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. 282,036 indexed, measured the same four ways as everything else here.

google-trends

11689

trendsmcp-ai/google-trends-mcp

MCP server Claude CodeCodexCursor +2

Google Trends: Search, Images, News, Shopping over time, growth metrics. Free key at trendsmcp.ai. Remote server at google-trends.api.trendsmcp.ai.

not rated 17 2mo ago A tokens not measured original MIT

higgsfield-unlimited-mcp

11690

nukIeer/higgsfield-unlimited-mcp

MCP server Claude CodeCodexCursor +2

MCP server "higgsfield-unlimited-mcp" as configured in nukIeer/higgsfield-unlimited-mcp. Runs locally from the higgsfield-unlimited-mcp Python package.

not rated 17 3mo ago A tokens not measured original MIT

openlmnp

11691

manganate006/openlmnp

MCP server Claude CodeCodexCursor +2

Accounting MCP for French LMNP furnished rentals: income, expenses, depreciation, tax return & FEC. Remote server at app.openlmnp.fr.

not rated 17 +1 2d ago A tokens not measured AGPL-3.0

inkeep/open-knowledge-skills

Skill Claude CodeCodex

Use when the user wants to create, author, write, or design a new Agent Skill (a SKILL.md) — for OpenKnowledge or for their editors — including requests like 'help me write a skill', 'make a skill that…', 'turn this workflow into a skill', or improving an existing skill's triggering and discipline. Also use when…

not rated 17 changed 1mo ago A Socket: passSnyk: warnSkillSpector: warn 152 tokens original MIT

skill-audit

11693

sharbelxyz/skill-audit

Skill Claude CodeCodex

Audits every skill installed on this agent and reports which ones are broken. Measures each SKILL.md against the published Agent Skills limits, flags descriptions that never say when to use the skill and therefore never fire, finds files over the 500 line and 5,000 token ceilings, reports how much context all the…

not rated 17 2mo ago A 159 tokens original MIT

api-design

11694

Indium-AI-Labs/indium-agentkit

Skill Claude CodeCodex

Design an API contract (resources, operations, request and response schemas, errors, authorization, pagination, idempotency, and versioning) from requirements before implementation, and produce an api-contract handoff. Use when a feature needs new or changed endpoints, an OpenAPI document, or a compatibility decision.…

not rated 17 changed 28d ago A 78 tokens

instagram-mcp

11695

adelaidasofia/instagram-mcp

MCP server Claude CodeCodexCursor +2

Official Instagram Graph API MCP. Multi-account read, publish, comments, analytics + (review-gated) DMs for Instagram Business/Creator accounts. ToS-safe, no private API. Runs locally from the adelaidasofia-instagram-mcp Python package. Needs 2 environment variables to run.

not rated 17 +2 17d ago A tokens not measured original MIT

format-agent

11696

KaguraNanaga/format-agent-skill

Skill Claude CodeCodex

A document-formatting tool for applying written rules or a Word template to a badly formatted DOCX file. DOCX is the editable document format used by Microsoft Word.

not rated 17 +1 changed 1mo ago A 97 tokens

tushare-api

11697

DayDreammy/tushare-openclaw-skill

Skill Claude CodeCodex

A helper for querying Tushare Pro, a Chinese financial-data service covering stocks, funds, futures, bonds, foreign exchange, and other markets. It uses the service’s API, which is a programmatic way to request data.

not rated 17 9mo ago A 56 tokens original MIT

EveryInc/google-workspace-mcp-server

MCP server Claude CodeCodexCursor +2

MCP server for Google Workspace APIs - Docs, Sheets, Drive, Gmail, and Calendar. Runs locally from the google-workspace-mcp-server npm package.

not rated 17 8mo ago A tokens not measured original MIT

figma-desktop

11699

jujunjun110/product-starter

MCP server Claude CodeCodexCursor +2

One of 2 in .mcp.json

MCP server "figma-desktop", hosted remotely at 127.0.0.1, as configured in jujunjun110/product-starter.

not rated 17 5mo ago A tokens not measured original MIT

geo-infer

11700

ActiveInferenceInstitute/GEO-INFER

Skill Claude CodeCodex

Geospatial Active Inference framework with 45 modules for ecological, civic, and commercial spatial analysis. Use when working with geospatial data, Active Inference, Bayesian modeling, H3 hexagonal indexing, spatial statistics, or any domain-specific geographic analysis (agriculture, health, economics, risk, climate…

not rated 17 changed 2mo ago A 76 tokens

causal-inference-mixtape

11701

Jill0099/causal-inference-mixtape

Skill Claude CodeCodex

This skill should be used when the user asks to "implement a DiD regression", "run a staggered difference-in-differences", "set up an event study", "implement IV / 2SLS", "run a regression discontinuity design", "build synthetic control", "do propensity score matching", "test parallel trends", "run Honest DiD", "wild…

not rated 17 3mo ago A 209 tokens original MIT

write-agents-md

11702

narumiruna/skills

Skill Claude CodeCodex

Create, review, audit, migrate, or update scoped AGENTS.md files with clear rules, verified commands, action limits, instruction order, and checks that prove the work is done. Use also when verified, durable repository guidance emerges during authorized work and should be captured at the narrowest applicable scope.

not rated 17 7d ago A 65 tokens original MIT

mercado-livre

11703

newerton/mcp-mercado-livre

MCP server Claude CodeCodexCursor +2

MCP server "mercado-livre" as configured in newerton/mcp-mercado-livre. Runs ${workspaceFolder}/build/main.js with node.

not rated 17 +1 yesterday A tokens not measured original MIT

qianwenai-observe

11704

QianWen-AI/qianwenai-deploy

Skill Claude CodeCodex

A read-only monitoring workflow for applications deployed on mainland Alibaba Cloud. It reports availability, performance, server and database status, and estimated costs in Chinese yuan.

not rated 17 2mo ago A 207 tokens original Apache-2.0

agent-refine-skill

11705

371684029/oh-my-co-work

Skill Claude CodeCodex

A manually triggered workflow for sending an outside agent's inputs, outputs, and conclusions to a shared cowork document center.

not rated 17 yesterday A 57 tokens

swigerb/squad-pod

Skill Claude CodeCodex

Protocol for sending queries, delegating tasks, and sharing context between independent Squad instances across different repositories.

not rated 17 +1 changed 1mo ago A 25 tokens

fancy-kanban

11707

robertoallende/fancy-kanban

Skill Claude CodeCodex

Generate valid fancy-kanban boards — markdown-embedded kanban boards with typed fields, swimlanes, workflow rules, and card face configuration for Obsidian and compatible tools.

not rated 17 3d ago A 40 tokens original MIT

langgraph-rag-mcp

11708

pedarias/langgraph-rag-mcp

MCP server Claude CodeCodexCursor +2

MCP server "langgraph-rag-mcp" as configured in pedarias/langgraph-rag-mcp. Runs locally from the langgraph-rag-mcp Python package.

not rated 17 1mo ago A tokens not measured

dst

11709

get-dst/dst

MCP server Claude CodeCodexCursor +2

dst, the data serve tool — governed data access layer (backend). Runs locally from the dst-core Python package. Needs 2 environment variables to run.

not rated 17 3d ago A Socket: warn tokens not measured original Apache-2.0

onequery-openclaw

11710

wordbricks/onequery

Skill Claude CodeCodex

Use OpenClaw's exec tool to inspect orgs, sources, and run bounded read-only SQL through the OneQuery CLI directly.

not rated 17 3mo ago A 33 tokens original Apache-2.0

ui-debugger

11711

developerz-ai/open-mmorpg

MCP server Claude CodeCodexCursor +2

One of 2 in .mcp.json

Autonomous UI debugging MCP server. Give a goal; a fast agent drives the browser/desktop, finds bugs + visual issues, and reports back. Runs locally from the @developerz.ai/ui-debugger-mcp npm package. Needs 2 environment variables to run.

not rated 17 2d ago A tokens not measured original MIT

local-ai-model-matcher

11712

Maciejdziuba/local-ai-model-matcher

Skill Claude CodeCodex

Safely auto-detect the current machine's hardware (GPU, VRAM, system RAM, OS) with read-only commands, then recommend the top 3 local AI models to run — most powerful that fits, best for coding, and best small-and-fast — each with download links. Use when someone asks "what AI models can my computer run" or "what's…

not rated 17 4mo ago A 89 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: