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. 269,901 indexed, measured the same four ways as everything else here.

mcp

11665

longbridge/longbridge-mcp

MCP server Claude CodeCodexCursor +2

MCP server "mcp" as configured in longbridge/longbridge-mcp. Runs in Docker (ghcr.io/longbridge/longbridge-mcp:0.9.0). Needs 3 environment variables to run.

not rated 14 yesterday A tokens not measured original Apache-2.0

nepa-screening

11666

pnnl/nepa-mcp

Skill Claude CodeCodex

Use NEPA-MCP for project-area environmental screening, biological and cultural resources, jurisdiction, soils, protected lands, flood risk, air quality, and regulatory research.

not rated 14 +1 changed 18d ago A 38 tokens original BSD-3-Clause

sprite-atlas-builder

11667

gvastethecreator/codex-studio

Skill Codex

Sprite atlas pipeline. Use for sprites, tilesets, textures, asset sheets, extraction, curation, and QA.

not rated 14 +2 yesterday A SkillSpector: pass 29 tokens original MIT

monarch-money

11668

vargahis/monarch-mcp

MCP server Claude CodeCodexCursor +2

Model Context Protocol (MCP) server for Monarch Money personal finance platform. Runs locally from the monarch-mcp Python package.

not rated 14 +1 9d ago A tokens not measured fork MIT

github

11669

sint-ai/sint-protocol

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. Needs 1 environment variable to run.

not rated 14 yesterday A tokens not measured original Apache-2.0

cad-automation

11670

NingWang13/cad-automation

Skill Claude CodeCodex

Generates DXF/DWG drawings, 3D models (STEP/STL), auto-dimensions, and BOM from text, images, or CAD files. Invoke for CAD drawing, image-to-CAD, 3D modeling, DWG conversion, BOM generation, GD&T annotation, or parametric templates.

not rated 14 +1 4mo ago A 68 tokens

doordash

11671

idanbeck/claude-skills

Skill Claude CodeCodex

Order food on DoorDash for the Beck family using the DoorDash CLI (dd-cli), composing a balanced order that covers everyone's tastes and is age-appropriate for the kids, then placing it only after Idan approves the exact items, total cost, tip, card, and ETA. Use when Idan wants to order dinner/food for the family…

not rated 14 +1 3d ago A 103 tokens

money-manager-mcp

11672

shahlaukik/money-manager-mcp

MCP server Claude CodeCodexCursor +2

MCP server for Realbyte Money Manager API. Runs locally from the money-manager-mcp npm package.

not rated 14 +2 10d ago A tokens not measured original MIT

geo-mcp

11673

MCPmed/GEOmcp

MCP server Claude CodeCodexCursor +2

A Model Context Protocol (MCP) server for accessing GEO (Gene Expression Omnibus) data through NCBI E-Utils API. Runs locally from the geo-mcp Python package.

not rated 14 5mo ago A tokens not measured original BSD-3-Clause

wujutong

11674

jangviktor-web/wujutong

Skill Claude CodeCodex

A Chinese-language skill based on the medical writings and methods of Wu Jutong, a historical physician associated with warm-disease theory. It is intended for academic study and role-based interpretation, not medical advice.

not rated 14 +1 1mo ago A 224 tokens original MIT

automox-mcp

11675

AutomoxCommunity/automox-mcp

MCP server Claude CodeCodexCursor +2

Official MCP server for Automox. Runs locally from the automox-mcp Python package. Needs 3 environment variables to run.

not rated 14 +1 5d ago A tokens not measured original MIT

openvisio

11676

syntaxPriest/openvisio-oss

MCP server Claude CodeCodexCursor +2

MCP server "openvisio" as configured in syntaxPriest/openvisio-oss. Launched with openvisio mcp . --watch.

not rated 14 +1 2mo ago A tokens not measured original MIT

garmin-connect

11677

eddmann/garmin-connect-cli

Skill Claude CodeCodex

Query Garmin Connect fitness and health data including activities, athlete stats, sleep, heart rate, stress, and body battery. Use when the user asks about Garmin data, workouts, training, or health metrics.

not rated 14 +1 4mo ago C 45 tokens original MIT

autonomous-learning-os

11678

gquthier/autonomous-learning-os

Skill Claude CodeCodex

Construit à l'utilisateur son propre dashboard d'apprentissage sur mesure — entretien de setup, deep research multi-agents sur son sujet, génération du curriculum, app Next.js au design BizOS, brief Telegram optionnel. À utiliser quand l'utilisateur veut apprendre un sujet sérieusement, se construire un cursus, ou…

not rated 14 +2 1mo ago A 71 tokens original MIT

b3os-report

11679

b3rys/b3rys-team-os

Skill Claude CodeCodex

A team reporting skill that turns approved markdown and HTML reports into entries in an internal reports portal. HTML becomes the main view when available, while markdown remains the source and download version.

not rated 14 +1 changed 16d ago A SkillSpector: pass 100 tokens original Apache-2.0

agentic-task-system

11680

renezander030/agentic-task-system

MCP server Claude CodeCodexCursor +2

MCP server giving AI agents persistent task memory across TickTick, Notion, GitHub, Linear & Beads. Runs locally from the @reneza/ats-mcp npm package. Needs 1 environment variable to run.

not rated 14 +2 3d ago A tokens not measured original MIT

gtm-workflow

11681

eliasstravik/gtm-skills

Skill Claude CodeCodex

Triggers when a user asks to build, create, update, run, test, schedule, deploy, host, upgrade, inspect, open the inspection UI, or delete a saved GTM workflow, its result table, runs, or diagram in a GTM workspace, with phrasings like "build a workflow that scores our inbound companies", "run Score inbound accounts"…

not rated 14 +1 changed yesterday A 169 tokens original MIT

AlterLab-IEU/AlterLab-FC-Skills

Skill Claude CodeCodex

This skill should be used when the user asks about "audio production", "ElevenLabs", "voice isolator", "audio post-production", "AI narration", "text to speech production", "voiceover studio", "audio native", "transcription", "Scribe", "multi-track audio", "audio assembly", "batch audio processing", "audio export"…

not rated 14 5mo ago A 162 tokens original MIT

context-receipts

11683

caioribeiroclw-pixel/pluribus

Skill Claude CodeCodex

Emit privacy-safe receipts for context selection, deferral, hydration, compaction, pruning, delegation, usage attribution, and boundary handoffs.

not rated 14 +1 2mo ago A 33 tokens original MIT

odoo-dev-superskill

11684

CodeForUsers/odoo-dev-superskill

Skill Claude CodeCodex

Expert guide for creating, reviewing, refactoring, and migrating Odoo modules in versions 16.0, 17.0, 18.0, and 19.0, strictly following OCA Guidelines. Use it when the user mentions: creating an Odoo module, inheriting models or views, writing security (ACL/ir.rule), migrating between Odoo versions (e.g., 16 to 18…

not rated 14 2mo ago A 181 tokens original MIT

local-memory-mcp

11685

studiomeyer-io/local-memory-mcp

MCP server Claude CodeCodexCursor +2

Persistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys. Runs locally from the @studiomeyer/local-memory-mcp npm package. Needs 4 environment variables to run.

not rated 14 +1 2d ago A tokens not measured original MIT

opensci-skill

11686

HughYau/opensci-skill

Skill Claude CodeCodex

Help an agent familiarize itself with any scientific Python library or codebase so it can write a high-quality opensci skill for that library. Use when creating, auditing, or refactoring opensci skills for published packages, source-only repositories, namespace packages, or mixed-layout projects. Content is optimized…

not rated 14 7mo ago A 0 tokens

experiment

11687

hdu-ailab/EasyResearch

Skill Claude CodeCodex

Use when Experiment must build, run, compare, or record reproducible ML/AI paper experiments locally or through the Research Assistant-configured ssh-bash tool and verified SSHFS workspace, including baselines, datasets, controlled trials, multi-seed formal evidence, ablations, and results promotion. Examples: user…

not rated 14 2d ago A SkillSpector: warn 171 tokens original MIT

run

11688

yimwoo/codex-agenteam

Skill Claude CodeCodex

Run a full pipeline for a task. Orchestrates roles through stages (standalone or HOTL-integrated).

not rated 14 +1 2mo ago A 25 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: