Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 269,003 indexed, measured the same four ways as everything else here.
ez-lbz/claude-code-security-skills
Skill Claude CodeCodex
Scans source code for security vulnerabilities — injection flaws, authentication bypasses, hardcoded secrets, XSS, and more — then filters false positives and ranks findings by severity and confidence. Supports all programming languages. Uses a three-phase audit-filter-report workflow with customizable scan categories…
MCP server Claude CodeCodexCursor +2
MCP server "rbinmcp" as configured in kirkderp/rbinmcp. Runs in Docker (ghcr.io/kirkderp/rbinmcp:1.3.0).
Skill Claude CodeCodex
Digital Citizenship Protocol — identity, intent declaration, and audit trail for AI agents.
houarnu166/skillful-agent-system-builder
Skill Claude CodeCodex
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
adanghd/sender-kalopilot-skill
Skill Claude CodeCodex
Kirim data TikTok Shop dari KaloPilot ke WhatsApp dan/atau Telegram secara terjadwal. Gunakan skill ini ketika user ingin setup pengiriman otomatis data kalopilot ke WA atau Telegram, mengubah jadwal, mengirim data sekarang, atau mengelola konfigurasi sender.
Skill Claude CodeCodex needs its repo
Build multi-page Astro websites from provided content (markdown articles, PDFs, eBooks). Use this skill when asked to build a website, create a new site, set up a web project, or turn content into a website. Triggers on phrases like "build a website", "new site", "create a website", "set up a site", "turn this into a…
Skill Codex
Use when the task mentions CodeKit, SiFli SDK CodeKit, the CodeKit MCP server, SiFli board/project/build/download/serial/monitor workflows, or VS Code extension-hosted SiFli tooling.
Skill Claude CodeCodex needs its repo
Research, author, and validate AI agent artifact catalog entries documenting the forensic artifacts AI agents leave on endpoints - install paths, config and credential files, MCP server configs, listening ports, process trees, registry keys, and the Windows event log records that prove a tool ran. Use this skill…
Skill Claude CodeCodex
Production pipeline for interactive and generative visual art using p5.js. Creates browser-based sketches, generative art, data visualizations, interactive experiences, 3D scenes, audio-reactive visuals, and motion graphics — exported as HTML, PNG, GIF, MP4, or SVG. Covers: 2D/3D rendering, noise and particle systems…
malvoamadeus-png/smart-money-miner
Skill Claude CodeCodex
A tool for finding and analyzing cryptocurrency wallet addresses associated with profitable trading activity. It covers tokens on PumpFun, Four Meme, and BNB Smart Chain, also called BSC.
Skill Claude CodeCodex
Review code changes for quality, correctness, and best practices.
MCP server Claude CodeCodexCursor +2
Lightweight browser automation for AI agents: navigate, screenshot, extract, PDF. One small binary. Runs locally from the @kitewright/mcp npm package.
vibeforge1111/vibeship-spawner
MCP server Claude CodeCodexCursor +2
MCP server "spawner", hosted remotely at mcp.vibeship.co, as configured in vibeforge1111/vibeship-spawner.
Carl-AI-Lab/feishu-bot-builder
Skill Claude CodeCodex
A guide to building Feishu (also called Lark) chat robots and message integrations. Feishu is a workplace messaging platform.
junsuk5/survival-flutter-skills
Skill Claude CodeCodex
A presentation-layer pattern for Flutter apps using ChangeNotifier ViewModels, immutable state, explicit actions, and separate root and screen widgets. The presentation layer is the part that connects application data to the user interface.
Skill Claude CodeCodex
Understands nono security sandbox constraints. Use when running inside a nono sandbox, when tool operations fail with permission errors, or when the user asks about sandbox capabilities.
Skill Claude CodeCodex
Skill "<kebab-case-name>" from jarvis823/skill-forge, covering when to invoke, what this repo does, house conventions (do this), code example from this repo and known drift (don't copy these).
gocallum/nextjs16-agent-skills
Skill Claude CodeCodex
Comprehensive guide for building AI agents using ToolLoopAgent, workflow patterns, and AI SDK UI components (useChat, generative UIs, tool calling).
angelapaia/n8n-to-claude-skill
Skill Claude CodeCodex
Migra workflows de n8n/Make al ecosistema Claude Code. Analiza JSONs, mapea nodos, propone implementacion (skills, crons, web apps, dashboards) y detecta mejoras. Usa cuando el usuario pegue un JSON de n8n o mencione migrar automatizaciones.
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Skill Claude CodeCodex
Search, browse, and resume past AI coding sessions across GitHub Copilot, Claude Code, OpenCode, Cursor, and Codex using the sessfind CLI. Use this skill whenever the user wants to find a previous conversation, search through session history, resume or continue an old session, check what was discussed before, look up…
Skill Claude CodeCodex
Manage background processes like dev servers. Use when you need to start, stop, or check status of long-running processes.
Skill Codex
A Chinese-language toolkit for managing coding-agent skills throughout their lifecycle, from creating and organizing them to testing and improving them. It supports several workflows for simple and complex skill projects.
Skill Claude CodeCodex
Loop Review is a periodic quality audit of the KitchenLoop's recent output. It reads experience reports, inspects merged PRs and their code changes, optionally runs external auditors (Codex, Gemini), and produces a durable synthesis report with findings categorized by severity.
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: