Code-Review plugins

Reviews code for real bugs: off-by-ones, null derefs, race conditions, swallowed errors. Skips style nitpicks.

Finds real bottlenecks. DB N+1, memory leaks, blocking calls, re-renders.

Finds code that fails silently: swallowed errors, failures masked as success, fallbacks that hide breakage. Runs on every PR review.

Automatically update CLAUDE.md file based on recent code changes

1 command

Perform a comprehensive code review of recent changes

1 command

Get comprehensive code reviews with suggestions for improvements, best practices, and potential issues.

1 command

Run Warden and query Warden Service

Review code changes locally with your own agent as the engine, and set up, reconfigure, troubleshoot, or remove OrcaCode Review — AI pull-request review powered by OrcaRouter — in any GitHub repository.

2 skills

SonarQube is the AI code quality and security verification platform used by millions of developers to catch bugs, vulnerabilities, and leaked secrets. This plugin enforces those standards in the agent coding loop: 7,500+ distinct issue types, secrets scanning, agentic analysis, and quality gates across 40+ languages.

10 skills · 1 agent

dependabotやrenovateが作成した依存関係の更新pull requestを、リポジトリごとに決めた自動化段階までレビュー・修正・mergeする指揮。起動したsessionが指揮役になり、pull requestごとに起動したsubagentがレビューと修正を行う。起動プロンプトの作成と、Claude Code on the webのroutineへの登録も行う。

5 skills

deprecated。代わりにdependency-updateを使う。ライブラリ更新pull requestのレビュー手順。dependabot/renovatebot PRの分析、release note調査、コード更新、過去の失敗調査を行う。

1 skill

PRのレビュー報告書を作成する。bugや脆弱性の調査だけでなく、exportされた対話コンテキスト・PR概要欄・実装されたコードの整合性を確認し、実装者の正気を疑う。

1 skill

Perform security audit on codebase

1 command

Get comprehensive code reviews with suggestions for improvements, best practices, and potential issues.

1 command

Perform a comprehensive code review of recent changes

1 command

Code review, compare, and debate tools using multiple AI models

Logic-first code review using semi-formal execution tracing. Surfaces behavioral bugs, type contract breaches, boundary blindspots, and interprocedural semantic mismatches — the logic errors that cause production incidents in syntax-clean code.

11 skills · 6 commands · hooks

Adversarial multi-model code review and model dispatch. Orchestrates Claude, Codex CLI, and Gemini CLI for cross-examined code review with 5 specialized reviewers.

1 skill · 3 commands · 1 agent

Hostile, bias-free review of a change — dispatches independent adversarial reviewers that hold the code against what was agreed and question whether what was agreed was right, plus a standalone false-positive filter, and reports only verified findings in plain language. Ships a full 18-reviewer panel, a cheaper quick panel that proposes the fewest reviewers that fit the change, lets you add or drop any, and keeps both verification gates, and a fast one-reviewer review that checks its own findings and re-checks only what changed since the last review.

3 skills

Governance-aware code review for the DSG Control Plane. Reviews changes against the repo's API route conventions, security conventions, truth boundary, runtime spine flow, deterministic gate boundary (UNSUPPORTED is never PASS), and Supabase/RLS rules. Includes a security-reviewer subagent.

1 skill · 1 agent

CI-optimized code review: multi-agent parallel review (lean/full profiles) with confidence scoring and atomic GitHub PR review posting via gh api

1 skill · 11 agents · hooks

AI Council - Orchestrate multiple AI consultants (Gemini 3.8 Flash, Codex, GLM-5.3, Kimi K3) for consensus-driven code reviews, plan validation, and architectural decisions

3 skills · 1 command · 7 agents · hooks

Clears AI reviewer feedback on your PR: reads real review-thread state, sweeps the sibling instances the reviewer missed, gates every push on your repo's own tests, then requests re-review — hard-capped at 3 re-review requests. Claude Code, Codex, Gemini and Copilot built in; any reviewer bot can be configured.

1 skill · hooks

Review Jules AI agent pull requests using council review with smart quick/full mode selection and GitHub PR review posting

1 skill

44 code-review and maintenance skills derived from a verified code-quality research atlas: 28 diff-shaped review lenses, 11 repo-shaped audits, a decision-time lens, an artifact-conventions lens (reviews authored artifacts like SKILL.md against their own standard — the diff-shaped count above includes the three product-experience lenses of Cluster VII: usability & interaction quality, outcome instrumentation, and conceptual integrity), a router that picks the right lenses for a change, a pre-pass that grounds the review in the repo's own linters and scanners, and a synthesizer that merges their findings into one ranked verdict, with provenance, examples, and cross-model evals.

45 skills · 6 commands · hooks

Collapsed 4-entrypoint form for cloud / account-skill / context-budget installs — lenses bundled and loaded on demand. Install this OR the standalone plugin, not both.

4 skills · hooks

Two skills: /branchdiff-review (post inline review comments on a diff) and /branchdiff-resolve (apply fixes for open review threads).

2 skills

Turn review into an organizational judgment asset. Review Judgment as Code for AI-assisted development: a Skill Registry of versioned, repo-owned review skills, driven by a review agent that runs perspective-based reviewer roles and verifies findings.

131 skills · 6 commands · 1 agent · hooks

Explica una pull request de GitHub a quien la va a revisar sin leer el código: un comentario Markdown listo para publicar con riesgo, diagramas, efectos secundarios, contraste con el ticket, decisiones sin aprobar, cobertura de tests y quién se entera si falla.

1 skill

Read-only simplicity reviewer for code diffs, design documents and architecture, applying Steve Jobs's philosophy: remove everything that isn't essential until what remains feels inevitable. /snap reviews a diff, files or a design doc; /rethink redesigns a subsystem from its essence. Never edits files. Requires bash and git; on Windows, run Claude Code with Git Bash.

1 skill · 2 commands · 1 agent