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.
Skill Claude CodeCodex
You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5, C.
Plugin Claude Code
Bundles 1 skill, 1 agent, 1 MCP server · 139 tokens together
Delegate code review, bug/root-cause investigation, logic-math verification, and bounded implementation to OpenAI Codex (GPT-5.5) via a background Sonnet subagent that calls the bundled codex-mcp tools.
danielsimonjr/beyondcompare-mcp
MCP server Claude CodeCodexCursor +2
MCP server "beyondcompare-mcp" as configured in danielsimonjr/beyondcompare-mcp. Runs locally from the @danielsimonjr/beyondcompare-mcp npm package.
ProductionMasterAI/production-master
Skill Claude Code needs its repo
Build all workspaces, run tests, lint, and validate the install manifests for the production-master thin-client monorepo. Use before opening a PR or when verifying a local checkout is healthy. Triggers on "build and test", "run the checks", "validate manifests", "verify the repo".
Plugin Claude Code
Bundles 11 skills · 239 tokens together
Run claude, codex, opencode, Antigravity, or any CLI coding agent as MCP tools from Claude Code, plus structured read-only code review.
danhuaxiansheng/claude-code-cleanup-skills
Plugin Claude Code
Bundles 3 skills · 305 tokens together
Collection of code cleanup skills for necessary-code audits, unused-code checks, and page-flow cleanup.
Plugin Claude Code
Bundles 1 skill, 1 agent · 108 tokens together
Two-gate principal-engineer quality check: a design-time skill that reviews an approach for scalability and maintainability before code, and a Stop-hook code gate that reviews the diff for performance and spaghetti anti-patterns before a task completes.
Skill Claude CodeCodex
Diff-focused PR/MR review that resolves merge conflicts, fixes the clear-cut findings itself, commits them locally, explains everything in plain language, and pushes to the PR/MR branch after your approval.
Plugin Claude Code
Bundles 6 skills · 682 tokens together
Verified, version-matched Agent Skills for .NET and AI-agent development: msaf-architect, microsoft-extensions-ai, mcp-sdk, spectre-console, maui-engineer, reviewers.
MCP server Claude CodeCodexCursor +2
Pin visual feedback on any live web page and send it to Claude Code, Cursor or your AI agent. Runs locally from the @yocoolab/mcp-server npm package. Needs 4 environment variables to run.
Plugin Claude Code
Bundles 11 skills, 6 agents, 1 hook · 693 tokens together
Personal engineering standards for Claude Code: an evidence-first persona, feature planning, ADRs and a decision council, session wrap-ups, a code review agent, and default Git conventions for projects that state none.
Agent Claude Code
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
MCP server Cursor
Local-first knowledge graph for token-efficient code review through MCP and CLI. Runs locally from the code-review-graph Python package.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 81 tokens together
Offline, deterministic engineering-trust certificate for a repository: tests, secrets, isolation, claim-vs-reality and CI discipline, scored against a published rubric with cited evidence. No network calls, no telemetry, no model call; the MCP server writes no files.
Plugin Claude Code
Bundles 8 skills, 2 commands, 1 hook, 1 MCP server · 585 tokens together
Codebase knowledge graph with focused development workflow skills. Query architecture, dependencies, blast radius, and more instead of reading files one at a time.
menaawed12/clean-code-refactor
Plugin Claude Code
Bundles 1 skill · 83 tokens together
Behavior-preserving refactoring, review remediation, lint and duplicate-code fixes, and security hardening for code in any major language.
Skill Claude CodeCodex needs its repo
A command-line tool that uses a Chrome browser already signed in to ChatGPT to create images and save them as local files. It supports prompts, reference images, styles, aspect ratios, and output locations.
Skill Claude CodeCodex
Multi-perspective code review covering readability, test coverage, performance, security, documentation accuracy, and best practices. Technology-agnostic — works on any language or stack. Use when reviewing a diff, PR, branch, or set of changed files before merge.
Plugin Claude Code
Bundles 41 skills · 1,431 tokens together
Skills for planning, building, code review, auditing, maintenance, shipping, assistance, writing, Obsidian, and end-to-end workflows.
Skill Claude CodeCodex
Use when the user wants to clean up, audit or refactor a messy or vibe-coded repository — dead code, duplicated logic, god files, circular dependencies — or asks for a codebase health score. Drives the reforge-mcp tools to scan, prioritise and apply one verified fix per commit.
Plugin Claude Code
Bundles 4 skills · 448 tokens together
Feanil's generic skills: draft PR reviews over the GitHub API, GitHub security advisories over the API, CVSS 4.0 scoring, git history editing.
Skill Claude CodeCodex
Run a comprehensive language-agnostic repository health audit, scored 0-100. Detects language, runs native tooling, never assumes JS/Python.
MCP server Claude CodeCodexCursor +2
AI-powered Kanban TUI for autonomous development workflows. Runs locally from the kagan Python package. Needs 3 environment variables to run.
Skill Claude CodeCodex
Audits, reviews, and refactors project architecture, code quality, structure, organization, and technical debt. Use for code review, architecture review, project audits, maintainability improvements, structural cleanup, scalability improvements, and refactoring existing codebases.
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: