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. 269,410 indexed, measured the same four ways as everything else here.

ux-audit

10633

EliaAlberti/ux-audit-skill

Skill Claude CodeCodex

Run a heuristic UX audit of a customer journey from screenshots. Use when the user asks for a UX audit, heuristic evaluation, usability review, design teardown, or expert review of screens, mockups, or a flow, whether your own product or a competitor's. Evaluates against named frameworks (Nielsen, Shneiderman…

not rated 18 3mo ago A 160 tokens original MIT

rust-doctor

10634

arthjean/rust-doctor

Skill Claude CodeCodex

Use when Rust code just changed and must not regress, when the user asks to scan, audit or health-check a Cargo workspace, says "rust-doctor", or wants one of its findings explained, tuned or switched off.

not rated 18 changed 15d ago A SkillSpector: warn 49 tokens original Apache-2.0

nutrient-dws-mcp

10635

PSPDFKit-labs/nutrient-skills

Skill Codex

Process, convert, OCR, sign, redact, parse, or extract data from documents with the Nutrient DWS MCP tools. Use when the user wants cloud document processing through the installed Nutrient plugin.

not rated 18 17d ago A 49 tokens

stitchapi-docs

10636

rejifald/StitchAPI

MCP server Claude CodeCodexCursor +2

StitchAPI documentation search, running locally over MCP stdio. Bundled docs, no network calls per query — the offline/air-gapped counterpart to the hosted stitchapi.dev/api/mcp server. Runs locally from the @stitchapi/docs-mcp npm package.

not rated 18 yesterday A tokens not measured original Apache-2.0

succubus

10637

enowdev/succubus

Skill Claude CodeCodex

Coordinate with other AI agents working on this same project. Use at the start of every session, and before editing any file, to adopt your identity, read the shared plan and task board, and lease the files you are about to change so two agents never edit the same file at once.

not rated 18 1mo ago A 62 tokens copy · 100% MIT

codegraph

10638

clouisle/Clouisle

MCP server Claude CodeCodexCursor +2

MCP server "codegraph" as configured in clouisle/Clouisle. Launched with codegraph serve --mcp.

not rated 18 2d ago A tokens not measured GPL-3.0

nondominium-domain

10639

Sensorica/nondominium

Skill Claude CodeCodex

Nondominium-specific architecture knowledge: NDO three-layer model (Prima Materia/Identity, Specified/ResourceSpec, Custodial/Process), Private Participation Receipt (PPR) system with 16 categories, capability slots as stigmergic attachment surface, ValueFlows alignment patterns for Nondominium's specific…

not rated 18 today A 122 tokens

dbos-golang

10640

dbos-inc/agent-skills

Skill Claude CodeCodex

DBOS Go SDK for building reliable, fault-tolerant applications with durable workflows. Use this skill when writing Go code with DBOS, creating workflows and steps, using queues, using the DBOS Client from external applications, or building Go applications that need to be resilient to failures.

not rated 18 +1 today A SkillSpector: warn 62 tokens original MIT

im-media

10641

tmwgsicp/im-cli-bridge

Skill Claude CodeCodex

Send voice messages, generate/send images, and send files/videos through IM. TRIGGER when user asks: send voice/audio, generate/send images, send files/documents, send videos. DO NOT trigger for regular text conversations.

not rated 18 2mo ago A 48 tokens

atlas

10642

cargofy/ATLAS

MCP server Claude CodeCodexCursor +2

MCP server "atlas" as configured in cargofy/ATLAS. Runs in Docker (/path/to/your/data:/data).

not rated 18 6mo ago A tokens not measured

tap

10643

LeonTing1010/tap

MCP server Claude CodeCodexCursor +2

Browser MCP for logged-in tasks. Uses your Chrome — credentials stay local. Zero-token replay. Runs locally from the @taprun/cli npm package.

not rated 18 1mo ago A tokens not measured original MIT

chisel

10644

ckanthony/Chisel

Skill Claude CodeCodex

Use Chisel MCP filesystem tools efficiently — patch-based edits, minimal token reads, shell exec patterns, and anti-patterns to avoid.

not rated 18 +1 6mo ago C 30 tokens

research-gap-finder

10645

LengFeng00/research-gap-finder

Skill Claude CodeCodex

Analyze scientific literature to identify research gaps and generate testable hypotheses. Use when users upload research papers (PDF), ask to "find research gaps", "generate hypotheses", "analyze literature", or "evaluate field progress". Automatically triggers for scientific paper analysis, literature review…

not rated 18 6mo ago A 77 tokens original MIT

skill-forge

10646

GodModeAI2025/skill-forge

Skill Claude CodeCodex

Autonome Verbesserung nach dem Autoresearch-Paradigma (Karpathy). Zwei Modi: (1) Skill-Modus — optimiert eine SKILL.md durch iterative Mutation und Evaluation. (2) Generic-Modus — optimiert beliebige Dateien gegen jede mechanische Metrik (Testabdeckung, Bundle-Size, Lighthouse-Score, Docker-Image-Größe, etc.). Zwei…

not rated 18 changed 3d ago A 276 tokens original MIT

founder-os

10647

wolulabs/hermes-founder-os

Skill Claude CodeCodex

Top-level orchestration skill for Hermes Agent startup workflows. Use it to route ideas between validation, PRD, architecture, build, UX, growth, and launch skills; summarize context between stages; prevent context pollution; and recommend the next workflow without doing every specialist task directly.

not rated 18 3mo ago A 59 tokens original MIT

content-engine

10648

iamasters-academy/content-engine

Skill Claude CodeCodex

Skill agéntica que convierte cualquier input (texto, idea, audio, vídeo, URL, PDF, artículo) en 5 piezas listas para redes sociales (LinkedIn, X, Instagram, YouTube short, TikTok) con voz de marca propia, genera la imagen con el modelo de imagen que el usuario elija (Fal.ai, OpenAI o cualquier otro vía URL) y publica…

not rated 18 4mo ago A 112 tokens original MIT

linxule/interpretive-orchestration

Skill Claude CodeCodex

Methodological integrity through isolation rules, preset application, and phase-aware guidance. Helps researchers maintain rigor throughout the analytical journey.

not rated 18 +1 2mo ago A 0 tokens

ble-mcp-server

10650

es617/ble-mcp-server

MCP server Claude CodeCodexCursor +2

Bluetooth Low Energy (BLE) Model Context Protocol server for AI agents and developer tooling. Runs locally from the ble-mcp-server Python package. Needs 4 environment variables to run.

not rated 18 5mo ago A tokens not measured original MIT

diataxis

10651

keithpatton/diataxis-agent-skill

Skill Claude CodeCodex

Classify, validate, generate, and audit documentation using the Diátaxis framework. Enforces quadrant purity across tutorials, how-to guides, reference, and explanation. Use when creating documentation, reviewing docs, auditing doc sets, restructuring existing content, or when the user mentions Diátaxis, documentation…

not rated 18 +1 7mo ago A 69 tokens CC-BY-SA-4.0

diagnose

10653

emiliosheinz/agent-skills

Skill Claude CodeCodex needs its repo

Root-causes complex bugs through a structured loop and saves a verified fix proposal — it diagnoses, it never fixes. Builds a fast deterministic feedback loop, reproduces, then probes ranked falsifiable hypotheses with parallel subagents and confirms the cause adversarially before writing the report. Use when a bug…

not rated 18 1mo ago A 102 tokens original MIT

evee

10654

goodfire-ai/evee-mcp

MCP server Claude CodeCodexCursor +2

MCP server "evee" as configured in goodfire-ai/evee-mcp. Runs locally from the python3 Python package.

not rated 18 +1 4mo ago A tokens not measured

playwright-parallel-mcp

10655

sumyapp/playwright-parallel-mcp

MCP server Claude CodeCodexCursor +2

MCP server for parallel browser automation with isolated Playwright sessions. Runs locally from the playwright-parallel-mcp npm package.

not rated 18 8mo ago A tokens not measured original MIT

mcp-terminal

10656

dillip285/mcp-terminal

MCP server Claude CodeCodexCursor +2

MCP Terminal Server - Execute commands within allowed paths. Runs locally from the @dillip285/mcp-terminal npm package.

not rated 18 1y ago A tokens not measured 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: