fcakyon/claude-codex-settings

Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.

What it solves

This project provides a curated set of plugins, skills, and configuration guidelines designed to improve the behavior of AI coding assistants. It specifically targets common AI pitfalls such as over-engineering, bloated abstractions, failure to seek clarification, and the use of repetitive AI-generated buzzwords in documentation.

How it works

The project offers a marketplace of plugins that can be installed into various AI tools including Claude Code, Codex CLI, Cursor, and Gemini CLI. These plugins implement specific behaviors via:

  • Skills: Specialized instructions and capabilities added to the AI's toolkit.
  • Hooks: Scripts that intercept actions (like writing or committing code) to enforce rules, such as blocking AI buzzwords or requiring a code simplification review before a commit.
  • Agents: Specialized reviewer agents (e.g., Fable 5 or GPT via Codex) to provide second opinions on architectural decisions.
  • Output Styles: Formatting rules to reduce token usage and prioritize concise, action-oriented responses.

Who it’s for

Developers using AI-powered IDEs and CLI tools (specifically Claude Code, Cursor, Codex CLI, and Gemini CLI) who want more professional, concise, and human-like output and higher-quality code reviews.

Highlights

  • Simplify Plugin: Brings a multi-angle code review flow (reuse, simplification, efficiency, altitude) to tools that lack it natively.
  • Humanize Plugin: Uses hooks to block a curated list of 53+ AI buzzwords and cliches in Markdown and docstrings.
  • Intelligent Compact: Prevents the loss of high-signal facts (like root causes and file paths) during session auto-summarization.
  • Cross-Model Advisors: Allows users to get second opinions from different models (e.g., using GPT to review Claude's plan) within the same workflow.
  • Office Skills: Integration of official Anthropic and OpenAI skills for processing PDF, Word, PowerPoint, and Excel files.

Related

  • Project
    alirezarezvani/claude-skills

    A comprehensive library of 388 modular agent skills and plugins for AI coding tools, providing specialized domain expertise across engineering, business, and research.

  • Project
    shinpr/claude-code-workflows

    Claude Code Development Workflows is a set of Claude Code plugins that turn the Claude AI assistant into a structured development pipeline. The plugins provide “recipes” (e.g. `/recipe‑implement`, `/recipe‑design`, `/recipe‑review`) that enforce outcome agreement, design documentation, work‑plan generation, task‑level implementation with automated verification, and an independent security review. Three plugin families cover backend, React frontend, and full‑stack projects, and they can be installed via Claude’s marketplace. The system is useful when you need repeatable safety gates and a formal hand‑off between design and code generation; for quick prototypes you can skip it.

  • Dispatch
    Claude Code Best Practices Guide

    Anthropic provides a comprehensive set of best practices for optimizing Claude Code, an agentic coding environment, focusing on context window management and autonomous verification.

  • Project
    pedrohcgs/claude-code-my-workflow

    A fork‑ready framework that uses Anthropic Claude Code to automate academic tasks (slides, papers, data analysis, etc.) via specialised agents, a ten‑gate quality suite, and extensible skills; includes setup scripts, pre‑commit hooks, and detailed documentation.

  • Project
    jamditis/claude-skills-journalism

    A collection of modular agent skills for Claude Code and Codex that provide journalists and researchers with specialized workflows for source verification, records requests, and professional reporting.