviewed byEvidence
1code-review-skill ★ 1,914 8/801.81 minClaude Opus 5.5 The reviews
2guard-skills ★ 1,153 8/801.42 minClaude Opus 5.5 The reviews
3review-forge ★ 220 8/801.32 minClaude Opus 5.5 The reviews
4clean-architecture-skills ★ 90 8/802.72 minClaude Opus 5.5 The reviews
5spencermarx/open-code-review ★ 331
Several reviewer personas write one report: every defect is in it, among 7 findings per pull request.
8/807.211 minClaude Opus 5.5 The reviews
6roborev ★ 1,746
Runs in the background on every commit; here it reviewed with gpt-6-astra through OpenCode and still found all eight.
8/800.913 mingpt-6-astra The reviews
7adamsreview ★ 243
Hit the 30-minute limit with one pull request unfinished; it found the defect in all seven it finished.
7/700.530 minClaude Opus 5.5 The reviews
8bug-hunter ★ 487
Treats test files as context only, by design, so it does not report a weakened test.
7/800.83 minClaude Opus 5.5 The reviews
9alibaba/open-code-review ★ 43,912
It skipped the two pull requests that only change tests, so the weakened test went unreviewed.
7/800.67 mingpt-6-astra The reviews
10vet ★ 519 7/801.118 mingpt-6-astra The reviews
11brooks-lint ★ 1,506
Reviews for design decay (coupling, complexity), not security: the logged card token and the weakened test scored 100/100.
5/800.93 minClaude Opus 5.5 The reviews
12gentleman-guardian-angel ★ 1,180
It checks code against a rules file you write. The test repo had none, so the agent wrote one from gga's Python example; its 30 failures on clean pull requests are that file's docstring and type-hint rules, not false alarms.
5/8see note6.09 mingpt-6-astra The reviews
13warden ★ 414
Its verification pass threw out candidate findings on the pull requests it missed, the SQL injection among them.
4/800.525 mingpt-6-astra The reviews
Not run (3)
  • cynical-sally: It sends the diff to its own hosted service, which answered Service Unavailable.
  • git-lrc: It sends the diff to a LiveReview server; there is none to review with locally.
  • claude-pr-review: It reviews pull requests on Bitbucket through the Bitbucket API; it has no way to review a local branch.

All results and scripts →

How we judge Claude Code review skills and tools: problems found, noise added

An AI code reviewer is judged by two numbers that pull against each other: how many real problems it finds, and how much noise it adds. On SWR-Bench, 1,000 manually verified pull requests from GitHub, current review tools find too little and do best on functional bugs; running several reviews and combining them raised F1 by up to 43.67%. Noise has a price too. In a company deployment reported at ICSE 2025, 73.8% of the AI's comments were resolved, yet the average time to close a pull request rose from 5 hours 52 minutes to 8 hours 20 minutes, and engineers named faulty, unnecessary and irrelevant comments as the drawback. ByteDance's reviewer filters its own comments in a second stage to reach 75.0% precision, and measures adoption by whether the code a comment pointed at was then changed. So we judge a Claude Code review skill or tool by what it does about both: does it filter before it posts, and can you see whether its comments were acted on.

Six kinds of Claude Code review tools

KindHow it worksWhere it helpsWhat to watch
Code review skills
30 · codex-plugin-cc, code-review-skill
A skill or plugin that has Claude Code or Codex review a diff on request. Runs before you commit, inside the agent you already use. The same model that wrote the code reviews it; ask a second model for important changes.
Local and CLI review
65 · open-code-review, code-review-graph
A command-line reviewer you run on a branch or a diff, often with fixed rules plus an LLM. Deterministic checks catch the known patterns; the model handles the rest. Local runs leave no shared record of what was flagged and fixed.
PR review bots and CI
39 · pr-agent, shippie
Comments on every pull request, in GitHub or GitLab, as a bot or a CI step. Every change gets a first pass, and resolved comments give you an adoption rate. Unfiltered comments slow merges; in one deployment, closing a PR took 2.5 hours longer on average.
Multi-agent review
24 · pr-af, bug-hunter
Several reviewers or models look at the same change and their findings are merged. Combining reviews raised F1 by up to 43.67% on SWR-Bench. Several times the tokens and the wait.
Security review
16 · DeepAudit, claude-code-security-review
Agents that look for vulnerabilities, some of which reproduce and fix them in a sandbox. Goes deeper on one class of problem than a general reviewer. A complement to a general review, not a replacement; check the grade, since these tools run code.
Code review platforms
9 · px0, kodus-ai
A self-hosted service that runs reviews across a team's repositories. One place for rules, history and adoption numbers. Someone has to own the rules and tune what gets posted.

The research measures review comments on real pull requests and in company deployments, not the specific tools listed here. Until we run them ourselves, the questions below are how we read that research.

Pick by where the review happens

Before you commit, on your ownA review skill in Claude Code or Codex, or a local CLI
Every pull request on a teamA PR bot that filters its comments and lets you set severity and scope
An important or risky changeMulti-agent review, or a second model on top of the first
Code that handles secrets, auth or user dataA security reviewer in addition to the general one

Four questions we ask of every Claude Code review tool

  1. Precision: does it filter or rank its own comments before posting them?
  2. Context: does it read beyond the diff, into the files and history the change touches?
  3. Adoption: can you see which comments were resolved or led to a code change?
  4. Cost: can you limit where and how much it comments, so merges do not slow down?

The floor is install safety. 6 entries on this page are flagged CAUTION or UNSAFE, 2 only for how they install. Check before installing: fullcase-web (sudo_usage, sensitive_env_vars); codebase-argus (sensitive_env_vars); claude-audit (eval_usage); codesense-ai (tunnel_service).

What our test and the research found

What we did, and what we did not

Sources

Jason Zhu · X · GitHub
Builds and maintains Agent Skills Hub and the awesome-claude-code-review list; tracking open-source agent skills and code review agents since 2024; author of the Blue Book of Agent Skills 2026.
Last reviewed 2026-10-08

Top 183 Claude Code Review Skills & Tools

1 open-code-review by alibaba
★ 54.3k Local & CLI review

Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.

🧪 Claude Code review test, 2026-10-10: It skipped the two pull requests that only change tests, so the weakened test went unreviewed. · found 7 of 8 planted defects · 0 false alarms on 4 clean pull requests · 0.6 findings per pull request · 7 min · reviewed by gpt-6-astra · See every review →
npm install -g @alibaba-group/open-code-review
2 codex-plugin-cc by openai
★ 35.3k Code review skills

Use Codex from Claude Code to review code or delegate tasks.

/plugin marketplace add openai/codex-plugin-cc
3 code-review-graph by tirth8205
★ 32.8k Local & CLI review

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

pip install code-review-graph
4 pr-agent by The-PR-Agent
★ 16.4k PR review bots & CI

🚀 PR Agent: The Original Open-Source PR Reviewer. This project is not the Qodo free tier.

pip install pr-agent
5 DeepAudit by lintsinghua
★ 7.3k Security review

DeepAudit: Open-source multi-agent code vulnerability auditing with one-click setup, sandbox PoC checks, Ollama deployment, reports, relay support.

docker pull ghcr.nju.edu.cn/lintsinghua/deepaudit-frontend:latest
6 claude-code-security-review by anthropics
★ 7.0k Security review

An AI-powered security review GitHub Action using Claude to analyze code changes for security vulnerabilities.

7 mantis by google
★ 2.8k Security review

A modular, stack-agnostic toolkit for AI coding agents to autonomously find, reproduce, and patch vulnerabilities.

8 shippie by mattzcarey
★ 2.5k PR review bots & CI

extendable code review and QA agent 🚢

npx shippie review
9 code-review-skill by awesome-skills
★ 2.2k Code review skills

A comprehensive code review skill for Claude Code, covering React 19, Vue 3, Rust, TypeScript, TanStack Query v5, and more.

🧪 Claude Code review test, 2026-10-10: found 8 of 8 planted defects · 0 false alarms on 4 clean pull requests · 1.8 findings per pull request · 1 min · reviewed by Claude Opus 5.5 · See every review →
git clone https://github.com/awesome-skills/code-review-skill.git `
10 px0 by px0-ai
★ 1.9k Code review platforms

px0 is an IDE built for reviewing AI-generated code, optimized for speed. It turns your browser into a zero-latency console with native Git and GitHub integrations, instant search across massive codebases, and seamless handoff to local AI coding harnesses.

git clone https://github.com/px0-ai/px0.git
11 sourcery by sourcery-ai
★ 1.9k PR review bots & CI

Instant AI code reviews

Quick Start: Add Sourcery to any repo to start seeing reviews on your new pull requests. Sourcery is completely free to use for public repos/open source projects. ...
12 roborev by kenn-io
★ 1.8k Local & CLI review

Continuous background code review database for agents, work faster and smarter with accountability for every line of generated code.

🧪 Claude Code review test, 2026-10-10: Runs in the background on every commit; here it reviewed with gpt-6-astra through OpenCode and still found all eight. · found 8 of 8 planted defects · 0 false alarms on 4 clean pull requests · 0.9 findings per pull request · 13 min · reviewed by gpt-6-astra · See every review →
brew install kenn-io/tap/roborev
13 openreview by vercel-labs
★ 1.7k PR review bots & CI

An open-source, self-hosted AI code review bot powered by Vercel.

14 brooks-lint by hyhmrright
★ 1.6k Code review skills

Portable AI code quality reviews for Codex, Cursor, Copilot and other coding agents: six Agent Skills for architecture, technical debt, tests and remediation.

🧪 Claude Code review test, 2026-10-10: Reviews for design decay (coupling, complexity), not security: the logged card token and the weakened test scored 100/100. · found 5 of 8 planted defects · 0 false alarms on 4 clean pull requests · 0.9 findings per pull request · 3 min · reviewed by Claude Opus 5.5 · See every review →
/plugin marketplace add hyhmrright/brooks-lint
15 kodus-ai by kodustech
★ 1.6k Code review platforms

Open source, self-hosted AI code review. Bring your own LLM.

16 git-lrc by HexmosTech
★ 1.5k Local & CLI review

Free, Micro AI Code Reviews That Run on Git Commit

🧪 Not run in our test: It sends the diff to a LiveReview server; there is none to review with locally.
17 sashiko by sashiko-dev
★ 1.4k Local & CLI review

Agentic review of Linux Kernel code changes

cargo install sashiko
18 guard-skills by amElnagdy
★ 1.3k Code review skills

Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs

🧪 Claude Code review test, 2026-10-10: found 8 of 8 planted defects · 0 false alarms on 4 clean pull requests · 1.4 findings per pull request · 2 min · reviewed by Claude Opus 5.5 · See every review →
npx skills add amElnagdy/guard-skills --list
19 gentleman-guardian-angel by Gentleman-Programming
★ 1.2k Local & CLI review

😇 Gentleman Guardian Angel (gga) - Provider-agnostic code review using AI. Use Claude, Gemini, Codex, Ollama to enforce your coding standards.

🧪 Claude Code review test, 2026-10-10: It checks code against a rules file you write. The test repo had none, so the agent wrote one from gga's Python example; its 30 failures on clean pull requests are that file's docstring and type-hint rules, not false alarms. · found 5 of 8 planted defects · 6.0 findings per pull request · 9 min · reviewed by gpt-6-astra · See every review →
git clone https://github.com/Gentleman-Programming/gentleman-guardian-angel.git
20 ai-codereviewer by villesau
★ 1.0k PR review bots & CI

AI Code Reviewer: Enhance your GitHub workflow with AI-powered code review! Get intelligent feedback and suggestions on pull requests using OpenAI's GPT-4 API, improving code quality and saving developers time.

21 herdr-reviewr by persiyanov
★ 994 Local & CLI review

Review your agent's diff in a terminal pane and send comments back to Claude Code, Codex, OpenCode or Pi. A herdr plugin.

git clone https://github.com/persiyanov/herdr-reviewr
22 diffity by nilbuild
★ 903 Local & CLI review

Mac app to review the code written by you or your agent with Claude in the loop.

23 metis by arm
★ 891 Security review

Metis is an open-source, AI-driven tool for deep security code review

git clone https://github.com/arm/metis.git
24 claude-review-loop by hamelsmu
★ 729 Code review skills

Claude Code plugin: automated code review loop with Codex

/plugin marketplace add hamelsmu/claude-review-loop
25 jev-review by devagrawal09
★ 705 Local & CLI review

A staged code-review workflow and local dashboard built with TypeSafe Jev.

26 pr-af by Agent-Field
★ 663 Multi-agent review

#1 open-source code reviewer on Code-Review-Bench

git clone https://github.com/Agent-Field/pr-af
27 ai-review by Nikita-Filonov
★ 603 PR review bots & CI

🚀 AI-powered code review tool for GitHub, GitLab, Bitbucket Cloud, Bitbucket Server, Azure DevOps and Gitea — built with LLMs like OpenAI, Claude, Gemini, Ollama, Bedrock, OpenRouter and Azure OpenAI

pip install xai-review
28 bug-hunter by codexstar69
★ 559 Multi-agent review

Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline finds security vulnerabilities, logic errors, and runtime bugs — then fixes them autonomously on a safe branch.

🧪 Claude Code review test, 2026-10-10: Treats test files as context only, by design, so it does not report a weakened test. · found 7 of 8 planted defects · 0 false alarms on 4 clean pull requests · 0.8 findings per pull request · 3 min · reviewed by Claude Opus 5.5 · See every review →
npx skills add codexstar69/bug-hunter
29 chorus by chorus-codes
★ 534 Multi-agent review

Multi-LLM peer review for code decisions. Bring your own CLI; Chorus convenes 2-4 other LLMs to review the work before you ship.

npm i -g chorus-codes # install (no sudo — see below)
30 vet by imbue-ai
★ 493 Local & CLI review

Find issues worth your attention.

🧪 Claude Code review test, 2026-10-10: found 7 of 8 planted defects · 0 false alarms on 4 clean pull requests · 1.1 findings per pull request · 18 min · reviewed by gpt-6-astra · See every review →
31 pr-cockpit by taovc
★ 486 Local & CLI review

Local AI PR workbench — Claude/Codex review in isolated git worktrees, human-gated GitHub comments

git clone https://github.com/taovc/pr-cockpit.git
32 Gito by Nayjest
★ 467 PR review bots & CI

An AI-powered GitHub code review tool that uses LLMs to detect high-confidence, high-impact issues—such as security vulnerabilities, bugs, and maintainability concerns.

pip install gito.bot
33 AsyncReview by AsyncFuncAI
★ 463 Code review skills

Open-source Agentic code review tool inspired by DevinReview, using Recursive Language Models (RLM)

npx asyncreview review --url https://github.com/org/repo/pull/123 -q "Check for breaking changes"
34 agentgg by agentgg-dev
★ 460 Security review

Open source agentic SAST. The engine behind hundreds of disclosed zero-days. 100+ AI security agents, any repo or PR diff, bring your own model.

npm install -g agentgg
35 skills by greptileai
★ 437 Code review skills

Agent skill for checking PR review comments, status checks, and description completeness

git clone https://github.com/greptileai/skills.git ~/.claude/skills/greptile
36 warden by getsentry
★ 423 Local & CLI review

Your code is under new management. Agents that review your code.

🧪 Claude Code review test, 2026-10-10: Its verification pass threw out candidate findings on the pull requests it missed, the SQL injection among them. · found 4 of 8 planted defects · 0 false alarms on 4 clean pull requests · 0.5 findings per pull request · 25 min · reviewed by gpt-6-astra · See every review →
npx @sentry/warden init
37 mira by miracodeai
★ 395 Code review platforms

Self-hosted AI code reviewer with indexed PR reviews, walkthroughs, vulnerability scanning, dependency graphs, custom rules, and a learning loop.

git clone https://github.com/miracodeai/mira.git
38 open-code-review by spencermarx
★ 384 Multi-agent review

AI-powered multi-agent code review. Simulates a customizable team of Engineers performing code review with built-in discourse.

🧪 Claude Code review test, 2026-10-10: Several reviewer personas write one report: every defect is in it, among 7 findings per pull request. · found 8 of 8 planted defects · 0 false alarms on 4 clean pull requests · 7.2 findings per pull request · 11 min · reviewed by Claude Opus 5.5 · See every review →
npm install -g @open-code-review/cli
39 genai-code-review by cirolini
★ 372 PR review bots & CI

GitHub Action that reviews pull request diffs with an LLM and posts the comments on the PR

Quick Start: One workflow file. Nothing else. No step is needed — the action reads the pull request over the API and never uses the repository on disk. The block i...
# .github/workflows/code-review.yml
on:
  pull_request:
    types: [opened, synchronize]

permissions:
  contents: read
  pull-requests: write

jobs:
  review:
    runs-on: ubuntu-latest
    steps:
      - uses: cirolini/genai-code-review@v3
        with:
          api_key: ${{ secrets.GEMINI_API_KE
40 vbsec by tanviet12
★ 331 Security review

Security scanning skill for Claude Code, Codex and Antigravity. Finds the 21 most common vulnerabilities in AI-written code and shows how to fix each one.

git clone https://github.com/tanviet12/vbsec ~/vbsec
41 codeball-action by sturdy-dev
★ 327 PR review bots & CI

🔮 Codeball – AI Code Review that finds bugs and fast-tracks your code

42 perch by lakeday-org
★ 311 Local & CLI review

Semantic code linting with Jev

npm install -g @lakeday/perch
43 RepoLens by TheMorpheus407
★ 304 Local & CLI review

Multi-lens code audit tool — 280 expert AI agents for code review, security testing, and infrastructure auditing

git clone https://github.com/TheMorpheus407/RepoLens.git
44 bitoai by gitbito
★ 299 PR review bots & CI

Get codebase-aware feedback in your GitHub, GitLab, Bitbucket pull requests or directly in your IDE.

45 chatgpt-code-review by domvwt
★ 289 Code review platforms

git clone https://github.com/domvwt/chatgpt-code-review.git
46 stage-cli by ReviewStage
★ 277 Local & CLI review

A viewer for reviewing local code changes in small individual chapters. Works with any AI agent.

npx skills add ReviewStage/stage-cli
47 ask-bonk by Cloudflare-Studio
★ 269 PR review bots & CI

Bonk is a code & docs agent that can build, review and triage for you, built on Cloudflare Workers & OpenCode.

48 gemini-ai-code-reviewer by truongnh1992
★ 258 PR review bots & CI

A GitHub Action that automatically reviews pull requests using Google's Gemini AI.

49 codexqa by openqa-cn
★ 254 Local & CLI review

codexqa: 11 local-first Agent Skills for Cursor, Claude Code, Codex & OpenClaw — change impact analysis, AI code review, defect scan, testcase generation, browser replay & RCA.

npx skills add openqa-cn/codexqa --skill code-analyzer
50 jev-review by NiazMorshed2007
★ 253 Local & CLI review

Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.

npx plugins add NiazMorshed2007/jev-review
51 adamsreview by adamjgmiller
★ 245 Multi-agent review

Multi-lens code review pipeline for Claude Code: deep review (Claude or Codex), auto-fix loop, interactive walkthrough, external-finding injection.

🧪 Claude Code review test, 2026-10-10: Hit the 30-minute limit with one pull request unfinished; it found the defect in all seven it finished. · found 7 of 7 planted defects · 0 false alarms on 4 clean pull requests · 0.5 findings per pull request · 30 min · reviewed by Claude Opus 5.5 · See every review →
/plugin marketplace add adamjgmiller/adamsreview
52 Easy-AI-CodeReview by spherical-up
★ 244 PR review bots & CI

A Code Review tool for developers with comparisons, comment suggestions, change summaries, and code quality alerts to understand commits and find issues faster.

git clone https://github.com/spherical-up/Easy-AI-CodeReview
53 GodModeSkill by 99xAgency
★ 241 Multi-agent review

Multi-LLM cross-review workflow for Claude Code. /work orchestrates plan/implement/bug-fix with 3 different model families voting on every gate.

git clone https://github.com/99xAgency/GodModeSkill.git
54 github-pr-summary by flows-network
★ 229 PR review bots & CI

Use LLM to summarize & review GitHub Pull Requests

55 review-forge by vikingmute
★ 224 Code review skills

review-forge is an Agent Skill for structured, auditable code review workflows

🧪 Claude Code review test, 2026-10-10: found 8 of 8 planted defects · 0 false alarms on 4 clean pull requests · 1.3 findings per pull request · 2 min · reviewed by Claude Opus 5.5 · See every review →
npx skills add vikingmute/review-forge
56 diffx by wong2
★ 218 Local & CLI review

A local code review tool designed for the coding agent workflow

npm install -g diffx-cli
57 inspect by Ataraxy-Labs
★ 214 Local & CLI review

Entity-level code review for Git. Graph-based risk scoring, change classification, commit untangling. 95% recall on the Greptile benchmark.

cargo install --git https://github.com/Ataraxy-Labs/inspect inspect-cli
58 claude-cybersecurity by AgriciDaniel
★ 208 Security review

AI-powered cybersecurity code review skill for Claude Code. 8 specialist agents, OWASP 2025, CWE Top 25, MITRE ATT&CK, 11 languages, zero configuration.

git clone https://github.com/AgriciDaniel/claude-cybersecurity.git
59 cf_ai_code_review by FelixNg1022
★ 203 Code review platforms

AI-powered code review application built on Cloudflare Workers

npx wrangler pages deploy frontend/dist --project-name cf-ai-code-review-frontend
60 reslop by tshemsedinov
★ 196 Local & CLI review

👁️ Review AI generated code and plan changes

npm i -g reslop
61 ai-reviewer by presubmit
★ 187 PR review bots & CI

Context-aware AI reviewer for Pull Requests. Instant summary, line-by-line comments, title generation and more

62 lareview by puemos
★ 184 Local & CLI review

The code review workbench.

brew install --cask lareview
63 Orca-Code-Review by Continuum-AI-Corp
★ 184 Code review skills

OrcaCode Review — the open code review harness. Multi-model reviews, merge gates, and no markup. Pay only for inference.

/plugin marketplace add Continuum-AI-Corp/orca-code-review
64 review-skills by amElnagdy
★ 172 Multi-agent review

Two-model debate review of PRs and MRs, plus a babysitter that works the review rounds. Skills for any coding agent.

npx skills add amElnagdy/review-skills
65 rejudge by syabro
★ 166 Multi-agent review

Independent multi-model review for AI coding agents

npm install -g rejudge
66 RedFlag by Addepar
★ 163 Security review

RedFlag uses AI to identify high-risk code changes. Run it in batch mode for release candidate testing or in CI pipelines to flag PRs and add reviewers. RedFlag's flexible configuration makes it valuable for any team.

pip install addepar-redflag
67 jev-code-reviewer by egma-ai
★ 152 Local & CLI review

Review behavior, not just diffs. Jev prioritizes human attention; OpenAI explains the changes. Local CLI + agent skill + GitHub extension.

git clone https://github.com/egma-ai/jev-code-reviewer.git
★ 146 Security review

A code auditing skill by the Oriental Hidden Hero team

69 tulip by VirtusLab
★ 142 Multi-agent review

Explains GitHub PRs in a human-friendly way, using LLMs.

npm install -g @virtuslab/tulip
70 vscode-extension by DeepCodeAI
★ 130 Security review

DeepCode extension for Visual Studio Code

71 proval by seoes
★ 129 Code review platforms

Self-Hosted LLM Code Review Agent for GitLab, Forgejo and GitHub. Local LLM support

72 code-gate by Gil2015
★ 127 Local & CLI review

Intelligent Git commit code reviewer. Supports local (Ollama) and cloud models (DeepSeek, OpenAI, Anthropic) with a rich CLI UI. 本地AI智能 Git 提交代码审查工具。支持使用本地 (Ollama) 及云端模型 (DeepSeek, OpenAI, Anthropic),提供丰富的 CLI 交互界面。

npx code-gate review <commit-hash>
73 insane-review by fivetaku
★ 127 Code review skills

Use GPT-5.5 Pro (web-only, no API) from inside Claude Code — repomix-pack the relevant code, send to subscription ChatGPT Pro, harvest the review (API cost $0)

/plugin install insane-review
74 codra by devarshishimpi
★ 125 Code review platforms

Self-hosted AI code review for GitHub pull requests, built on Cloudflare Workers.

★ 124 Code review skills

76 linus-torvalds-skill by Mte90
★ 122 Multi-agent review

Distilled Code Reviewer skills/soul from 32k~ email from the kernel newsletter

77 hodor by mr-karan
★ 116 PR review bots & CI

Agentic code reviewer for GitHub PRs and GitLab MRs. Multi-step reasoning with autonomous tool orchestration — catches bugs requiring analysis across files.

npx @mrkaran/hodor <PR_URL>
78 octopus by octopusreview
★ 115 PR review bots & CI

AI-powered PR review tool — multi-armed code analysis, no bug escapes 🐙

79 claude-pr-review by GGGODLIN
★ 114 Multi-agent review

Multi-axis PR review orchestration for Claude Code — 5 independent review perspectives, symmetric cross-verification, deterministic coverage assertion

🧪 Not run in our test: It reviews pull requests on Bitbucket through the Bitbucket API; it has no way to review a local branch.
80 revmux by umputun
★ 114 Multi-agent review

Multi-agent code review, supervised and auditable

brew install umputun/apps/revmux
81 oss-pr-reviewer by vuphongle
★ 113 Local & CLI review

AI-powered CLI for reviewing GitHub pull requests, detecting potential bugs, security risks, regressions, and missing tests, with structured Markdown reports for open-source maintainers.

82 code_review_agent by huoji120
★ 113 Multi-agent review

A simple, efficient code auditing agent

83 pi-review-loop by nicobailon
★ 112 Local & CLI review

Automated code review loop extension for Pi coding agent

84 clean-architecture-skills by nathankim0
★ 111 Code review skills

Clean Architecture and Kent Beck refactoring skills for Claude Code and OpenAI Codex: code review, architecture design, SOLID, and simple design.

🧪 Claude Code review test, 2026-10-10: found 8 of 8 planted defects · 0 false alarms on 4 clean pull requests · 2.7 findings per pull request · 2 min · reviewed by Claude Opus 5.5 · See every review →
/plugin marketplace add nathankim0/clean-architecture-skills
85 AI-Code-Reviewer by Ali-Marandi
★ 109 Local & CLI review

AI-Powered Code Review and Quality Analysis Tool

git clone https://github.com/Ali-Marandi/AI-Code-Reviewer.git
86 reviu by reviu-dev
★ 108 Local & CLI review

The review app for code your agent writes. Native Rust/GPUI desktop app with real Git workflows.

87 LiveReview by HexmosTech
★ 107 Code review platforms

Blast-Radius Aware AI Code Review for Business-Critical Systems

88 reviewbot by qiniu
★ 106 PR review bots & CI

Empower Your Code Quality with Self-Hosted Automated Analysis and Review

★ 106 Code review skills

Salesforce DX code review: Apex, LWC, Flows, security (CRUD/FLS), governors, and Bugbot.

git clone https://github.com/rediga/Salesforce-Code-Review-Agent.git
90 cynical-sally by w1ckedxt
★ 102 Code review skills

Brutally honest senior-engineer code reviews for Claude Code, Cursor & Windsurf - and your terminal. Scores, evidence-backed issues, usable fixes.

🧪 Not run in our test: It sends the diff to its own hosted service, which answered Service Unavailable.
npm install -g @cynicalsally/cli
91 juror by Juror-AI
★ 100 PR review bots & CI

Cheaper and better Greptile alternative runs on your own github actions.

npx juror-ai init --set-secrets
92 ChatGPT-Reviewer by feiskyer
★ 98 PR review bots & CI

Automated pull requests reviewing and issues triaging with ChatGPT.

Quick Start: Create an OpenAI API key here, and then set the key as an action secret in your repository named . Finally, create a file named with the following con...
name: ChatGPT Review

on: [pull_request]


jobs:
  chatgpt-review:
    name: ChatGPT Review
    runs-on: ubuntu-latest
    steps:
    - uses: feiskyer/ChatGPT-Reviewer@v0
      name: ChatGPT Review
      env:
        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        OPENAI_API_KEY: ${{ secrets.OPENA
★ 94 PR review bots & CI

Prototype Gitlab Webook that submits code to OpenAI for review

Quick Start: Prerequisites Python 3.8 or higher Docker (optional) An OpenAI API key A GitLab API token Installation Clone the repository: Install the required Pyth...
https://git.facha.dev/facha/openai-gitlab-pr-review.git
cd ai-code-reviewer
94 fullcase-web by dalemoncayo
★ 93 Multi-agent review

A practical example of integrating AI code review into a real-world codebase. Built with Next.js and Firebase, this repo highlights structured prompts, reusable review skills, and parallel subagent execution via Claude Code and OpenAI Codex.

95 ai-code-review-helper by Usagi-org
★ 92 PR review bots & CI

AI Code Review Helper automates code review with GitHub/GitLab webhooks and LLMs, posting feedback to PRs/MRs and notifying WeCom.

git clone https://github.com/dingyufei615/ai-code-review-helper.git
96 mr-agent by ZJunCher
★ 91 Multi-agent review

An open-source multi-agent platform for GitLab MR code review, governance, and CI self-healing.

git clone https://github.com/ZJunCher/mr-agent.git
97 lucidity-mcp by hyperb1iss
★ 90 Local & CLI review

AI-powered code quality analysis using MCP to help AI assistants review code more effectively. Analyze git changes for complexity, security issues, and more through structured prompts.

git clone https://github.com/hyperbliss/lucidity-mcp.git
98 ai-code-reviewer by buxuku
★ 90 PR review bots & CI

一个利用 openai api 对 gitlab 提交的 merge request 进行 code review 的小工具

npm i @buxuku/ai-code-reviewer
99 vulnhawk by momenbasel
★ 90 Security review

AI-powered SAST scanner that finds auth bypass, IDOR, and logic bugs Semgrep/CodeQL miss. Free GitHub Action. Supports Python, JS/TS, Go, PHP, Ruby.

pip install vulnhawk
100 pr-review-agent-council by csy-csy123
★ 89 Multi-agent review

学习 learn-claude-code 后的 PR Review Agent 实践项目:构建 Debate Council 多 Agent 审查、Tool Calling、结构化报告与 AI Judge 评估。

git clone https://github.com/csy-csy123/pr-review-agent-council.git
101 mr-agent by zixingtangmouren
★ 89 PR review bots & CI

mr-agent: A Node.js service that auto-triggers AI-powered code reviews when receiving Git merge request webhook events. Integrates with GitHub/GitLab/Bitbucket to analyze changes, flag issues, and suggest improvements—streamlining reviews for teams of all sizes.

102 code-review-skills by akkie76
★ 88 Code review skills

Evidence-based code review skills for Codex and Claude Code

103 codex-maintainer by snakyvine
★ 83 Local & CLI review

Evidence-grounded issue triage, pull request review, and release notes for GitHub maintainers. CLI + GitHub Action.

git clone https://github.com/snakyvine/codex-maintainer.git
104 AI-dev-assistant by imDarshanGK
★ 83 Code review platforms

AI-powered code analysis tool with bug detection, code explanations, and AI-powered suggestions.

105 semantic-review by mikker
★ 82 Local & CLI review

Semantic diff review for coding agents

npx skills add mikker/semantic-review
★ 80 PR review bots & CI

A GitHub Action that uses OpenAI ChatGPT to do code review

Quick Start: To use this action in your workflow, add the following step:
name: OpenAI ChatGPT Code Review
uses: adshao/chatgpt-code-review-action@v0.2
with:
    PROGRAMMING_LANGUAGE: 'JavaScript'
    REVIEW_COMMENT_PREFIX: 'chatgpt:'
    FULL_REVIEW_COMMENT: 'chatgpt'
    OPENAI_TOKEN: ${{ secrets.OPENAI_TOKEN }}
    GITHUB_TOKEN: ${{ secrets.GH_TOKEN }}
107 codemoot by katarmal-ram
★ 78 Local & CLI review

Multi-model collaborative development platform — Claude + GPT debate, review, and build together

npm install -g @codemoot/cli
108 opencode-review-gitea by ccsert
★ 77 PR review bots & CI

AI-powered PR review for Gitea/Forgejo built on OpenCode. Runs in Gitea Actions, fetches PR diffs, and posts structured reviews. Supports Docker or source install with isolated .opencode-review config.

109 crg by n24q02m
★ 76 Local & CLI review

Knowledge graph for token-efficient code reviews -- semantic search and call-graph resolution across your codebase.

git clone https://github.com/n24q02m/crg
110 ai-agent-agentscope-codereview by kevinten-ai
★ 74 Multi-agent review

An AI code review agent based on the AgentScope Java SDK and a tutorial covering ReAct, tools, and multi-agent collaboration.

111 pair-review by in-the-loop-labs
★ 74 Local & CLI review

AI assisted code review with a human in the loop

npx @in-the-loop-labs/pair-review <PR-number-or-URL or --local>
112 pr-reviewer by truskovskiyk
★ 73 PR review bots & CI

Use LLM to help you with PR review

Quick Start:
pip install pr-review-bot
113 reviewd by simion
★ 71 Local & CLI review

Local AI pull request reviewer — review GitHub and BitBucket PRs right from your terminal, powered by the Claude Code, Gemini, and Codex CLIs.

pip install reviewd
114 lgtm by kunkka19xx
★ 69 Local & CLI review

Read what your agent wrote before you say LGTM. A fast TUI in Zig for reviewing code with vim motions.

brew install kunkka19xx/tap/lgtm
115 CodeReviewAgent by gitbito
★ 68 PR review bots & CI

On-demand, context-aware AI code reviews in your Git workflow or IDE as you code.

116 gitpack-ai by gitpack-ai
★ 67 PR review bots & CI

Automate Pull Request Reviews with AI 🪄

117 adverse by addyosmani
★ 66 Multi-agent review

Multi-agent adversarial code review for any coding agent

npm install -g adverse
118 codingfox by furudo-erika
★ 65 PR review bots & CI

Open Source AI Code Review Tool that Works Like Magic!

119 robin-ai-reviewer by Integral-Healthcare
★ 65 PR review bots & CI

Robin is your AI pull request reviewer in the form of a super fast lightweight github action.

120 autonomous-qa-loop by MaxwellCCC
★ 65 Multi-agent review

Portable fresh-agent QA loop prompt for finding bugs without biased self-checks / 通用自动 QA 循环 SKILL

121 ai-pr-review by snarktank
★ 62 PR review bots & CI

A robust GitHub Actions workflow that provides AI-powered code reviews using Amp or Claude Code

122 codebase-argus by AaronZ345
★ 59 Multi-agent review

Multi-agent codebase review for PRs, CI, and downstream fork syncs.

/plugin marketplace add AaronZ345/codebase-argus
123 chai-ai-code-reviewer by Aestheticsuraj234
★ 59 PR review bots & CI

124 openrabbit by aryanbrite
★ 58 PR review bots & CI

Free, AI PR reviewer that runs entirely in GitHub Actions. No hosting required.

125 SeCoRA by shivamsaraswat
★ 58 Security review

Secure Code Review AI Agent (SeCoRA) - AI SAST

git clone https://github.com/shivamsaraswat/secora.git
126 ai-code-review by bobmatnyc
★ 56 Local & CLI review

AI-powered code review CLI with multiple providers (Gemini, Claude, OpenAI). Features 95%+ token reduction via semantic chunking, 7 review types (security/performance/evaluation), multi-language support, interactive fixes, and developer skill assessment.

pnpm add -g @bobmatnyc/ai-code-review
127 droid-code-review by Factory-AI
★ 55 PR review bots & CI

Droid code review

128 clab by mberneti
★ 54 Code review skills

Open source Claude skill for automated GitLab MR reviews. Configurable lint rules, semantic analysis, and inline comment posting for self-hosted GitLab instances.

git clone https://github.com/mberneti/clab.git
129 auditlm by ellenhp
★ 53 PR review bots & CI

Self-hostable AI code review for your Forgejo

130 claude-git-pr-skill by aidankinzett
★ 53 Code review skills

Professional GitHub PR review skill for Claude Code with pending reviews, code suggestions, and user approval workflow

Quick Start: Option 1: Plugin Marketplace (Recommended) Install directly from the marketplace using Claude Code: For team-wide installation, add to : Option 2: Man...
# Add this marketplace
/plugin marketplace add aidankinzett/claude-git-pr-skill

# Install the plugin
/plugin install github-pr-review

# Verify installation
/plugin list
131 katichai by kodehash
★ 52 Local & CLI review

Context-aware, AI-assisted code review CLI tool that prevents unnecessary AI-generated code, detects duplicated logic, enforces architectural patterns, and ensures high-quality engineering standards

132 AICodePal by giorgiop
★ 51 Local & CLI review

An AI-managed open-source code review and assistance tool to help developers write better, more efficient, and secure code.

git clone https://github.com/username/AICodePal.git
133 scanline by ScanLineDev
★ 50 Local & CLI review

Expert AI code reviews Catch bugs before they hurt Run Scanline in your CLI to find: - race conditions - logical errors - security risks - optimizations

134 evaos-code-review-bot-neondiff by electricsheephq
★ 50 PR review bots & CI

Stop giving away your code. NeonDIFF is your local-first AI PR reviewer for teams that want professional quality code reviews and issue enrichment without handing every diff to a hosted review SaaS.

git clone https://github.com/electricsheephq/evaos-code-review-bot-neondiff.git neondiff
135 duetlens by xieziyu
★ 50 Local & CLI review

Conversational code review on macOS: review a PR or local branch together with a codex agent, and ask about any line instead of just reading its findings.

136 turingmind-code-review by turingmindai
★ 50 Code review skills

Claude Code Review Skill

/plugin marketplace add turingmindai/turingmind-code-review
137 code-review-skill by killop
★ 50 Local & CLI review

138 slop-review by dbachelder
★ 49 Local & CLI review

A native /slop-review window for Claude Code, Codex CLI, and pi — review the slop before you ship it. Monaco-powered inline comments, agent reads them back. Forked from badlogic/pi-diff-review.

139 argot by get-tmonier
★ 49 Local & CLI review

A statistical code analyzer built from your repository's history.

140 claude-review-all by ncoevoet
★ 45 Multi-agent review

Comprehensive multi-agent code review for Claude Code

141 diffo by DiffoHQ
★ 45 Local & CLI review

Local, live code review for the AI age - read what the agent wrote and send feedback straight back

142 agent-verifier by Aurite-ai
★ 44 Code review skills

🔍 Agent Verifier is a coding agent skill that verifies code against organizational policies, code quality patterns, security requirements, and framework best practices — before code ships. Works with Claude Code, Cursor, Windsurf, and 30+ agents.

143 open-code-review by raye-deng
★ 40 Local & CLI review

🤖 AI code quality gate for AI-generated code. Detects hallucinated packages, phantom dependencies, stale APIs, and more. MCP Server + CLI + CI/CD Action.

144 draft by drafthq
★ 40 Code review skills

Context-Driven Development plugin for Claude Code, Cursor, GitHub Copilot, Gemini

145 Agentic-Tool-Optimization by WillNigri
★ 34 Local & CLI review

Local-first multi-runtime AI cockpit (CLI + desktop + MCP). War-rooms, review receipts, open multi-model coding benchmarks. MIT.

146 simulacra by mturac
★ 34 Code review skills

Ghost personas review your code before it ships. Find edge cases, race conditions, and business logic bugs before production.

147 dunk by amix
★ 31 Local & CLI review

Review diffs in a terminal UI, leave inline comments, and let coding agents fix them

148 code-review-agent by SomeStay07
★ 30 Code review skills

Code review agent for Claude Code. One .md file — 14 review categories, 4 severity levels, auto-fix, OWASP security checks. Zero dependencies.

149 agent-guardrails by logi-cmd
★ 27 Local & CLI review

Checks AI-generated code changes before merge: scope, validation, risk, review evidence, and optional Verity receipts.

150 brutal-coding-tool by fabriziosalmi
★ 27 Security review

Audit your vibecode and make it brutally solid :)

151 ai-pre-commit-reviewer by ispuppy
★ 24 Local & CLI review

AI-powered git pre-commit hook for automated code review with customizable rules.

152 ask-llm by Lykhoyda
★ 21 Code review skills

MCP server and CLI for second opinions: lets Claude Code, Codex and Cursor consult Codex, Claude, Gemini, Grok and local Ollama models for code review and plan debate

153 buoy by ahoybuoy
★ 20 Local & CLI review

Design system guardian for code. Anchors to design system, catches drift in React/Vue/Tailwind, reviews PRs automatically. Free for open source.

154 Assumptions by Teycir
★ 20 Code review skills

A SKILL that turns a code diff into an evidence-backed ledger of hidden assumptions, failure modes, and falsification tests.

155 elek by selimozten
★ 19 PR review bots & CI

Review-only AI code review for GitHub pull requests. Cross-check PRs with model-agnostic reviewers that can comment inline but cannot approve, merge, or close.

156 spectra by leocder07
★ 19 Multi-agent review

8 AI agents grade your entire repository across 6 dimensions — signed, verifiable A+ to F audit reports in minutes

157 OpsGuard-AI by oscaar90
★ 16 Security review

Context Aware Security Gate for GitHub Actions. Validates deployments using Hybrid Analysis (Deterministic Rules + LLM Reasoning).

158 pi-review by ZephyrDeng
★ 15 Multi-agent review

Isolated AI-powered code and plan reviews from the command line

159 code-cortex-loop by whitequeen306
★ 15 Code review skills

One-command AI code quality pipeline: review, security, tests, performance, simplify & cleanup. Health scores, CI gate. For Cursor, Claude Code, Qoder, Trae.

160 claude-audit by itsmesherry
★ 15 Local & CLI review

Command-line code auditor: fast static checks, plus an optional audit where Claude investigates the code with read-only tools.

161 askdiff by narghev
★ 12 Local & CLI review

Ask your AI questions about its own code changes — from a Git diff viewer.

162 revet by umitkavala
★ 12 Local & CLI review

Code review agent

163 review-skill by wxmb01
★ 11 Code review skills

Evidence-based review skill for diff, project, and artifact review across code, readiness, architecture, requirements, and risk.

164 shipcheck by lohani-mohit
★ 11 Code review skills

🚦 Senior-QA review skill for Claude Code: runs a regression hunter + a change reviewer in parallel, then gives one read-only SIGN OFF / DO NOT SHIP verdict with file:line evidence.

165 jev-security-scan by win4r
★ 11 Security review

使用 TypeSafe Jev 审查 Skill 与 MCP 可疑行为 | Review Agent Skills and MCP code with Jev, static evidence, and explicit coverage gaps

166 sieve by DanielT777
★ 11 Local & CLI review

Filter AI slop before it hits your codebase. A structured human review workflow for AI-generated code.

167 highstakes by zanetworker
★ 11 Local & CLI review

AI writes code faster than you can review it. HighStakes reads your codebase, scores every file by blast radius, and tells you where human review matters and where AI can handle the rest.

★ 11 Multi-agent review

Claude Code workflow to grade your project's maintainability by Human and LLM

169 Design-Patterns by VoDaiLocz
★ 11 Code review skills

Full-spectrum design patterns skill: Detect anti-patterns, diagnose architectural debt, generate production-ready refactored code. GoF, SOLID, DDD, CQRS, Microservices.

170 reviewer by alxnddr
★ 11 Local & CLI review

UI for agent-generated code reviews

171 commitbrief by CommitBrief
★ 11 Local & CLI review

Local LLM code review CLI for git diffs — review staged/unstaged changes, any git diff range, or a GitHub PR, right in your terminal.

172 manta by mantacron
★ 10 Local & CLI review

20 AI agents in your git workflow. Secrets, injection flaws and unsafe migrations are blocked at commit; performance, coverage and the rest are reviewed at push. Research → Plan → Implement workflow with GO/NO-GO gates before you write a line. Generates production-ready code, product wikis and codebase maps on demand. Any language. Free.

173 diffler by matheusfillipe
★ 10 Local & CLI review

Terminal code review with vi-like bindings. Live diffs, comments the agent answers, PR review, MCP built in.

174 diffback by verabravo
★ 9 Local & CLI review

Local web UI to review AI-generated code changes and generate structured feedback prompts

175 diffpal by diffpal
★ 9 PR review bots & CI

Open-source, provider-agnostic AI review for pull requests.

176 revio by witold-andelie
★ 8 Local & CLI review

Agentic code review CLI — LangGraph orchestrates 13 deterministic static analyzers (oxlint/bandit/clippy/spotbugs/golangci/cppcheck) + LLM reasoning across 23 languages including industrial PLC. Grounding validator kills hallucinated paths. RAG over your guidelines. dedup --fix actually edits files with multi-step undo (no git required).

177 preflight by jsliapark
★ 8 Local & CLI review

⚡ Preflight — AI code review before you open the PR Multi-agent system that gives instant, senior-level feedback on git diffs.

178 objection by victorserpa
★ 7 Code review skills

OBJECTION! A skill and plugin for AI coding agents (Claude Code, Codex, Cursor, Gemini): accusers, a defender and a judge review the PR, and a gate blocks it until APPROVED.

179 claude-codex-review by agent-0x
★ 7 Local & CLI review

Dual-AI automated code review: Codex finds issues, Claude fixes them — loop until clean.

180 codesense-ai by vikram-codes-hub
★ 7 Security review

AI-powered code review platform that automatically analyzes GitHub PRs for security vulnerabilities, bugs, and complexity issues — posts inline comments like a real senior developer.

181 code-smells-skill by barlevysh
★ 7 Code review skills

🦨 Stop shipping smelly code. 120+ named code smells with before/after examples across C, C++, C#, Java, Python, Go, Rust, JavaScript, TypeScript & SQL — an AI agent skill that improves code quality during both development and code review.

182 adversarial-review by voodootikigod
★ 7 Local & CLI review

Skeptical ship/no-ship adversarial code review of a git diff or branch — runs against any LLM (API or local CLI agent)

183 Agent-Review-CLI by Open-Document-Alliance
★ 6 Local & CLI review

A CLI that orchestrates parallel AI coding agents to reciew, fix and ship code changes

Top 20 Compared

Tool Stars Score
open-code-review ★ 54.3k 82
codex-plugin-cc ★ 35.3k 69
code-review-graph ★ 32.8k 76
pr-agent ★ 16.4k 77
DeepAudit ★ 7.3k 65
claude-code-security-review ★ 7.0k 74
mantis ★ 2.8k 78
shippie ★ 2.5k 68
code-review-skill ★ 2.2k 75
px0 ★ 1.9k 66
sourcery ★ 1.9k 61
roborev ★ 1.8k 66
openreview ★ 1.7k 58
brooks-lint ★ 1.6k 75
kodus-ai ★ 1.6k 64
git-lrc ★ 1.5k 67
sashiko ★ 1.4k 66
guard-skills ★ 1.3k 83
gentleman-guardian-angel ★ 1.2k 59
ai-codereviewer ★ 1.0k 58

Related Categories

Frequently Asked Questions

Is there a code review skill or plugin for Claude Code?

Yes. openai/codex-plugin-cc lets Claude Code hand a review to Codex, and awesome-skills/code-review-skill is a review skill covering React, Vue, Rust, TypeScript and more. For reviews by several models that check each other: chorus-codes/chorus. They are listed on this page under Agent skills and Multi-agent.

What open source AI code review tools review pull requests?

The-PR-Agent/pr-agent reviews pull requests on GitHub, GitLab and others; alibaba/open-code-review is a code review engine used at Alibaba's scale; kodustech/kodus-ai is self-hosted and works with your own LLM. They are listed on this page under PR bots & CI, Local & CLI and Platforms.

What are the best code review tools in 2026?

The top code review tools in 2026 are open-code-review, codex-plugin-cc, code-review-graph. Agent Skills Hub ranks 183 options by GitHub stars, quality score (9 dimensions, including completeness, examples and agent readiness), and recent activity. The list is rebuilt every 8 hours from live GitHub data.

How do I choose between open-code-review and codex-plugin-cc?

open-code-review (54.3k stars) is the most adopted choice for general code review workflows, written in Go. codex-plugin-cc (35.3k stars) is a strong alternative and uses JavaScript instead. Pick by your existing stack: match the language and runtime your team already uses to minimize integration cost. If unsure, start with open-code-review — it has the deepest community and the most examples online.

When should I NOT use a code review tool?

Avoid pre-built code review tools when (1) your use case requires deep customization that the tool's plugin system doesn't support, (2) you have strict compliance requirements that ban third-party dependencies, (3) the tool's maintenance is inactive (last commit >6 months ago), or (4) your data volume is small enough that a 50-line custom script is cheaper than learning the tool. For most production workflows above 100 requests/day, the time savings from a maintained tool outweigh the customization loss.

What's the difference between code review and claude code hooks, subagents & statusline?

Code Review focuses specifically on claude code review skills and ai code review tools for claude code and codex: pr review bots, local cli reviewers, security review and multi-agent review. every one is security-graded before you install it. Claude Code Hooks, Subagents & Statusline is a related but distinct category — see https://agentskillshub.top/best/claude-code-hooks/ for those tools. The two often appear in the same agent pipeline but solve different problems: choose code review when your primary goal is the specific task, and claude code hooks, subagents & statusline when the workflow is broader.

Is open-code-review better than building it yourself?

For most teams, yes. open-code-review has 54.3k stars worth of community testing, handles edge cases you haven't thought of, and ships with documentation. Build your own only when (1) your requirements are deeply non-standard, (2) you have a security/compliance reason to avoid OSS dependencies, or (3) the maintenance burden is small enough (<200 lines of code) that you'll save time long-term. The break-even point is usually around 2-3 weeks of dev time saved.

Are these code review tools free to use?

Most code review tools listed are open source under permissive licenses (MIT, Apache 2.0). A handful offer paid managed/cloud versions on top of free self-hosted core. Always check the LICENSE file on each tool's GitHub repository before commercial use — some use AGPL or non-commercial restrictions that may not fit your deployment model.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

Get Weekly AI Tool Picks

Top 20 fastest-growing AI tools delivered every Monday. Free.

No spam, unsubscribe anytime.

Explore All Skills on Agent Skills Hub