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. 269,004 indexed, measured the same four ways as everything else here.

Code Execution

9194

winsenlabs/platos

Skill Claude CodeCodex

Run Python, Node.js, AND arbitrary shell commands in a secure E2B cloud sandbox that PERSISTS across calls within a conversation. Clone repos, install packages, run CLI tools (git, psql, ffmpeg, duckdb), and build up state turn over turn.

not rated 24 3d ago A 60 tokens original Apache-2.0

devcake-ops

9195

flieber-inc/devcake

Skill Claude CodeCodex

Set up, inspect, configure, troubleshoot, and upgrade a self-hosted DevCake deployment for its operator. Use for questions about missions, repository context, memory, scheduled tasks, skills, or deployment health; developing DevCake's own code follows AGENTS.md instead.

not rated 24 changed yesterday A 59 tokens GPL-3.0

cookbook-doc-review

9196

TencentCloudAgentRuntime/ags-cookbook

Skill Claude CodeCodex

Review AGS Cookbook documentation for language, wording, logic, and Markdown layout from an external AGS user's perspective. Use before handing off changes to public READMEs, tutorials, reference guides, or example documentation anywhere in this repository. Do not use for source-code review or explicit…

not rated 24 yesterday A 67 tokens

sidecar

9197

tommo/sublime-claude

Skill Claude CodeCodex

Unqualified "sidecar" in a Sublime session means SUBLIME SIDECAR: MCP sublime spawnsession (another sheet), not grok/kimi/codex CLI. Use when the user says sidecar, sublime sidecar, worker sheet, spawn a session, or fork a worker in the editor.

not rated 24 +2 18d ago A 67 tokens

magnusfroste/flowwink

Skill Claude CodeCodex

Admin Copilot site-builder loop (copilot-action) is exposed as MCP skill buildsitestep so external claws drive the same loop the admin UI uses.

not rated 24 +1 yesterday A 41 tokens original MIT

agents-inc/skills

Skill Claude CodeCodex

CSS animation patterns - transitions, keyframes, scroll-driven timelines, @property, compositor-friendly properties, prefers-reduced-motion.

not rated 24 changed 11d ago A SkillSpector: pass 30 tokens original MIT

holochain

9200

Soushi888/holochain-agent-skills

Skill Claude CodeCodex

Holochain hApp development assistant covering coordinator/integrity zome architecture, Rust HDK/HDI patterns, entry/link types, CRUD, validation, cross-zome calls, Sweettest testing, TypeScript client integration, DNA migration and init properties, and Nix dev environments. USE WHEN writing zome code, designing DHT…

not rated 24 +1 8d ago A 158 tokens

supernote-mystyle

9201

mphinance/alpha-skills

Skill Claude CodeCodex

A round-trip system for Supernote e-ink tablets. A small JSON spec is the shared contract between human and agent: the agent renders it into a device-correct 'MyStyle' template PNG, the human writes/ticks on the tablet, exports the note, and the agent reconciles the marks back into a master list. Use when the user…

not rated 24 +2 5d ago A 166 tokens original MIT

hypruse

9202

IlyasKhallouki/hypruse

Skill Claude CodeCodex

Sees and drives the live Hyprland (Wayland) desktop through the hypruse CLI: lists windows and workspaces, focuses, moves, closes and launches apps over IPC, takes screenshots and zooms, reads GTK/Qt controls by name from the accessibility tree and clicks them, types text, presses shortcuts, runs the owner's keybinds…

not rated 24 5d ago A 194 tokens original MIT

acolomba/pi-claude-marketplace

Skill Claude CodeCodex

Unit testing rules for TypeScript -- pairing, coverage, case structure, naming, assertions, test doubles, test data, hermeticity, and production design for tests. Apply when writing or changing tests//.ts or the extension modules they pair with.

not rated 24 +1 today A 54 tokens original MIT

hmem-write

9204

Bumblebiber/hmem

Skill Claude CodeCodex

Hmem write protocol — picks prefix (L/E/D/P/N/R/I/H…), tree location, and tags, and detects duplicates before persisting. Use before any writememory or appendmemory call (skipping it creates duplicates and misplaced entries), or when the user says 'remember this', 'save this', 'log this', or invokes /hmem-write.

not rated 23 2mo ago A 77 tokens original MIT

tighten

9205

scandnavik/writing-harness

Skill Claude CodeCodex

A Markdown editing tool that finds common unnecessary words, repeated headings, and padded explanations, then rewrites the marked sections with a language model. Markdown is a plain-text format commonly used for documentation.

not rated 23 2mo ago A 86 tokens original MIT

my-agent-browser

9206

briqt/my-agent-browser

Skill Claude CodeCodex

Browser automation guidance and patterns. Trigger this skill BEFORE starting any browser interaction (navigating pages, logging in, scraping, filling forms, testing UI) to learn the correct workflow and avoid common pitfalls. Also trigger when browser MCP tools misbehave: element not found, click does nothing, page…

not rated 23 changed 5d ago A 117 tokens

shi-yigong-perspective

9207

Hongying-LIN/shi-yigong-skill

Skill Claude CodeCodex

A thinking and communication framework based on the public talks, interviews, books, and university-building work of Shi Yigong, a Chinese scientist and founder of Westlake University. It provides mental models, decision guidelines, and a distinct way of explaining ideas.

not rated 23 5mo ago A 159 tokens

memory

9208

aictx/memory

Skill Claude CodeCodex

Use this skill when working in a project that uses Memory by Aictx as product-layer project memory. It guides the agent to query memory on demand mid-task, save product-meaningful changes after meaningful work, and sync memory at session end.

not rated 23 +1 1mo ago A SkillSpector: warn 52 tokens original MIT

about-oneclaw

9209

GNHua/oneclaw

Skill Claude CodeCodex

Comprehensive knowledge base about OneClaw -- architecture, features, tools, and configuration.

not rated 23 6mo ago A 22 tokens

react-code-reviewer

9210

vladilenm/irreplaceable_hub

Skill Claude CodeCodex

Senior code reviewer agent for TypeScript and React codebases. Performs deep 7-level code review: security vulnerabilities (OWASP-aligned), correctness bugs, performance issues, accessibility violations, style/best-practices violations, architecture problems, and provides auto-fix diffs for every finding. Uses three…

not rated 23 5mo ago A 228 tokens

aws-athena-mcp

9211

ColeMurray/aws-athena-mcp

MCP server Claude CodeCodexCursor +2

A simple, clean MCP server for AWS Athena integration. Runs locally from the aws-athena-mcp Python package. Needs 4 environment variables to run.

not rated 23 5d ago A tokens not measured original MIT

blog-writer

9212

sinmb79/blog-writer_mcp

MCP server Claude CodeCodexCursor +2

MCP server "blog-writer" as configured in sinmb79/blog-writermcp. Runs locally from the blog-writer Python package.

not rated 23 5mo ago A tokens not measured

maestro-mobile-testing

9213

tovimx/maestro-mobile-testing-skill

Skill Claude CodeCodex

Maestro mobile E2E testing patterns for React Native/Expo apps: YAML test flows, testID selectors, adaptive auth state, optimistic update verification, GraalJS scripting, cross-platform stability, CI/CD integration, Maestro Cloud, and MCP server integration.

not rated 23 7mo ago C 56 tokens

Veridise/audithub-skills

Skill Codex

Coordinate full or multi-stage AuditHub OrCa fuzzing campaigns for Solidity projects. Use when a user asks to run an autonomous OrCa campaign, plan and execute setup/tuning/spec/long-run loops, resume an OrCa campaign, or coordinate target selection, deployment setup, smoke runs, callmetrics.json analysis, tuning, [V]…

not rated 23 1mo ago A 89 tokens

ai-tips-tricks

9215

0xMulight/human-social-copy

Skill Claude CodeCodex

An automated workflow for searching the web for practical AI tips, techniques, and workflows, then writing tutorial-style Chinese posts and sending them to Telegram.

not rated 23 1mo ago C 53 tokens original MIT

agent-scaffolder

9216

xuanhieu2611/build-your-own-agents-skill

Skill Claude CodeCodex

Generate a runnable Python project from an Agent Build Spec. Turns architecture documents into working code with a controller loop, tool stubs, session state, permission checks, and observability.

not rated 23 5mo ago A 41 tokens original 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: