19,479 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
shadoprizm/cyberlens-mcp-server
MCP server Claude CodeCodexCursor +2
Security scanning for websites, public repositories, and Open CLAW skills. Runs locally from the @shadoprizm/cyberlens-mcp-server npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
Codebase analysis tools for AI agents: complexity, prop drilling, doc coverage, code smells. Runs locally from the scopewalker-mcp npm package. Needs 1 environment variable to run.
Command Claude Code
A code-review command that examines current changes for risks, regressions, missing tests, and readability.
Skill Claude CodeCodex
A code-review guide for native WeChat Mini Program projects, which are small applications that run inside WeChat.
Skill Codex
Review existing code, documents, products, tests, and hotfixes with relevant companion skills and evidence-backed, severity-ranked findings, without editing reviewed content.
Plugin Claude Code
Bundles 2 skills, 3 commands, 1 agent, 1 MCP server · 259 tokens together
Orchestrate AI-driven PR reviews at scale. Unified MCP interface for CodeRabbit, Gemini, Copilot, Sourcery, Qodo, Codex, and Greptile with parallel multi-agent coordination.
MCP server Claude CodeCodexCursor +2
MCP server "gitlab" as configured in DevquasarX9/mcp-gitlab. Launched with gitlab-mcp-server. Needs 4 environment variables to run.
MCP server Claude CodeCodexCursor +2
TUT (Take Ur Turn): multi coding-agent collaboration via a local Context Hub — append-only shared memory, derived task state, human approval gates. Runs locally from the take-ur-turn npm package.
Skill Claude CodeCodex
Use when Codex must directly operate or troubleshoot the installed grok-plugin-codex MCP capability surface, including CLI/model checks, literal prompt runs or continuations, session inspection or export, and known background-job control. Do not use for bounded repository delegation, implementation, review…
gongchen0916/claude-science-codex-review
Skill Claude CodeCodex
Use when Claude Science must obtain an independent OpenAI Codex review, second opinion, reproducibility check, statistical or figure audit, debugging handoff, or delegated implementation.
MCP server Claude CodeCodexCursor +2
MCP server "gitlab-mr-reviewer" as configured in katamaraju/ai-code-reviewer. Runs locally from the gitlab-mr-reviewer npm package.
MCP server Claude CodeCodexCursor +2
Local-first, auditable code review system for coding agents. Runs locally from the @yibei-wz/agent-review npm package.
mdanouf44-cyber/Code-review-agent-with-MCP
MCP server Claude CodeCodexCursor +2
MCP server "ai-review-agent" as configured in mdanouf44-cyber/Code-review-agent-with-MCP. Runs locally from the ai-review-agent Python package.
Plugin Claude Code
Bundles 7 skills, 2 hooks, 1 MCP server · 573 tokens together
Slash commands for /q-plan, /q-brainstorm, /q-skystorm, /q-validate, /q-review, /q-research via the quorum MCP server.
Skill Claude CodeCodex
Review Bitbucket Server pull requests from the shell with the bb CLI, with no MCP server process involved. Use when the user asks to review a Bitbucket PR, look at a merge request, read a PR's diff or changed files without cloning, post review comments or inline findings, draft a review and publish it with a verdict…
MCP server Claude CodeCodexCursor +2
Adversarial Quality Gate MCP for vibe-coding: IDE AI vs Critic AI, human decides on deadlock. Runs locally from the vibe-gate-mcp npm package. Needs 16 environment variables to run.
Skill Claude CodeCodex
A GitLab workflow tool for GitLab, a service for hosting code and managing team development work. It covers merge requests, code review, automated build checks, branches, and merges while following stated team rules.
Plugin Claude Code
Bundles 20 skills, 5 agents, 5 hooks · 1,825 tokens together
Domain-knowledge-driven agent workflow plugin for complex projects (pilot-planner → [pilot-planner-critic] → pilot-generator → pilot-evaluator) + pilot-code-review for pre-PR code review. /pilot:autopilot provides opt-in supervised autonomy for a single feature.
Plugin Claude Code
Bundles 3 skills, 5 agents · 436 tokens together
Review every code change before the turn ends: fresh-context reviewer agents, a verified finding standard, honest convergence, and a measured token budget — enforced by a Stop hook, graph-aware when you have a code graph, zero-cost when you don't.
Plugin Cursor
Bundles 29 skills, 1 agent, 3 hooks · 1,377 tokens together
Engineering skills for code that must survive contact with reality.
Agent Claude Code
Use this agent when you need to review code for adherence to project guidelines, style guides, and best practices. This agent should be used proactively after writing or modifying code, especially before committing changes or creating pull requests. It will check for style violations, potential issues, and ensure code…
MCP server Claude CodeCodexCursor +2
One of 2 in mcp.json
GitHub's hosted MCP server: lets the agent search code, read and create issues and pull requests. Remote server at api.githubcopilot.com.
Plugin Cursor
Score any public GitHub repo 0-100 against the commit.show audit rubric — Lighthouse, repo signals, security, surfaced as paste-ready markdown inside Cursor.
Cursor rule Cursor
DeterminAgents audit harnesses — apply when the user asks for a code audit, security review, test-gap analysis, or autonomous completion loop.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: