Claude Codex Settings

Battle-tested Claude Code, Claude Desktop, OpenAI Codex, and Cursor setup with skills, commands, hooks, subagents, and MCP servers, plus Kimi, MiniMax, and GLM API support.

"They make wrong assumptions on your behalf and just run along with them without checking. They don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs. They really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves." -- Andrej Karpathy

This repo's guidelines are structured to fix exactly these pitfalls.

Installation • Plugins • Configuration • References

Installation

Plugins add skills, commands, and automations to your AI coding tool. Install only what you need from the plugin list below.

Prerequisites: See INSTALL.md for setup requirements.

# Add marketplace (one time)
claude plugin marketplace add fcakyon/claude-codex-settings

# Install any plugin by name
claude plugin install fable-advisor@claude-settings

# Add marketplace (one time)
codex plugin marketplace add fcakyon/claude-codex-settings

# Install any plugin by name
codex plugin add simplify@claude-settings

# Install any plugin by name
gemini extensions install --path ./plugins/simplify

# Install any plugin by name
cursor plugin install simplify@claude-settings

Want the shared agent guidance too? .claude/CLAUDE.md is the file written for your projects. Run /claude-tools:sync-claude-md to pull it into ~/.claude/CLAUDE.md, or paste it into a project as CLAUDE.md, then point the other tools at the same file:

ln -sfn CLAUDE.md AGENTS.md # Codex CLI, Cursor, Copilot
ln -sfn CLAUDE.md GEMINI.md # Gemini CLI

Plugins

Run /simplify to review your staged or committed diff across four angles (reuse, simplification, efficiency, altitude) with parallel agents, then apply the cleanups. It reviews changed-code quality, not correctness bugs. It brings Claude Code's built-in /simplify to Codex, Cursor, and Gemini, which don't ship it natively, so all three get the same review and apply flow.

Skills:

• simplify - review the changed diff across four angles and apply the fixes

Hooks:

• guard.py - Require a completed /simplify run before each Claude Code or Codex commit, unless you explicitly ask to skip it for one commit

Before a Write or Edit saves, humanize scans the new text and blocks whatever reads like a machine wrote it, each hit paired with a plain-word swap. It reads markdown files whole and, in code, only the comments and docstrings, never the code:

• 3 marks: the em-dash, section sign, and stray semicolon (the en-dash stays)
• 53 stock words like leverage, seamlessly, vibrant, game-changing, each mapped to a plain swap
• 16 openers and cliches like in conclusion, a testament to, aims to bridge
• 10 pile-up words like crucial or significant, flagged at 3+ uses in one write

Runs on Claude Code and Gemini. Unlike a markdown rule the model can ignore, the hook checks every Write or Edit and blocks each match until it is replaced. The word list draws on Wikipedia's "Signs of AI writing".

Skills (ZIP for claude.ai, ChatGPT, Claude Code, Cursor, Codex, VS Code):

Skill	Description	ZIP
humanize	Avoid common AI writing patterns with examples

Hooks:

• humanize.py - blocks matched marks, buzzwords, and cliches before a Write or Edit lands

Ask a Fable 5 reviewer to challenge a plan or conclusion before you commit, a drop-in for the built-in advisor when the Opus-main plus Fable-advisor pairing fails with a bare "unavailable" (#73365). Claude Code uses a native Fable agent with the recent conversation attached. Codex, Cursor, and Gemini call the same model through an authenticated Claude Code CLI with claude -p --model fable.

Agents:

• fable-advisor - Native Claude Code reviewer with recent conversation context

Skills:

• fable-advisor - Routes Claude Code to its native agent and other tools to claude -p

Ask GPT to challenge a plan before you build it, the cross-model check the built-in advisor cannot give you. Claude Code attaches the recent conversation, so "ask the codex advisor" is enough. Codex, Cursor, and Gemini reach the same reviewer. Needs the Codex CLI signed in.

Agents:

• codex-advisor - Sends the recent conversation to GPT and returns the verdict verbatim

Skills:

• codex-advisor - Routes Claude Code to its native agent and other tools to codex exec

Cuts filler and keeps output token use down with the answer or next step first, one-action-per-step lists, concrete time estimates, a single under-two-minute next action, and short teaching notes while coding. Claude Code applies the output style automatically. Codex, Cursor, and Gemini CLI expose the same instructions as an adhd-output-style skill because they do not support plugin output styles.

Output styles:

• ADHD Explanatory - Low-token ADHD formatting plus educational Insight blocks while coding

Skills (ZIP for claude.ai, Claude Code, Cursor, Codex, VS Code):

| Skill | Description | ZIP

…