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. 281,625 indexed, measured the same four ways as everything else here.

absurd

817

earendil-works/absurd

Skill Claude CodeCodex

Debug and operate Absurd durable workflows with absurdctl. Use when working with Absurd queues, tasks, runs, events, retries, schema setup, or when a user wants to inspect, spawn, retry, cancel, or wake workflows.

not rated 2.5k +13 yesterday A SkillSpector: pass 51 tokens original Apache-2.0

fns-mcp

818

haierkeys/fast-note-sync-service

Skill Claude CodeCodex

Fast Note Sync Service MCP SSE Skill (Bilingual). Allows agents to access and manage notes, files, and vaults via the MCP protocol.

not rated 2.5k +27 2mo ago A SkillSpector: pass 34 tokens original Apache-2.0

chrome-cdp

819

mattzcarey/shippie

Skill Claude CodeCodex

Drive a headless Chrome over the Chrome DevTools Protocol (CDP) for browser QA — navigate, click, fill forms, read the DOM/accessibility tree, screenshot, and assert. Use whenever a task requires loading a web page and interacting with it like a user. Chrome is launched by a bash step (recipe below); this skill…

not rated 2.5k +5 16d ago A SkillSpector: warn 91 tokens original MIT

xiaohongshu-ops

820

Xiangyu-CAS/xiaohongshu-ops-skill

Skill Claude CodeCodex

A Xiaohongshu operations skill covering account positioning, topic research, content creation, publishing, review, and corrective work. Xiaohongshu is a Chinese social platform for discovering and sharing lifestyle and product content.

not rated 2.5k +49 7mo ago A 91 tokens

penecho-canvas-uat

821

penecho/penecho

Skill Codex

A canvas tool for PenEcho's user-acceptance testing (UAT), where people check that software works as expected. It lets an agent place diagrams, interactive demonstrations, and handwritten feedback beside the chat when the user explicitly selects PenEcho UAT testing.

not rated 2.5k +4 5d ago A 85 tokens AGPL-3.0

vercel/workflow

Skill Claude CodeCodex ✓ vendor

Upgrades a custom Workflow SDK World implementation from the v4 spec, or from a 5.0.0 beta, to the current v5 spec (spec version 8). Use when a package implements the World interface from @workflow/world and is moving to 5.x, or is on a 5.0.0 beta and the runtime reports This Workflow runtime supports Worlds with spec…

not rated 2.5k +9 changed 8d ago A SkillSpector: pass 229 tokens original Apache-2.0

notte

823

Bitterbot-AI/bitterbot-desktop

Skill Claude CodeCodex

Deploy browser automations as scheduled, API-callable serverless Functions — plus stealth sessions, vault-backed login, captcha solving, and natural-language agent runs via the Notte CLI. Turns any browser flow into a deterministic Bitterbot-callable endpoint, ideal for crystallized skills + dream-engine cron…

not rated 2.5k +2 yesterday A SkillSpector: warn 63 tokens original MIT

tavily-mcp

824

tavily-ai/tavily-mcp

MCP server Claude CodeCodexCursor +2

MCP server for advanced web search using Tavily. Runs locally from the tavily-mcp npm package. Needs 2 environment variables to run.

not rated 2.5k +9 yesterday A Socket: warn tokens not measured original MIT

paperbanana

825

llmsresearch/paperbanana

MCP server Claude CodeCodexCursor +2

Agentic framework for automated academic illustration generation. Runs locally from the paperbanana Python package.

not rated 2.5k +22 1mo ago A Socket: warn tokens not measured original MIT

subsy/ralph-tui

Skill Claude CodeCodex

Convert PRDs to beads for ralph-tui execution using beads-rust (br CLI). Creates an epic with child beads for each user story. Use when you have a PRD and want to use ralph-tui with beads-rust as the task source. Triggers on: create beads, convert prd to beads, beads for ralph, ralph beads, br beads.

not rated 2.5k +1 2d ago A Socket: passSnyk: passSkillSpector: pass 89 tokens original MIT

emil-design-eng

827

exceptionless/Exceptionless

Skill Claude CodeCodex

This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

not rated 2.5k +1 changed 1mo ago A 35 tokens copy · 92% Apache-2.0

chat-sdk

828

vercel/chat

Skill Claude CodeCodex ✓ vendor

Build multi-platform chat bots with Chat SDK (chat npm package). Use when developers want to scaffold a bot with create-chat-sdk, build a Slack, Teams, Google Chat, Discord, Telegram, GitHub, Linear, or WhatsApp bot, handle mentions, direct messages, subscribed threads, reactions, slash commands, cards, modals, files…

not rated 2.5k +9 changed 29d ago A Socket: passSnyk: passSkillSpector: warn 108 tokens original MIT

shortfilm-prompt

829

jnMetaCode/agency-orchestrator

Skill Claude CodeCodex

A five-part method for writing prompts for AI-generated videos, such as Sora or Seedance. It organizes each prompt into the subject, setting, visual style, camera movement, and timed shots with sound.

not rated 2.4k +21 changed 1mo ago A SkillSpector: pass 66 tokens original Apache-2.0

webclaw

830

0xMassi/webclaw

MCP server Claude CodeCodexCursor +2

Zero-install launcher for the webclaw MCP server: web extraction and anti-bot access for AI agents. Runs npx @webclaw/mcp. Runs locally from the @webclaw/mcp npm package.

not rated 2.4k +16 2d ago A tokens not measured AGPL-3.0

task-manager

831

iamlukethedev/Claw3D

Skill Claude CodeCodex

Capture actionable user requests as persistent tasks, update task status as work progresses, and keep a shared task store in sync. Use when a user asks an agent to do work, check progress, block a task, complete a task, or manage the Kanban board.

not rated 2.4k +10 2d ago A SkillSpector: warn 56 tokens original MIT

prompt-review

832

spacedriveapp/spacebot

Skill Claude CodeCodex

This skill should be used when the user asks to "review the prompt", "audit the system prompt", "check prompt quality", "inspect what the LLM sees", "debug prompt issues", or "find prompt engineering problems". Pulls the live rendered prompt via the API, explains how it's composed, and reviews it for issues.

not rated 2.4k +3 1mo ago A SkillSpector: pass 70 tokens

ade

833

landing-ai/ade-cli

Skill Claude CodeCodex

Parse documents and extract schema-shaped data with the ADE (Agentic Document Extraction) v2 APIs through the ade CLI. A local job-item store makes every run idempotent, resumable, and citable — repeat runs are free, interrupted runs resume, and every answer can cite element ids with visual evidence.

not rated 2.4k +1 7d ago A 65 tokens original Apache-2.0

kunlun-m-general

834

LoRexxar/Kunlun-M

Skill Codex needs its repo

A scripted workflow for Kunlun-M, a static security scanner that examines source code without running it. It supports PHP, JavaScript, Solidity smart contracts, and Chrome extensions, and can create scanner rules and tamper settings.

not rated 2.4k +2 yesterday A SkillSpector: pass 85 tokens original MIT

playwright-electron

835

777genius/agent-teams-ai

MCP server Claude CodeCodexCursor +2

MCP server "playwright-electron", hosted remotely at 127.0.0.1, as configured in 777genius/agent-teams-ai.

not rated 2.4k +38 yesterday A tokens not measured AGPL-3.0

agents-best-practices

836

DenisSergeevitch/agents-best-practices

Skill Claude CodeCodex

Use this skill when designing, generating an MVP blueprint for, auditing, troubleshooting, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral agent architecture for OpenAI, Anthropic, and OpenAI-compatible APIs: agent loops, tool design, record provenance, interactive presentation…

not rated 2.4k +8 changed 19d ago A 164 tokens original MIT

probe-skill

837

The-Vibe-Company/companion

Skill Claude CodeCodex

Verify that the compiled Companion can load a skill and execute its packaged shell resource.

not rated 2.4k +3 25d ago A 20 tokens original MIT

clawfeed

838

kevinho/clawfeed

Skill Claude CodeCodex

AI-powered news digest tool. Automatically generates structured summaries (4H/daily/weekly/monthly) from Twitter and RSS feeds.

not rated 2.4k +3 6mo ago A 0 tokens original MIT

tourmind-booking

839

tourmind-com/Tourmind-Booking-Skills

Skill Codex

MUST USE for any hotel or accommodation intent in any language, including hotel search, hotel recommendations, nearby accommodation, hostels, guesthouses, resorts, where-to-stay questions, room rates, room types, hotel or room photos, amenities, meals, cancellation policies, taxes, real-time availability, rate…

not rated 2.4k +8 changed 18d ago B 162 tokens original MIT

remote-compute-modal

840

UnicomAI/wanwu

Skill Claude CodeCodex

Run GPU jobs on the user's own Modal account via host.compute.create('byoc:modal', ...). Covers the create→submit→waitfornotification flow, the computeprovider kernel for env setup, image/volume resolution, and the two approval cards. Load once you've decided to dispatch to Modal.

not rated 2.4k +3 14d ago A SkillSpector: warn 65 tokens original Apache-2.0

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: