Everything for Codex

Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 272,429 indexed, measured the same four ways as everything else here.

mcp-hydrocoder-ssh

16657

hydroCoderClaud/mcpHydroSSH

MCP server Claude CodeCodexCursor +2

SSH MCP Server for Claude Code. Runs locally from the mcp-hydrocoder-ssh npm package.

not rated 6 6mo ago A tokens not measured original MIT

notepatra-mcp

16658

singhpratech/notepatra

MCP server Claude CodeCodexCursor +2

MCP server "notepatra-mcp" as configured in singhpratech/notepatra. Launched with notepatra-mcp.

not rated 6 20d ago A tokens not measured GPL-3.0

yomitan-mcp-server

16659

GoRakuDo/yomitan-mcp

MCP server Claude CodeCodexCursor +2

MCP server for Yomitan dictionary lookup. Runs locally from the yomitan-mcp-server npm package.

not rated 6 6mo ago A tokens not measured original MPL-2.0

agendum

16660

sralli/agendum

MCP server Claude CodeCodexCursor +2

Universal project management for AI coding agents — MCP server + CLI + git-native task board. Runs locally from the agendum Python package.

not rated 6 5mo ago A tokens not measured original MIT

pipeshub

16661

pipeshub-ai/mcp-server

Skill Claude CodeCodex

Search and ask questions about the organization's documents — Drive, Slack, Gmail, Jira, Confluence, and the knowledge base. Use whenever a question could be answered by company content rather than general knowledge.

not rated 6 changed 18d ago B 44 tokens original Apache-2.0

audit

16662

telus-labs/stagecraft

Skill Claude CodeCodex

Run a structured codebase audit — map architecture, assess health (compliance / tests / docs), perform deep analysis (security / performance / code quality), and synthesize a prioritized roadmap. Use this skill when the user says things like 'audit the codebase', 'understand this project', 'find problems', '/audit'…

not rated 6 4d ago A SkillSpector: pass 103 tokens original MIT

speckit-checklist

16663

grostim/cloudcli-cron

Skill Claude CodeCodex

Generate a custom checklist for the current feature based on user requirements.

not rated 6 2mo ago A 19 tokens

npm-trusted-publishing

16664

JoviDeCroock/skills

Skill Codex

Use when hardening npm package release workflows with trusted publishing, OIDC, GitHub environments, pinned GitHub Actions, disabled publish-path caching, Changesets release PRs, direct tag-based npm publish flows, staged publishing, or npm release-supply-chain reviews.

not rated 6 changed 17d ago A 59 tokens

dream-wf-grill-prd

16665

dream-rec/dream-workflow

Skill Claude CodeCodex

Use during Trellis planning when creating or refining a PRD. Applies grill-me style clarification: ask one question at a time, inspect code before asking, provide options and a recommended answer, update prd.md after each decision, verify technical facts against latest knowledge with grok-search-mcp before…

not rated 6 1mo ago A 77 tokens

macos-vision-mcp

16666

woladi/macos-vision-mcp

MCP server Claude CodeCodexCursor +2

Local OCR & screen understanding for agents: read any window, find what to click. No uploads. Runs locally from the macos-vision-mcp npm package.

not rated 6 1mo ago A tokens not measured original MIT

diagram

16667

victusfate/scaffold

Skill Claude CodeCodex

Generate or update a mermaid diagram with the .mmd text as source of truth — defaults to a lightweight zero-dependency Node live-preview server that watches the .mmd and hot-reloads a browser tab (pan/zoom), with a self-hosted mermaid.live editor via Docker, system-viewer SVG, VS Code live preview, or a public…

not rated 6 yesterday A 135 tokens original MIT

skincare-products-skill

16668

mochenxin2025-png/skincare-products-skill

Skill Claude CodeCodex

Dermatology-oriented cosmetic formulation analysis. Analyzes skincare, sunscreen, cleanser, shampoo, and cosmetic products by ingredient list using first-principle reasoning, evidence-based evaluation, and a structured scoring system. Use when the user asks to analyze, evaluate, review, or score a cosmetic product…

not rated 6 2mo ago A 181 tokens

local-test-runner

16669

cohere-ai/vllm-skills

Skill Claude CodeCodex ✓ vendor

Run vLLM Buildkite CI-equivalent tests locally on NVIDIA GPUs using the current shell environment. Use when the user asks to run CI tests locally, reproduce CI failures, run a specific test file or test area, or match Buildkite test behavior.

not rated 6 3mo ago A 56 tokens original Apache-2.0

nextjs-reusable-table

16670

ninsau/nextjs-reusable-table

Skill Claude CodeCodex needs its repo

Use this skill when building or customising data tables with nextjs-reusable-table. Covers installation, all props, sorting, pagination, search, row actions, dark mode, custom styling, and Tailwind setup for Next.js 13+ and React 18+.

not rated 6 6mo ago A 59 tokens original 0BSD

vulners-mcp

16671

vulnersCom/vulners-mcp

MCP server Claude CodeCodexCursor +2

MCP interface server fronting the Vulners API (https://vulners.com). Runs locally from the vulners-mcp Python package.

not rated 6 5mo ago A tokens not measured

quilt

16672

wkoverfield/quilt

MCP server Claude CodeCodexCursor +2

Track which AI agent wrote which lines in a shared Git checkout; each commits only its own lines. Runs locally from the @quilt-dev/cli npm package.

not rated 6 3d ago A tokens not measured original MIT

ozon-seller

16673

woyaxnini/mcp-ozon-seller

MCP server Claude CodeCodexCursor +2

MCP server for Ozon Seller API. 26 tools: products, prices, orders, analytics, finance, rating. Runs locally from the @woyax/mcp-ozon-seller npm package. Needs 2 environment variables to run.

not rated 6 5mo ago A tokens not measured

security-scan

16674

ArmisSecurity/armis-appsec-mcp

Skill Claude CodeCodex

On-demand AI-powered security scanning. Use when the user asks to scan code for vulnerabilities, run a security check, scan code for security issues, scan a file, scan a diff, scan staged changes, check for security issues, check for secrets, find hardcoded credentials, or run an appsec scan. Triggers: /security-scan…

not rated 6 2d ago A 110 tokens original Apache-2.0

tg-user-skill

16675

Maatq1544/ai-agent-telegram-skill

Skill Claude CodeCodex

Read, search, and send Telegram messages from any AI agent via the @cyberdrk/tg CLI. Use when the user asks to check inbox, search chats, send a message, look up a contact, list group members, or download media (photos/videos/files) from accessible chats. Works with Claude Code, Cursor, Aider, OpenHands, and any agent…

not rated 6 4mo ago A 105 tokens original MIT

browserstack

16676

emersinrp/qa-expert-agent

Skill Claude CodeCodex

Use this skill for BrowserStack App Automate (mobile E2E on real devices) and App Live (manual/interactive mobile testing) — uploading apps, configuring capabilities (bstack:options), running XCUITest / Espresso / Detox / Appium suites on cloud, parallel sharding, local testing tunnel (Local/Gateway), CI integration…

not rated 6 2mo ago A 174 tokens

grug-brain

16677

nickperkins/grug-brain

Skill Claude CodeCodex

Apply the Grug Brained Developer philosophy: fight complexity, prefer simple solutions, avoid over-engineering. Use when asked to think like grug, apply grug principles, or review code for unnecessary complexity.

not rated 6 6mo ago A 47 tokens

plugin-self-improve

16678

patrykkopycinski/elastic-cursor-plugin

Skill Claude CodeCodex

Audit and improve the Elastic Cursor Plugin itself — analyze coverage gaps, identify missing tools/skills/rules, assess quality, and implement improvements. Use when asked to improve, extend, audit, or enhance the plugin.

not rated 6 4mo ago A 48 tokens

wave-spec

16679

dimkurilo/opencode-skills

Skill Claude CodeCodex

A planning workflow for multi-day or multi-session projects. It creates shared specification, plan, worker-brief, status, and handoff files in the repository before work begins.

not rated 6 1mo ago A 155 tokens original MIT

api-docs-generator

16680

patricio0312rev/skillset

Skill Claude CodeCodex needs its repo

Generates API documentation using OpenAPI/Swagger specifications with interactive documentation, code examples, and SDK generation. Use when users request "API documentation", "OpenAPI spec", "Swagger docs", "document API endpoints", or "generate API reference".

not rated 6 8mo ago A 54 tokens copy · 100% MIT

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: