Code review

OutlineDriven/odin-reflector

Plugin Claude Code

Bundles 4 hooks

Codex CLI reflector — independent critic, oracle, and metacognition layer.

Orcus2021/code-review-mcp-server

MCP server Claude CodeCodexCursor +2

MCP Server with Code Review. Runs locally from the code-review-mcp-server npm package.

faxenoff/ultracode

Skill Claude CodeCodex

Code analysis for TS/JS/Python/C#/Go/Rust/Java/C++/Swift/Kotlin/Zig/Bash — search, impact, refactoring, security, diagnostics.

Railly/skills

Skill Claude CodeCodex

Gate whether a fix or existing contributor PR is the right thing to build. Use before implementation when a defect has multiple solution shapes or changes a contract, especially session state, long-lived process configuration, restart or reuse behavior, fixes to prior review findings, and decisions to adopt, absorb…

szarkans/multi

Plugin Claude Code

Bundles 6 skills, 5 agents · 734 tokens together

Several models on the same question at once — Claude sub-agents, OpenAI Codex and a cheap third via OpenCode. Review code (code-review), check whether the work is actually finished rather than finished-looking (check-if-done), brainstorm wide with a different model per cognitive frame (adhd), or just ask all of t.

tamnguyendinh/Anvien

Skill Claude CodeCodex

use when user ask to review spec.

Jmosier69/refute

Skill Claude Code

Multi-angle code review that adapts to what is being reviewed — a mid-flight worktree increment, a full PR before production, a merge-window integration sweep, or a security-only pass. Findings are scored, adversarially refuted, widened to the same defect elsewhere in the codebase, and reported to the native review…

wezendy/elon-musk-algorithm-skills

Cursor rule Cursor

Musk 5-step engineering algorithm. Primarily for reviewing and cleaning up existing systems. Apply in strict order: question requirements, delete parts, simplify, accelerate, automate. Bias toward deletion. Never advance to a later step until earlier steps are visibly complete.

Sungmin-Cho/deep-suite

Plugin Claude Code

Plugin marketplace listing 10 plugins: deep-work, deep-wiki, deep-evolve, deep-review, deep-docs.

qingye-lab/rootloom

Skill Codex

Initialize, retrieve, and explicitly update the separate Rootloom Memory plugin's repository-owned architecture, risk, decision, and failure lessons. Use only when explicitly requested. Memory is experimental, advisory, and outside Rootloom Core.

davesheffer/hunch

Cursor rule Cursor

Hunch engineering memory — consult the hunch MCP tools before editing.

oikon48/claudecode-book

Agent Claude Code

A read-only code reviewer for TypeScript, TSX, React, and Next.js projects. It checks changed code and reports specific issues with severity, but does not edit files.

qazi0/claude-plugins

Plugin Claude Code

Bundles 1 skill, 7 commands · 157 tokens together

Access GitHub repository documentation and AI-powered Q&A via DeepWiki - compare repos, explore architecture, quickstart guides, deep dives, and troubleshooting.

Nmor/the-claude-council

Skill Claude Code

Frontend development patterns for React, React Native, Vue, Next.js, SwiftUI, Flutter, state management, performance optimization, and UI best practices.

ilandahan/AID

Plugin Claude Code

Bundles 39 skills, 47 commands, 39 agents, 1 hook · 2,721 tokens together

AI Development Methodology: 6 phase gates from discovery to ship, 28 skills, 38 review sub-agents, and WHY-first enforcement hooks. Stops code being written before the problem is understood.

teakzc/backpack-plus

MCP server Claude CodeCodexCursor +2

MCP server "code-review-graph" as configured in teakzc/backpack-plus. Launched with C:\Python313\python.exe -m code_review_graph serve.

kunaltulsidasani/claude-reimagined

MCP server Claude CodeCodexCursor +2

Local-first knowledge graph for token-efficient code review through MCP and CLI. Runs locally from the code-review-graph Python package.

StringKe/std-agent

Skill Claude CodeCodex

Review the current diff for correctness and regressions.

igloude/ds-skills

Plugin Claude Code

Bundles 4 skills · 118 tokens together

Police large volumes of AI-generated frontend work for design-system conformance, and audit the design system itself so it can be policed. Report-only: verdicts, reviews, plans, and issues — it never edits your code.

QBall-Inc/the-bulwark

Plugin Claude Code

Bundles 30 skills, 17 agents, 6 hooks · 1,988 tokens together

Full-lifecycle SDLC guardrailing framework for Claude Code — from product ideation and planning through implementation, code review, and test validation. Enterprise-grade skills and agents for AI-human peer collaboration.

strikersam/autonomous-ai-agency

Skill Claude CodeCodex

Review codebase or design for modularity problems and produce actionable improvement recommendations. Also guides design of new modular boundaries from functional requirements. Inspired by Vlad Khononov's balanced-coupling model and golden-age-of-modularity principles. NOTE: Full upstream plugin at…

SunflowersLwtech/covate

Plugin Claude Code

Bundles 1 MCP server

Covate - Context-aware learning sidebar for AI coding assistants, served as an MCP server.

user-hash/Lifeblood

Skill Codex

Use when an agent should work with Lifeblood's MCP semantic-code tools: analyzing C# or Unity workspaces, querying symbols/dependencies/blast radius/file impact/test impact, checking architectural invariants, validating edits with compilecheck/diagnose, or choosing the right Lifeblood tool instead of grep-style…

dkstm95/hope

Plugin Claude Code

Bundles 6 skills · 199 tokens together

Adds intent-and-decision alignment before implementation with an optional durable HTML record, explicit behavior-preserving codebase cleanup, evidence-based review, PR explanations, clear explanatory visuals, and clear writing. Requires Node.js 22 or newer.