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. 496,737 indexed, measured the same four ways as everything else here.

cline-sdk

265

cline/cline

Skill Claude CodeCodex

Comprehensive Cline SDK skill for building AI agents. Covers the Agent runtime, ClineCore sessions, custom tools, plugins, events, LLM providers, scheduling, multi-agent teams, and production deployment. Use for any task involving @cline/sdk or its sub-packages.

not rated 67k +139 yesterday A 59 tokens original Apache-2.0

publish-cli

266

cline/cline

Skill Claude CodeCodex

Use when preparing, tagging, and publishing an apps/cli npm release. Guides changelog drafting, apps/cli/package.json version bumps, cli-vX.Y.Z tags, local npm publishing, and the publish-cli GitHub workflow.

not rated 67k +139 yesterday A 50 tokens original Apache-2.0

publish-desktop

267

cline/cline

Skill Claude CodeCodex

Use when preparing, tagging, and publishing a Cline desktop app (apps/examples/desktop-app) release — stable (desktop-vX.Y.Z from main) or beta (desktop-vX.Y.Z-beta.N from desktop-experimental, shipped as the side-by-side "Cline Beta" app). Guides changelog drafting, version bumps in package.json + tauri.conf.json…

not rated 67k +139 yesterday A 107 tokens original Apache-2.0

cline AGENTS.md

268

cline/cline

Instructions file CodexOpenCode

AGENTS.md instructions for cline/cline, covering cloud agent instructions, cline cli, build / lint / test, gui display and vs code extension (apps/vscode, package claude-dev).

not rated 67k +139 yesterday A 1,407 tokens original Apache-2.0

OpenSpec AGENTS.md

269

Fission-AI/OpenSpec

Instructions file CodexOpenCode

AGENTS.md instructions for Fission-AI/OpenSpec, a project described as: Spec-driven development (SDD) for AI coding assistants.

not rated 67k +235 2d ago not scanned tokens not measured original MIT

Fission-AI/OpenSpec

Skill Claude CodeCodex

Archive multiple completed changes at once. Use when archiving several parallel changes.

not rated 67k +235 2d ago A 23 tokens original MIT

openspec-explore

271

Fission-AI/OpenSpec

Skill Claude CodeCodex

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

not rated 67k +235 2d ago A 39 tokens original MIT

openspec-onboard

272

Fission-AI/OpenSpec

Skill Claude CodeCodex

Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.

not rated 67k +235 2d ago A 26 tokens original MIT

seo-review

273

leonardomso/33-js-concepts

Skill Claude CodeCodex

Perform a focused SEO audit on JavaScript concept pages to maximize search visibility, featured snippet optimization, and ranking potential.

not rated 67k +2 1mo ago A 25 tokens original MIT

test-writer

274

leonardomso/33-js-concepts

Skill Claude CodeCodex

Generate comprehensive Vitest tests for code examples in JavaScript concept documentation pages, following project conventions and referencing source lines.

not rated 67k +2 1mo ago A 26 tokens original MIT

write-concept

275

leonardomso/33-js-concepts

Skill Claude CodeCodex

Write or review JavaScript concept documentation pages for the 33 JavaScript Concepts project, following strict structure and quality guidelines.

not rated 67k +2 1mo ago A 27 tokens original MIT

agent-browser

276

shanraisshan/claude-code-best-practice

Skill Claude CodeCodex

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…

not rated 66k +74 today A 108 tokens original MIT

shanraisshan/claude-code-best-practice

Skill Claude CodeCodex

The conceptual framework behind the presentation — what "Vibe Coding to Agentic Engineering" means, why the journey is structured the way it is, and how every slide fits the narrative arc.

not rated 66k +74 today A 44 tokens original MIT

playwright

279

shanraisshan/claude-code-best-practice

MCP server Claude CodeCodexCursor +2

One of 3 in .mcp.json

Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.

not rated 66k +74 today A tokens not measured copy · 86% MIT

context7

280

shanraisshan/claude-code-best-practice

MCP server Claude CodeCodexCursor +2

One of 3 in .mcp.json

Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.

not rated 66k +74 today A tokens not measured original MIT

deepwiki

281

shanraisshan/claude-code-best-practice

MCP server Claude CodeCodexCursor +2

One of 3 in .mcp.json

Lets the agent read DeepWiki's AI-generated documentation of any public GitHub repository and ask questions about a codebase. Runs locally from the deepwiki-mcp npm package.

not rated 66k +74 today A tokens not measured original MIT

warpdotdev/warp

Skill Claude CodeCodex

GUI desktop app only. Launch two parallel Oz cloud agents with computer use to download and install the latest stable Linux Warp build, capture screenshots while walking through first-time onboarding in both logged-out and logged-in states, then selectively fan out follow-up cloud agents for distinct onboarding…

not rated 65k +56 yesterday A 98 tokens AGPL-3.0

github

283

warpdotdev/warp

MCP server Claude CodeCodexCursor +2

Lets the agent work with GitHub: search code, read and create issues and pull requests, and manage repositories through the GitHub API. Runs locally from the @modelcontextprotocol/server-github npm package.

not rated 65k +56 yesterday A tokens not measured AGPL-3.0

warp AGENTS.md

284

warpdotdev/warp

Instructions file CodexOpenCode

AGENTS.md instructions for warpdotdev/warp, covering agents.md, development commands, build and run, running with local warp-server and connect to server on default port 8080.

not rated 65k +56 yesterday A 4,233 tokens AGPL-3.0

claude-api

285

warpdotdev/warp

Skill Claude CodeCodex

Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…

not rated 65k +56 yesterday A 193 tokens AGPL-3.0

create-skill

286

warpdotdev/warp

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.

not rated 65k +56 yesterday A 64 tokens AGPL-3.0

gsd-build/get-shit-done

Instructions file CodexOpenCode

Instructions for gsd-build/get-shit-done, covering repository guidelines, active discussions, project structure & module organization, build, test, and development commands and coding style & naming conventions.

not rated 65k +14 3mo ago A 739 tokens original MIT archived

mem0 AGENTS.md

288

mem0ai/mem0

Instructions file CodexOpenCode

AGENTS.md instructions for mem0ai/mem0, covering agents.md, do not, where to look, repository map and setup.

not rated 65k +175 2d ago A 3,110 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: