Claude Codex Settings
A curated collection of battle-tested plugins, skills, and configurations for Claude Code, OpenAI Codex, and other AI coding assistants.
What is Claude Codex Settings?
fcakyon/claude-codex-settings is a curated collection of plugins, skills, commands, hooks, and MCP servers for AI-powered coding tools like Claude Code, OpenAI Codex, Gemini CLI, and Cursor. It bundles official and community-developed tools to enhance developer productivity across domains such as office document processing, framework best practices, database design, cloud deployment, and browser automation. The project solves the problem of manually finding and integrating disparate AI coding tools by providing a single, battle-tested setup.
Developers who regularly use AI coding assistants like Claude Code, OpenAI Codex, Gemini CLI, or Cursor and want to enhance their capabilities with pre-configured skills for specific tasks. It is particularly useful for full-stack developers working with React, Next.js, databases, cloud platforms, and academic researchers.
Developers choose this project because it offers a comprehensive, daily-use setup that curates and integrates the most useful official skills and tools from Anthropic, OpenAI, Vercel, MongoDB, Supabase, Stripe, and others into a single cohesive package. Its unique selling point is providing a battle-tested, practical configuration that works across multiple AI coding tools, saving time on manual setup and plugin discovery.
Overview
Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.
Use Cases
Best For
- Adding official office document processing skills (PDF, Word, PowerPoint, Excel) from Anthropic and OpenAI to an AI coding assistant.
- Implementing React, Next.js, and React Native best practices and performance patterns during development with an AI agent.
- Designing database schemas and optimizing queries for MongoDB or Supabase Postgres using AI-assisted skills.
- Integrating payment systems like Stripe or Polar billing and subscription workflows with AI guidance.
- Automating browser and Electron app interactions with reduced context usage compared to traditional MCP servers.
- Conducting academic research, including hypothesis design, paper review, and citation verification, using AI-powered PhD workflow tools.
Not Ideal For
- Developers who only need a single, specialized skill and prefer minimal installations to avoid plugin bloat and maintenance overhead.
- Teams with strict, vetted security policies that restrict third-party plugins or MCP servers from unverified sources.
- Projects using AI coding assistants infrequently or for simple tasks where the comprehensive setup is overkill.
- Environments where manual control over individual plugin versions and updates is critical for stability and compliance.
Pros & Cons
Pros
Bundles battle-tested skills from Anthropic, OpenAI, Vercel, MongoDB, and other official sources, saving developers hours of manual discovery and integration, as highlighted in the plugin list.
Supports Claude Code, OpenAI Codex, Gemini CLI, and Cursor with shared configurations and symlinks, ensuring a consistent workflow across multiple AI coding tools, as shown in the installation section.
Includes tools like agent-browser that reduce context usage by 93% and provides alternative settings for cheaper models like Z.ai GLM, offering significant efficiency gains and cost savings.
Covers office documents, frameworks, databases, cloud deployment, and academic research with pre-configured plugins, making it a one-stop shop for diverse development needs.
Cons
Requires managing multiple plugins, symlinks, and per-plugin setup commands (e.g., /setup for Azure or GCloud tools), which can be time-consuming and prone to errors, as indicated in the configuration section.
Relies on external sources for skills and MCP servers; updates or breaking changes in upstream projects (like Anthropic or OpenAI skills) can cause compatibility issues without direct control from this bundle.
Some plugins depend on MCP servers that require additional resources, such as Docker for paper-search-tools, adding infrastructure complexity and potential performance bottlenecks.
The bundled approach makes it harder to tweak or remove individual components without affecting the entire setup, unlike manually curating plugins where each piece can be independently managed.
Frequently Asked Questions
Related Projects
SuperpowersAn agentic skills framework & software development methodology that works.
Everything Claude CodeThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Learn Claude CodeBash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
Claude Scientific SkillsTurn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 190,000+ scientists worldwide. 165 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.