Code review

sivaguru-2113/Agent-persona

Skill Claude CodeCodex

Evaluates code diffs for correctness, maintainability, performance, security, and testability.

SauliusDev/glyph

Skill Claude CodeCodex

MUST be used when editing code that carries a hard-won lesson, a deliberate decision, or a correctness invariant. Enforces inline @agent: notes recorded next to the code, so the next agent reads the reason for free and does not repeat the mistake. Load whenever writing or modifying non-trivial logic. Paired with…

imisic/claude-marketplace

Plugin Claude Code

Bundles 4 skills · 93 tokens together

Generate a code review skill and coding rules fitted to your own repository, then improve them from what your reviews keep finding. You start each generator yourself, and the learning loop asks before it applies any change.

rbutera/harness-bridge

Skill Claude CodeCodex

Ask Claude Code for a second opinion — code reviews, explanations, plan critiques, performance analysis, or general questions.

Sandip124/wisegit

MCP server Claude CodeCodexCursor +2

Extracts decision intent from git history and protects intentional code from AI modification. Runs locally from the @sandip124/wisegit npm package.

SamoraDC/Tetrad

MCP server Claude CodeCodexCursor +2

Quadruple consensus MCP server for code validation using Codex, Gemini, and Qwen. Runs locally from the @samoradc/tetrad npm package.

Thinkode/thinkreview-mcp

MCP server Claude CodeCodexCursor +2

Live PR/MR code reviews via reviewurlcode. OAuth or portal Bearer auth. Remote server at mcp.thinkreview.dev.

Shawn5cents/agentskin

Skill Claude CodeCodex

Auto Review closeout. Codex review is the default when no engine is set and is the recommended reviewer.

dingdawg/dingdawg-agent-1

MCP server Claude CodeCodexCursor +2

One of 9 in server.json

AI code review — security, quality, performance. Learns your patterns. Receipted. Runs locally from the dingdawg-code-review npm package. Needs 1 environment variable to run.

darylmcd/Roslyn-Backed-MCP

Plugin Claude Code

Bundles 41 skills, 3 agents, 2 hooks, 2 MCP servers · 3,396 tokens together

Semantic C# analysis and refactoring for AI agents, powered by Roslyn. Load .sln/.csproj files, inspect the live MCP catalog at runtime, and use 32 bundled agent skills for analysis, refactoring, testing, architecture review, and release workflows.

davidweb3-ctrl/mcp-git-enhanced

MCP server Claude CodeCodexCursor +2

One of 2 in server.json

Enhanced Git MCP Server - Code review, commit analysis, and branch management. Runs locally from the @davidweb3-ctrl/mcp-git-enhanced npm package. Needs 1 environment variable to run.

invigil/invigil

MCP server Claude CodeCodexCursor +2

Linters check your code. Invigil checks whether your repo is legible — to newcomers and to AI agents. Runs locally from the invigil Python package.

pamela-0/safe-fix-mcp

Skill Claude CodeCodex

Finds real dead code (unused imports, functions, classes) and unused dependencies in a Python repository, and proposes a safe, test-gated branch+PR to remove the safely-removable ones. Use this whenever the user asks to find or clean up dead code, unused imports, unused dependencies, or "bloat" in a Python project…

pedroknigge/arkgate

Skill Claude Code

Map import rules and leftover design. No apply. CLI is a sensor; you read the tree.

webmoleai/mcp-vibe-checker

MCP server Claude CodeCodexCursor +2

Vibe-check your code — personality types, energy ratings, aesthetic suggestions. Runs locally from the mcp-vibe-checker npm package.

x51xxx/kimi-mcp-server

MCP server Claude CodeCodexCursor +2

MCP server bridging AI assistants to Moonshot AI Kimi Code CLI for code analysis and review. Runs locally from the @trishchuk/kimi-mcp-server npm package. Needs 4 environment variables to run.

paoloricciuti/letmediff

MCP server Claude CodeCodexCursor +2

The official Letmediff MCP server helping you review your code with an agent first workflow. Runs locally from the letmediff npm package.

Patent-PreCheck/patent-precheck-mcp

Skill Claude CodeCodex

Score code for patentability with Patent PreCheck. Use when the user asks "can this be patented?", wants a patentability/novelty/§101/§102/§103 check, or wants to know if an invention or codebase is filing-ready.

MyAgentHubs/aimemo

Skill Claude CodeCodex

Review GitHub PRs with learned code style preferences using aimemo persistent memory.

SKY-lv/diff-viewer

Skill Claude CodeCodex

Skill "diff-viewer" from SKY-lv/diff-viewer, covering skylv-diff-viewer, skill metadata, what it does, unified diff (default) and side-by-side view.

fullstackcrew-alpha/skill-smart-pr-review

Skill Claude Code

Opinionated AI code reviewer — not a yes-machine. 6-layer deep review (logic, edge cases, performance, security, maintainability, architecture) with Devil's Advocate mode and standardized MUST FIX / SHOULD FIX / SUGGESTION output. Supports GitHub PR URL, local diff, commit hash. Languages: TypeScript/JavaScript…

aiflowlearn/awesome-claude-code

Command Claude Code

A review command that examines the current changes from four angles: risk, regressions, missing tests, and readability.

andr-ca/agentharness

Skill Claude Code

Use when reviewing a diff, pull request, or code change — systematic checklist for correctness, clarity, security, testability, and adherence to the project's conventions. Covers what to look for, how to give actionable feedback, and when to approve vs. request changes.

RockaRhymeLLC/claude-code-skills

Plugin Claude Code

Bundles 7 skills · 428 tokens together

Production-tested Claude Code skills for professional development workflows — code review, smart commits, PR generation, spec-driven development, and context management.