Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,761 indexed, measured the same four ways as everything else here.
DiegoFleitas/letterboxd-movie-justwatch
MCP server Claude CodeCodexCursor +2
One of 3 in .mcp.json
MCP server "sonarqube", hosted remotely at api.sonarcloud.io, as configured in DiegoFleitas/letterboxd-movie-justwatch.
Jakevin/fastcontext-agent-tools
Skill Codex
Use Microsoft FastContext as the default read-only code exploration subagent before answering, editing, reviewing, or debugging code you are not already certain about. Trigger when a task requires reading more than one file, tracing logic across modules, locating files/symbols/call paths/tests, mapping dependencies…
MCP server Claude CodeCodexCursor +2
MCP server "openapi.com", hosted remotely at 127.0.0.1, as configured in openapi/mcp-server.
Skill Claude CodeCodex
Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's dos verify and dos commit-audit — never the agent's own narration.
MCP server Claude CodeCodexCursor +2
MCP server "agnt" as configured in standardbeagle/agnt. Launched with agnt mcp.
Skill Claude CodeCodex
Appraise the complete post-ingest Gaia tree: run 13 deterministic audit dimensions, recompute evidence, Trust Magnitude and rank eligibility, use Jev/Luna for bounded semantic review, adversarially verify findings, and report structural proposals. Gaia computes authority; Jev is read-only advice; humans ratify all…
aws-samples/sample-ai-assistant-on-agentcore
Skill Claude CodeCodex ✓ vendor
Creates polished PowerPoint presentations with dark-first design, custom palettes, charts, and tables. Use when creating, designing, or generating PPTX slide decks or presentations.
Skill Claude CodeCodex
Scaffold new AI agent skills with proper symlinking across all IDE tools (Cursor, Claude Code, Codex, etc.). Use when creating a new skill, adding a local skill, or when the user wants to write a custom skill -- either workspace-wide or for a specific project.
Skill Claude CodeCodex
A workflow guide for analysing protein molecular-dynamics simulations, which model how atoms move over time. It describes procedures for correcting periodic-boundary artefacts, measuring motion and flexibility, and studying structural changes and interactions.
Skill Claude CodeCodex
Build, test, and deploy a Sapiom agent — a controlled, multi-step, deployable automation defined in TypeScript. Use when the user wants to automate a multi-step, scheduled, recurring, or deployable task ("build an agent that checks competitor prices every morning", "automate our weekly report", "make a bot that…
AAzzAAzzAAzzAA/remove-chinese-ai-tics
Skill Codex
A Chinese-language editing guide for removing repeated, formulaic wording and artificial-sounding patterns while keeping the original facts, tone, and character voices.
MCP server Claude CodeCodexCursor +2
Spawn multiple specialized Claude Code agents as MCP servers, each independently configured. Runs locally from the claude-octopus npm package. Needs 7 environment variables to run.
leejpsd/typescript-react-nextjs-patterns
Skill Claude CodeCodex
Production-grade TypeScript reference for React & Next.js frontend development. Covers type narrowing, component Props, generic hooks, discriminated unions, as const, satisfies, Zod validation, TanStack Query, server/client boundaries, forms, state management, performance, accessibility, debugging, and code review.…
Skill Claude CodeCodex
Generate publication-grade ML explainer videos and carousels the way 3Blue1Brown actually builds them — in real manimGL (NOT Manim Community Edition), as a tiny domain DSL of self-arranging Mobjects choreographed into transform-driven beats where every motion carries meaning. Overlap is prevented at construction time…
Skill Claude CodeCodex
Generates a project closure report aggregating data from charter, plan-fact report, risk register, and lessons learned. Last artifact of the Closing phase. Summarizes project outcomes, deviations, realized risks, and lessons.
Skill Claude CodeCodex
Skill "code-refactor" from ZeroPointRepo/CRHQ-PRDs, covering code refactor skill, when to use this skill, the two modes, core principles and the seven phases (shared by both modes).
MCP server Claude CodeCodexCursor +2
MCP server for Ghostfolio management. Runs locally from the ghostfolio-mcp Python package. Needs 13 environment variables to run.
Skill Claude CodeCodex
Run visual regression tests, review screenshot diffs, and manage baselines on a Lastest instance via the @lastest/mcp-server MCP tools.
MCP server Claude CodeCodexCursor +2
MCP server "tbp" as configured in salviz/termux-browser-pilot. Launched with tbp-mcp.
Skill Claude CodeCodex
Automatically delegate complex, logic-intensive tasks to OpenAI Codex CLI via codex exec --full-auto. Claude Code uses this skill to invoke Codex for complex backend logic, intricate algorithms, or persistent bugs. Enables seamless AI-to-AI collaboration where Claude Code analyzes and Codex executes.
Skill Claude CodeCodex
OpenDash is a shared markdown file layer for humans and agents. This skill gives an agent a safe, repeatable way to read and write files through the OpenDash API.
Carlos-Dominguez-faber/crear-agente-imperio
Skill Claude CodeCodex
Crea automatizaciones inteligentes (agentes de IA) en la nube de Cloudflare, paso a paso, en español sencillo, sin necesidad de saber programar. Úsalo cuando alguien escriba "/crear-agente", "/crear-agente-imperio", "quiero crear un agente", "quiero hacer un agente", "quiero automatizar [X]", "quiero un sistema que me…
Skill Claude CodeCodex
Run static quality evaluation for agent skills. Scores each skill on format (2.1.1), content completeness (2.1.2), and writing quality (2.1.3), total 24 pts. Output text report, JSON, CSV, or a radar chart for a single skill. Use when the user wants to score skills, audit skill quality, export scores to CSV, or…
MCP server Claude CodeCodexCursor +2
DaVinci Resolve integration through the Model Context Protocol. Runs locally from the davinci-resolve-mcp Python package.
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: