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. 274,359 indexed, measured the same four ways as everything else here.

workflows

23666

hybridindie/comfyui_mcp

Skill Claude CodeCodex

Knowledge about ComfyUI workflow API format, node connections, and common patterns. Use when helping users build, modify, or understand workflows.

not rated 3 2d ago A 31 tokens original MIT

ai-therapy-memory

23667

dion-hagan/mcp-ai-therapy

MCP server Claude CodeCodexCursor +2

MCP server "ai-therapy-memory" as configured in dion-hagan/mcp-ai-therapy. Runs /path/to/mcp-ai-therapy/mcp-server/src/main.py with /path/to/your/python. Needs 3 environment variables to run.

not rated 3 1y ago A tokens not measured original MIT

il2cpp-decompiler

23668

rkuhn153/il2cpp-decompiler

Skill Claude CodeCodex

Static analysis for Unity IL2CPP games via il2cpp-decompiler-agent MCP (listdumps, loadproject, searchsymbols, getclassinfo, decompilemethod). Use when runtime is IL2CPP, GameAssembly.dll is involved, or remakes like Who's Your Daddy Remake. Always MCP-first — do not start with Il2CppStudio CLI.

not rated 3 1mo ago A 80 tokens original MIT

write-terva-skill

23669

terva-sh/terva

Skill Claude CodeCodex

Author a new terva skill, a reusable SKILL.md instruction set that terva loads on demand. Install it where terva discovers it, in the project .terva/skills/ or the global $TERVAHOME/skills/. Use for create/add/write-a-skill requests, not extensions.

not rated 3 2d ago A 71 tokens original MIT

fkf-learn

23670

fmind/fkf

Skill Claude CodeCodex

Keep FKF project notes, wiki concepts and task folders current after meaningful work. Use after a decision, a finished task, a corrected assumption, or when the user asks to remember something.

not rated 3 changed 19d ago A 43 tokens original MIT

git-workflow

23671

0xNyk/oneclaw

Skill Claude CodeCodex

When the user asks you to perform git operations, create branches, open PRs, manage releases, or resolve conflicts, follow this guide. These are the procedural patterns you should apply consistently.

not rated 3 1mo ago A 0 tokens original MIT

rhino

23672

kbangaru-cyber/Rhino-mcp

MCP server Claude CodeCodexCursor +2

MCP server "rhino" as configured in kbangaru-cyber/Rhino-mcp. Launched with uv --directory /ABSOLUTE/PATH/TO/Rhino_MCP run rhino-mcp. Needs 3 environment variables to run.

not rated 3 1mo ago A tokens not measured original MIT

muxy-extension

23673

tofunori/atelier-studio

Skill Claude CodeCodex

Best-practice guide for authoring a Muxy extension — how it should look and behave so it reads as a native part of the app. Covers theming (follow the theme, never hardcode colors), the sizing scale, and which surface to use. Mechanics (manifest fields, permissions, the window.muxy API) live in the linked docs.

not rated 3 +1 2d ago A 77 tokens original MIT

brain

23674

eSlider/2dph

Skill Claude CodeCodex

Deduction search over the 2dph brain (Ladybug graph: ops corpus, portfolio, ssh hosts) with bin/brain/search.go instead of reading files or grepping repos. Use whenever a question starts with "where is", "what runs on", "which file describes", "who is", "how is X done", before opening any documentation.

not rated 3 changed 27d ago A 75 tokens original MIT

noita-wiki-rag

23675

a1113622001/noita-wiki-zh

Skill Claude CodeCodex

A question-answering skill for Noita, a game involving spells, wands, perks, enemies, bosses, alchemy, maps, and world lore. It searches a local Chinese Noita wiki and uses the results to answer questions.

not rated 3 1mo ago A 97 tokens

agent-codewalk

23676

andylin-hao/agent-codewalk

Skill Claude CodeCodex

Publish a navigable Agent CodeWalk walkthrough the user steps through in their editor, with each block highlighted in place. Use after modifying code (publishwalkthrough), and for requests to analyze, explain, review, trace, or walk through how existing code works (publishexplanation). Do not use for planning…

not rated 3 +1 1mo ago A 77 tokens original MIT

capability-discovery

23677

444136347/dsh-capability-discovery

Skill Claude CodeCodex needs its repo

Use when a user asks to find, compare, or evaluate an existing DeepSeek Harness plugin, Skill, MCP server, agent extension, profile, or similar ecosystem capability.

not rated 3 1mo ago A 39 tokens original Apache-2.0

rust-native-scanner

23678

aphrody-code/bxc

Skill Claude CodeCodex

Expertise in high-performance native codebase scanning and validation using Rust. Trigger this skill when asked to "scan the codebase natively", "run rust scanner", or "validate bxc core using rust".

not rated 3 1mo ago A 47 tokens original Apache-2.0

wechat-dev-skill

23679

jiawei686/wechat-dev-skill

Skill Claude CodeCodex

A debugging workflow for WeChat DevTools, the development program used to build and test WeChat mini-programs. It checks build output, DevTools messages, output logs, and network errors, then summarizes problems and suggests fixes.

not rated 3 +1 3mo ago A 124 tokens

typescript-review

23680

RichardGeorgeDavis/Codex-Workspace

Skill Claude CodeCodex

Use when reviewing TypeScript changes that need attention to typing, runtime behavior, and verification.

not rated 3 +1 25d ago A 21 tokens copy · 100% MIT

cowork-review

23681

Maless88/Roadboard

Skill Claude CodeCodex

Worker-prompt lifecycle and the Architect/Analyst review gates — prompt frontmatter (status, reviewround, outputstatus), the draft→in-review→approved loop, the append-only review logs, the output gate (review-output → promote), and the tasks/{todo,run,done} transitions. Use when drafting, reviewing, or executing a…

not rated 3 1mo ago A 77 tokens original MIT

docker

23682

soyrageagency/docker-mcp-server

MCP server Claude CodeCodexCursor +2

Chat with your Docker host. A Model Context Protocol (MCP) server that lets any LLM list containers, read logs, manage lifecycle and deploy Compose stacks — safely. Built by SoyRage Agency. Runs locally from the @soyrageagency/docker-mcp npm package. Needs 3 environment variables to run.

not rated 3 changed 1mo ago A tokens not measured original MIT

eighty-three-zx81

23683

alffcpu/eighty-three

MCP server Claude CodeCodexCursor +2

MCP server "eighty-three-zx81" as configured in alffcpu/eighty-three. Launched with ./build/e83_mcp ./build/.

not rated 3 +1 1mo ago A tokens not measured GPL-2.0

plumb

23685

aram-devdocs/plumb

MCP server Claude CodeCodexCursor +2

MCP server "plumb" as configured in aram-devdocs/plumb. Launched with cargo run --quiet -p plumb-cli -- mcp.

not rated 3 2mo ago A tokens not measured original Apache-2.0

ilya-sutskever

23686

beel-collab/presets.dev

Skill Claude CodeCodex

Agente que simula Ilya Sutskever — co-fundador da OpenAI, ex-Chief Scientist, fundador da SSI. Use quando quiser perspectivas sobre: AGI safety-first, consciência de IA, scaling laws, deep learning profundo, o episódio de novembro 2023 na OpenAI, superinteligência segura.

not rated 3 5mo ago A 67 tokens original MIT

securly

23687

BghitCode/Securly

Skill Claude CodeCodex

Apply security guidelines when designing, building, or reviewing AI chatbots, LLM-powered apps, autonomous/tool-using agents, and mobile apps (React Native/Expo, Flutter) — covering agent controls (authorization checks, plan validation, execution limits, audit logging), LLM/prompt security (prompt injection, RAG…

not rated 3 3mo ago A 198 tokens original MIT

blackjose007-stack/adaptive-reasoning-router

Skill Codex

Classify project work into medium, high, or extra-high reasoning effort while keeping high as the stable default. Use when planning or starting a work order, choosing validation scope, handling repeated failures, making architecture or release decisions, controlling reasoning-cost usage, or preventing frequent…

not rated 3 2mo ago A 76 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: