Claude Codex Settings Agent Skill

<div align="center"> <img src="https://github.com/user-attachments/assets/a978cb0a-785d-4a7d-aff2-7e962edd3120" width="10000" alt="Claude Codex Settings Logo">

Battle-tested Claude Code, Claude Desktop, OpenAI Codex, Cursor, and Antigravity CLI 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

Claude Settings has setup guides and skill downloads. Agent Plugins is the compact plugin directory.

</div>

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.

<details open> <summary><strong>Claude Code</strong></summary>

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

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

In Claude Code desktop, select + beside the prompt, then Plugins and Add plugin.

</details> <details> <summary><strong>Codex CLI</strong></summary>

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

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

In the Codex desktop app, open Plugins, find the plugin, and select Install.

</details> <details> <summary><strong>Antigravity CLI</strong></summary>

git clone https://github.com/fcakyon/claude-codex-settings.git
cd claude-codex-settings
uv run .github/scripts/antigravity.py install simplify

Requires Antigravity CLI and uv. The installer packages skills and MCP servers for Antigravity, keeps long instructions in full, and installs them with agy plugin install. Claude-specific hooks, agents, commands, and output styles stay with their original tools. Add more plugin names to install several at once.

</details> <details> <summary><strong>Cursor</strong></summary>

# Add marketplace (one time)
cursor-agent plugin marketplace add https://github.com/fcakyon/claude-codex-settings

# Start the interactive CLI
cursor-agent

Enter /plugin, open the marketplace, and install the plugin at user or project scope. In the Cursor app, open Customize and select Install.

</details>

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, Cursor, Antigravity, Copilot

Plugins

<details> <summary><strong>simplify</strong> - Review changed code for reuse, redundancy, and over-engineering, then apply fixes</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install simplify@claude-settings	codex plugin add simplify@claude-settings	uv run .github/scripts/antigravity.py install simplify

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 Antigravity, 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

</details> <details> <summary><strong>humanize</strong> - Write naturally and block AI buzzwords in files, commits, and messages</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install humanize@claude-settings	codex plugin add humanize@claude-settings	uv run .github/scripts/antigravity.py install humanize

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 checks comments and docstrings in code files while skipping source code and recognized code-shaped references:

• 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

The hook runs on Claude Code and Codex; Antigravity receives the writing skill. 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

</details> <details> <summary><strong>fable-advisor</strong> - Get a second opinion from Claude Fable 5.1 before big decisions</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install fable-advisor@claude-settings	codex plugin add fable-advisor@claude-settings	uv run .github/scripts/antigravity.py install fable-advisor

Ask a Fable 5.1 reviewer to challenge a plan or conclusion before you commit. Claude Code uses the native plugin agent, while Codex, Cursor, and Antigravity call the same model through an authenticated Claude Code CLI with claude -p --model claude-fable-5-1.

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

</details> <details> <summary><strong>codex-advisor</strong> - Get a second opinion from GPT-6 Astra via Codex CLI before big decisions</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install codex-advisor@claude-settings	codex plugin add codex-advisor@claude-settings	uv run .github/scripts/antigravity.py install codex-advisor

Ask GPT-6 Astra 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 Antigravity reach the same reviewer. Needs the Codex CLI signed in.

Agents:

• codex-advisor - Sends the recent conversation to GPT-6 Astra and returns the verdict verbatim

Skills:

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

</details> <details> <summary><strong>adhd-output-style</strong> - Use fewer output tokens with short steps, quick insights, and clear next actions</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install adhd-output-style@claude-settings	codex plugin add adhd-output-style@claude-settings	uv run .github/scripts/antigravity.py install adhd-output-style

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 Antigravity 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
adhd-output-style	Apply the same reply format in Codex, Cursor, and Antigravity CLI

</details> <details> <summary><strong>intelligent-compact</strong> - Keep file paths, root causes, and open questions through auto-summaries</summary>

Claude Code	Codex CLI
claude plugin install intelligent-compact@claude-settings	codex plugin add intelligent-compact@claude-settings

When Claude Code auto-summarizes a long session, the default summary routinely drops the highest-signal facts. This plugin tells the summarizer to keep them:

• File paths under investigation so the next turn doesn't re-discover where you were
• Confirmed root causes so you don't re-debug what's already solved
• Open questions, metrics, and IDs that prose summaries usually round away
• Findings from expensive subagent runs that took minutes to gather

Runs on every /compact (manual) and every auto compaction. Claude Code only; Codex, Cursor, and Antigravity CLI don't yet expose a comparable summary hook.

Hooks:

• precompact_priorities.sh - Priority-preservation instructions for the compaction summarizer

</details> <details> <summary><strong>claude-telemetry-hooks</strong> - Track Claude Code usage, rejections, and session stats in one dashboard</summary>

Claude Code	Codex CLI
claude plugin install claude-telemetry-hooks@claude-settings	n/a

Adds the two missing pieces Claude Code's telemetry needs to power a usage dashboard:

• Sticky session ID per project: resumed conversations stay one session, not dozens
• Categorized rejection reasons (profanity, wrong target, scope drift, retry, and more): chart why Claude pushes back

Per-device data is already in Claude Code's built-in OpenTelemetry stream. Pairs naturally with openobserve-skills for the dashboard side.

Hooks:

• session_start_chat_id.py - SessionStart hook that emits a sticky per-project chat_id
• user_prompt_reject_feedback.py - UserPromptSubmit hook that categorizes tool-rejection reasons

</details> <details> <summary><strong>anthropic-office-skills</strong> - Official Anthropic PDF, Word, PowerPoint, Excel skills</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install anthropic-office-skills@claude-settings	codex plugin add anthropic-office-skills@claude-settings	uv run .github/scripts/antigravity.py install anthropic-office-skills

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/anthropic-office-skills --skill '*'

Official office document skills from anthropics/skills.

Skill	Description	Install
pdf	PDF processing (read, merge, split, create, OCR, forms)
pptx	PowerPoint presentation building and editing
xlsx	Excel spreadsheet processing with formulas
docx	Word document creation and editing

</details> <details> <summary><strong>openai-office-skills</strong> - Official OpenAI PDF, Word, PowerPoint, Excel skills</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install openai-office-skills@claude-settings	codex plugin add openai-office-skills@claude-settings	uv run .github/scripts/antigravity.py install openai-office-skills

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/openai-office-skills --skill '*'

Office document skills for creating and editing PDFs, Word documents, slide decks, and spreadsheets.

Skill	Description	Install
pdf	PDF generation and extraction with visual review
slides	Slide deck creation with PptxGenJS
spreadsheet	Spreadsheet processing with formulas and formatting
doc	Word document creation and editing

</details> <details> <summary><strong>python-skills</strong> - Python best practices from PEP 8, Zen of Python, Google style, and Effective Python</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install python-skills@claude-settings	codex plugin add python-skills@claude-settings	uv run .github/scripts/antigravity.py install python-skills

Python coding guidelines grounded in authoritative sources: PEP 8, PEP 20 (Zen of Python), Google Python Style Guide, and Brett Slatkin's "Effective Python" (3rd ed.). Covers code integration, idiomatic patterns, YAGNI anti-abstraction rules, Google-style docstrings, and 18 before/after code examples.

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

Skill	Description	ZIP
python-guidelines	Core rules, self-tests, and reference index

Reference files:

• zen-of-python.md - Full PEP 20 with annotations
• google-style-guide.md - Curated sections with source URLs
• idiomatic-patterns.md - 18 patterns with before/after code
• effective-python-tips.md - Key tips from 3rd edition

</details> <details> <summary><strong>typescript-skills</strong> - TypeScript type safety and coding practices</summary>

Use practical examples to model types and validate data at application boundaries.

Claude Code	Codex CLI	Antigravity CLI
claude plugin install typescript-skills@claude-settings	codex plugin add typescript-skills@claude-settings	uv run .github/scripts/antigravity.py install typescript-skills

Skill	What it does	Download
typescript-best-practices	Type safety, boundary validation and practical examples	ZIP

</details> <details> <summary><strong>heroui-skills</strong> - HeroUI for web and mobile apps</summary>

Build and theme React and React Native interfaces, or migrate an existing HeroUI app to v3.

Claude Code	Codex CLI	Antigravity CLI
claude plugin install heroui-skills@claude-settings	codex plugin add heroui-skills@claude-settings	uv run .github/scripts/antigravity.py install heroui-skills

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/heroui-skills --skill '*'

Skill	What it does	Download
heroui-react	Build and theme React interfaces with HeroUI v3	ZIP
heroui-migration	Migrate React apps from HeroUI v2 to v3	ZIP
heroui-native	Build React Native interfaces with HeroUI Native	ZIP

</details> <details> <summary><strong>react-skills</strong> - Official React, Next.js, and React Native best practices</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install react-skills@claude-settings	codex plugin add react-skills@claude-settings	uv run .github/scripts/antigravity.py install react-skills

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/react-skills --skill '*'

React and frontend best practices from vercel-labs/agent-skills.

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

Skill	Description	ZIP
composition-patterns	React composition patterns: compound components, render props, context
react-best-practices	64 React/Next.js performance rules from Vercel Engineering
react-native-skills	35+ React Native/Expo rules for performance and animations
react-view-transitions	View Transition API for page/route animations
web-design-guidelines	UI review against 16 web interface guideline categories

</details> <details> <summary><strong>agent-browser</strong> - Drive browsers and Electron apps, run UI QA, and turn websites into API clients</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install agent-browser@claude-settings	codex plugin add agent-browser@claude-settings	uv run .github/scripts/antigravity.py install agent-browser

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/agent-browser --skill '*'

Browser automation via CLI instead of MCP. 93% less context usage than Playwright MCP by using snapshot + element refs instead of full DOM tree dumps. From vercel-labs/agent-browser.

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

Skill	Description	ZIP
agent-browser	Browser automation: navigation, forms, clicking, screenshots, auth, sessions
electron	Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion)
derive-client	Build a direct API client from a site's recorded browser traffic
dogfood	Explore a web app to find bugs and UX issues
webmcp-gen	Expose a page's workflows as WebMCP tools
ui-regression	Verify actions, recovery, locales, accessibility, and real integrations

The locally maintained ui-regression skill checks known workflows on local, staging, and deployed UIs, including browser extensions. Use dogfood for exploratory bug discovery.

CLI Tool: agent-browser - install via npm i -g agent-browser && agent-browser install

</details> <details> <summary><strong>frontend-design-skills</strong> - Frontend design, testing, and writing skills (Anthropic + OpenAI + Vercel)</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install frontend-design-skills@claude-settings	codex plugin add frontend-design-skills@claude-settings	uv run .github/scripts/antigravity.py install frontend-design-skills

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/frontend-design-skills --skill '*'

Frontend design, testing, and writing skills from anthropics/claude-plugins-official, openai/plugins, and vercel-labs/writing-guidelines.

Skill	Description	Install
openai-frontend-design	Composition-first design: restrained layout, image-led hierarchy, tasteful motion
frontend-testing-debugging	Test rendered apps, debug interactions, and check responsive layouts
anthropic-frontend-design	Bold aesthetic direction, distinctive typography, anti-generic AI aesthetics
writing-guidelines	Review interface copy and text for clear, consistent writing

Pairs naturally with reusable-app-components.

</details> <details> <summary><strong>mongodb-skills</strong> - Official MongoDB skills for schema design, queries, indexing, and Atlas Search</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install mongodb-skills@claude-settings	codex plugin add mongodb-skills@claude-settings	uv run .github/scripts/antigravity.py install mongodb-skills

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/mongodb-skills --skill '*'

Official MongoDB agent skills for schema design, queries, indexing, Atlas Search, and connections. From mongodb/agent-skills.

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

Skill	Description	ZIP
mongodb-atlas-stream-processing	Atlas stream processing patterns
mongodb-connection	Connection management
mongodb-mcp-setup	MCP server setup
mongodb-natural-language-querying	Natural language to queries
mongodb-query-optimizer	Query performance tuning
mongodb-schema-design	Schema design patterns
mongodb-search-and-ai	Atlas Search and AI integration

</details> <details> <summary><strong>supabase-skills</strong> - Supabase skills for Postgres, Auth, Edge Functions, the JS SDK, and the CLI</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install supabase-skills@claude-settings	codex plugin add supabase-skills@claude-settings	uv run .github/scripts/antigravity.py install supabase-skills

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/supabase-skills --skill '*'

Supabase skills covering Postgres query/schema best practices from supabase/agent-skills, JavaScript SDK usage from supabase/supabase-js, and CLI workflows from supabase/cli.

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

Skill	Description	ZIP
supabase-postgres-best-practices	Postgres performance and schema design across 8 categories
supabase-js	JavaScript SDK for auth, database, storage, realtime, edge functions
supabase-cli	CLI for local dev, migrations, edge functions, project management
supabase	Supabase security, RLS, CLI, and schema change workflow

</details> <details> <summary><strong>stripe-skills</strong> - Official Stripe skills for payments, billing, Connect, Apps, and API upgrades</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install stripe-skills@claude-settings	codex plugin add stripe-skills@claude-settings	uv run .github/scripts/antigravity.py install stripe-skills

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/stripe-skills --skill '*'

Official Stripe agent skills for payment integration: API selection, Connect platform setup, billing/subscriptions, Treasury, and SDK upgrades. From stripe/ai.

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

Skill	Description	ZIP
stripe-best-practices	Payments, billing, Connect, Treasury integration best practices
stripe-projects	Stripe Projects CLI setup and stack provisioning
upgrade-stripe	Stripe API version and SDK upgrade guide
connect-recommend	Choose a Stripe Connect setup for marketplaces and platforms
connect-required-verification-information	Connected account verification and KYC requirements
metronome	Usage-based billing with Metronome
stripe-apps	Build and review Stripe Apps
stripe-docs	Look up Stripe docs and API reference

</details> <details> <summary><strong>polar-skills</strong> - Official Polar agent skills for billing, subscriptions, and local dev environment</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install polar-skills@claude-settings	codex plugin add polar-skills@claude-settings	uv run .github/scripts/antigravity.py install polar-skills

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/polar-skills --skill '*'

Official Polar agent skills for billing system, Stripe integration, subscription lifecycle, and local dev with Docker. From polarsource/polar.

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

Skill	Description	ZIP
polar-billing	Polar billing system, Stripe integration, subscriptions, benefit provisioning
polar-local-environment	Polar local development environment with Docker

</details> <details> <summary><strong>livekit-skills</strong> - Build, test, simulate, and deploy LiveKit voice AI agents</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install livekit-skills@claude-settings	codex plugin add livekit-skills@claude-settings	uv run .github/scripts/antigravity.py install livekit-skills

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/livekit-skills --skill '*'

Voice AI agent development with the LiveKit Agents SDK, from design and live testing to simulations and production. Works with LiveKit Cloud or a self-hosted server, and looks up current docs with the lk CLI when no docs server is connected. Based on livekit/agent-skills, patched so the Cloud-only parts also cover self-hosting.

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

Skill	Description	ZIP
building-livekit-agents	Structure voice agents: latency, context size, handoffs and tasks
debugging-livekit-agents	Drive a local conversation with the agent and read its tool calls
operating-livekit-agents	Deploy, roll back, and keep a live agent fast and stable
reading-livekit-docs	Look up current LiveKit APIs, CLI flags, and changelogs
running-livekit-simulations	Run whole-conversation simulations before shipping
testing-livekit-agents	Write turn-level agent tests with pytest or Vitest
writing-livekit-scenarios	Write and maintain the scenarios simulations run

</details> <details> <summary><strong>cloudflare-skills</strong> - Pick Cloudflare products and build with Workers, Durable Objects, and Wrangler</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install cloudflare-skills@claude-settings	codex plugin add cloudflare-skills@claude-settings	uv run .github/scripts/antigravity.py install cloudflare-skills

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/cloudflare-skills --skill '*'

Choose the Cloudflare services your project needs, then load the relevant specialist skill. From cloudflare/skills.

• Includes Workers, Wrangler, Durable Objects, Agents SDK, Sandbox, and Turnstile guidance.
• Covers Next.js deployment, email, Zero Trust, migrations, and web performance.
• Keeps detailed references inside each skill so they are read only when needed.

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

Skill	Description	ZIP
cloudflare-deploy	Cloudflare platform: compute, storage, AI, networking, security
agents-sdk	Build applications with the Agents SDK
basin	Stream, catalog, and query analytics data in R2
cloudflare-email-service	Configure email sending and routing
cloudflare-one	Configure Zero Trust and SASE
cloudflare-one-migrations	Plan migrations to Cloudflare One
durable-objects	Build persistent state and coordination
k2	Build durable logs with K2 Streams
nextjs-on-cloudflare	Deploy Next.js with vinext
sandbox-migrate-to-next	Migrate Sandbox stable to preview
sandbox-next	Build with the Sandbox preview SDK
sandbox-stable	Maintain stable Sandbox applications
turnstile-spin	Set up and verify Turnstile
web-perf	Audit loading and interaction performance
workers-best-practices	Write and review production Workers
cf-cli	Build and deploy with the Cloudflare CLI
gateway-workers	Transform Gateway HTTP traffic with Workers
workers-profiling	Profile Worker CPU usage and find hotspots
wrangler	Configure and operate the Wrangler CLI

</details> <details> <summary><strong>web-performance-skills</strong> - Web performance audits with Core Web Vitals and Chrome DevTools</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install web-performance-skills@claude-settings	codex plugin add web-performance-skills@claude-settings	uv run .github/scripts/antigravity.py install web-performance-skills

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/web-performance-skills --skill '*'

Audit web page performance using Chrome DevTools MCP. Measures Core Web Vitals (FCP, LCP, TBT, CLS, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. From cloudflare/skills.

Bundles the chrome-devtools MCP server (no API key needed).

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

Skill	Description	ZIP
web-performance-optimization	Core Web Vitals, Lighthouse, render-blocking, accessibility audits

</details> <details> <summary><strong>openobserve-skills</strong> - Search logs, metrics, and traces and build OpenObserve dashboards via curl</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install openobserve-skills@claude-settings	codex plugin add openobserve-skills@claude-settings	uv run .github/scripts/antigravity.py install openobserve-skills

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/openobserve-skills --skill '*'

Programmatic access to OpenObserve (Cloud or self-hosted) via the documented REST API. Covers:

• Auth and search: HTTP Basic auth, the search/SQL endpoint with microsecond timestamps
• Streams and dashboards: stream listing/schema, dashboard CRUD, the v8 panel JSON schema
• Known pitfalls: the customQuery re-aggregation bug that doubles table rows when fields.y carries an aggregationFunction

Built for AI agents: uses curl only, no SDK or CLI dependency. Pairs naturally with claude-telemetry-hooks for Claude Code usage dashboards. Reference docs are mirrored from openobserve/openobserve-docs.

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

Skill	Description	ZIP
openobserve-api	Search SQL, streams, dashboards, panel schema, ingestion endpoints, common pitfalls

</details> <details> <summary><strong>hetzner-skills</strong> - Hetzner Cloud CLI skill for servers, networks, firewalls, DNS, and storage</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install hetzner-skills@claude-settings	codex plugin add hetzner-skills@claude-settings	uv run .github/scripts/antigravity.py install hetzner-skills

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/hetzner-skills --skill '*'

Hetzner Cloud infrastructure management via the hcloud CLI. Decision trees for compute, networking, storage, DNS, and common deploy workflows. Reference docs extracted from hetznercloud/cli.

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

Skill	Description	ZIP
hetzner-deploy	Servers, networks, firewalls, load balancers, DNS, volumes, storage

</details> <details> <summary><strong>dokploy-skills</strong> - Dokploy deployment skill for Dokploy Cloud and self-hosted dashboards</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install dokploy-skills@claude-settings	codex plugin add dokploy-skills@claude-settings	uv run .github/scripts/antigravity.py install dokploy-skills

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/dokploy-skills --skill '*'

Dokploy Cloud and self-hosted dashboard workflows from Dokploy/website, plus a compact CLI command index generated from Dokploy/cli.

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

Skill	Description	ZIP
dokploy-deploy	Dokploy Cloud, self-hosted dashboard, Docker Compose, databases, domains, remote servers, CLI index

</details> <details> <summary><strong>anthropic-essentials</strong> - Feature dev, CLAUDE.md management, skill creation</summary>

Best-of bundle from anthropics/claude-plugins-official. Cherry-picks skills, agents, and commands from multiple upstream plugins.

Skills:

• claude-md-improver - Audit and improve CLAUDE.md files across a codebase
• skill-creator - Create, improve, and benchmark Agent Skills with eval testing

Agents:

• code-architect - Architecture design from codebase patterns
• code-explorer - Deep codebase exploration and analysis
• code-reviewer - Code quality and review

Commands:

• /feature-dev - Guided feature development workflow
• /revise-claude-md - Capture session learnings into CLAUDE.md

Hooks:

• Stop (prompt) - Suggest CLAUDE.md updates after significant code changes
• SessionEnd (prompt) - Remind to capture learnings when session ends

</details> <details> <summary><strong>anthropic-plugin-dev</strong> - Plugin development toolkit</summary>

Actively maintained plugin development toolkit from anthropics/claude-plugins-official. 7 skills, 3 agents, and guided plugin creation.

Skills: hook-development, mcp-integration, plugin-structure, plugin-settings, command-development, agent-development, skill-development

Agents: agent-creator, plugin-validator, skill-reviewer

Commands: /create-plugin - Guided plugin workflow

</details> <details> <summary><strong>labrat</strong> - Reproduce papers, compare and debug ML runs, check paper claims</summary>

Lab Rat, the ML research toolkit from fcakyon/labrat (formerly phd-skills). Paper reproduction, experiment design, run comparison, debugging, paper checks and rebuttals, with guardrail hooks that review conclusions in Claude Code.

Skills:

• compare - Compare training runs at the same epoch and write experiment reports
• dataset-curation - Analyze dataset bias, stratified samples and fairness
• debug - Diagnose failing runs from evidence before claiming a cause
• experiment-design - Plan ablations, baselines and experiment matrices
• launch - Pre-flight checklist before long training jobs
• literature-research - Find related work, literature gaps and open source code
• paper-check - Check numbers, formulas and citations against code, and prepare code release
• paper-write - Write and revise paper sections and fix the LaTeX build
• rebuttal - Anticipate reviewer questions and draft rebuttals
• reproduce - Reproduce an arxiv paper from code clone to replication runs
• setup - Auto-detection tour and optional notifications, allowlist and LaTeX setup

</details> <details> <summary><strong>github-dev</strong> - Git workflow agents + skills</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install github-dev@claude-settings	codex plugin add github-dev@claude-settings	uv run .github/scripts/antigravity.py install github-dev

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/github-dev --skill '*'

Git and GitHub automation. Run the setup skill after install.

Agents:

• commit-creator - Intelligent commit workflow
• pr-creator - Pull request creation
• pr-reviewer - Code review agent
• pr-comment-resolver - PR comment resolution

Skills:

• commit-staged - Commit staged changes and write the message
• create-issue - Create or revise a concise problem report
• create-pr - Create a pull request from the full branch diff
• review-pr - Review a pull request for bugs and regressions
• resolve-pr-comments - Address unresolved PR review comments
• update-pr-summary - Update the PR title and description
• clean-gone-branches - Clean local branches deleted from remote
• setup - Configure GitHub CLI

Hooks:

• git_commit_confirm.py - Confirmation before git commit
• gh_pr_create_confirm.py - Confirmation before gh pr create
• block_ai_attribution.py - Block AI attribution lines in commits and PRs
• block_commit_type.py - Block commit types outside the allowed set

</details> <details> <summary><strong>ultralytics-dev</strong> - YOLO training and Ultralytics Platform skills, with format and force-push hooks</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install ultralytics-dev@claude-settings	codex plugin add ultralytics-dev@claude-settings	uv run .github/scripts/antigravity.py install ultralytics-dev

Ultralytics Platform API flows and YOLO26 training know-how, plus auto-formatting hooks for Python, JavaScript, Markdown, and Bash and a guard that blocks force-push and rebase.

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

Skill	Description	ZIP
ultralytics-platform	Platform API: uploads, training, hosted inference, Moondream and AI annotation
yolo-training	YOLO26 training diagnosis: read the curves, pick the knob

Hooks:

• post_write.py - Formats each Python, Markdown, shell, and web file you change with the Ultralytics Actions format rules
• block_force_push.py - Block force-push and rebase

Install uv, Node.js, and shfmt first (setup).

</details> <details> <summary><strong>ultralytics-branding</strong> - Ultralytics brand colors, fonts, logo, naming, and tone for branded content.</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install ultralytics-branding@claude-settings	codex plugin add ultralytics-branding@claude-settings	uv run .github/scripts/antigravity.py install ultralytics-branding

Official colors, Archivo typography, logo and naming rules, tone of voice, and per-format defaults from ultralytics.com/brand for PDF/PPTX/Canva decks, DOCX documents, marketing email HTML, social posts, and web designs.

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

Skill	Description	ZIP
ultralytics-branding	Brand colors, fonts, logo, naming, tone, format defaults

</details> <details> <summary><strong>azure-tools</strong> - Query and manage Azure resources through the Azure MCP server and Azure CLI login</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install azure-tools@claude-settings	codex plugin add azure-tools@claude-settings	uv run .github/scripts/antigravity.py install azure-tools

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/azure-tools --skill '*'

Uses your Azure CLI login. Run /azure-tools:setup after install.

Skills:

• azure-usage - Best practices for Azure
• setup - Troubleshooting guide

Commands:

• /azure-tools:setup - Configure Azure MCP

MCP: .mcp.json | microsoft/mcp/Azure.Mcp.Server

</details> <details> <summary><strong>claude-tools</strong> - Sync CLAUDE.md + allowlist + context refresh</summary>

Claude Code	Codex CLI
claude plugin install claude-tools@claude-settings	codex plugin add claude-tools@claude-settings

Commands for syncing CLAUDE.md and permissions allowlist from repository, plus context refresh for long conversations.

Commands:

• /load-claude-md - Refresh context with CLAUDE.md instructions
• /sync-claude-md - Sync CLAUDE.md from GitHub
• /sync-allowlist - Sync permissions allowlist

</details> <details> <summary><strong>gcloud-tools</strong> - Query Google Cloud logs, metrics, and traces through the Cloud Observability MCP</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install gcloud-tools@claude-settings	codex plugin add gcloud-tools@claude-settings	uv run .github/scripts/antigravity.py install gcloud-tools

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/gcloud-tools --skill '*'

Logs, metrics, and traces. Run /gcloud-tools:setup after install.

Skills:

• gcloud-usage - Best practices for GCloud Logs/Metrics/Traces
• setup - Troubleshooting guide

Commands:

• /gcloud-tools:setup - Configure GCloud MCP

MCP: .mcp.json | google-cloud/observability-mcp

</details> <details> <summary><strong>paper-search-tools</strong> - Paper Search CLI & Skills</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install paper-search-tools@claude-settings	codex plugin add paper-search-tools@claude-settings	uv run .github/scripts/antigravity.py install paper-search-tools

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/paper-search-tools --skill '*'

Search papers, look up DOIs, download PDFs, and follow citations with Paper Search CLI. Run /paper-search-tools:setup after install. Requires uv and Python 3.10+; no Docker or MCP server.

Skills:

• paper-search-usage - Best practices for paper search
• setup - Troubleshooting guide

Commands:

• /paper-search-tools:setup - Install and verify Paper Search CLI

CLI: fcakyon/paper-search-cli

</details> <details> <summary><strong>tavily-tools</strong> - Search the web and extract pages with Tavily, and route built-in web tools to it</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install tavily-tools@claude-settings	codex plugin add tavily-tools@claude-settings	uv run .github/scripts/antigravity.py install tavily-tools

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/tavily-tools --skill '*'

Web search and content extraction. Run /tavily-tools:setup after install.

Skills:

• tavily-usage - Best practices for Tavily Search
• setup - Troubleshooting guide

Commands:

• /tavily-tools:setup - Configure Tavily MCP

Hooks:

• webfetch_to_tavily_extract.py - Redirect WebFetch to Tavily extract
• websearch_to_tavily_search.py - Redirect WebSearch to Tavily search
• tavily_extract_to_advanced.py - Upgrade Tavily extract depth

MCP: .mcp.json | tavily-ai/tavily-mcp

</details> <details> <summary><strong>overleaf-skills</strong> - Pull Overleaf review comments into your .tex repo and apply the edits</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install overleaf-skills@claude-settings	codex plugin add overleaf-skills@claude-settings	uv run .github/scripts/antigravity.py install overleaf-skills

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/overleaf-skills --skill '*'

Pull reviewer comments from an Overleaf project, locate each in your local git-tracked *.tex files, and apply edits you review. Auth comes from a logged-in Chrome via agent-browser, with a pasted session cookie as fallback. The same script pulls GitHub commits into Overleaf and recompiles the PDF. Pairs naturally with github-dev for the commit step.

Skills:

• setup - Capture and refresh the Overleaf session cookie
• review-overleaf - Fetch unresolved review threads and apply edits to local .tex files

</details> <details> <summary><strong>aeo</strong> - Turn buyer questions and AI citations into content that wins customers</summary>

Claude Code	Codex CLI	Cursor	Antigravity CLI
claude plugin install aeo@claude-settings	codex plugin add aeo@claude-settings	Run cursor-agent, enter /plugin, and install by name	uv run .github/scripts/antigravity.py install aeo

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/aeo --skill '*'

Help people who have not heard of your product discover it through answer engine optimization (AEO).

• Map acquisition questions by audience, buying stage, use case, market, and language, without naming your product.
• Check content access and inspect the sources AI answers cite before choosing what to fix or publish.
• Prioritize channels using customer evidence and keep prompt coverage within budget.
• Measure unprompted discovery and customer outcomes, keeping branded accuracy checks separate.

Use it for a strategy, audit, prompt portfolio, content brief, or performance review.

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

Skill	Description	ZIP
aeo	Evidence-led AI search strategy for any product

</details> <details> <summary><strong>google-telemetry</strong> - Read app usage and search traffic around releases</summary>

Claude Code	Codex CLI	Cursor	Antigravity CLI
claude plugin install google-telemetry@claude-settings	codex plugin add google-telemetry@claude-settings	Run cursor-agent, enter /plugin, and install by name	uv run .github/scripts/antigravity.py install google-telemetry

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/google-telemetry --skill '*'

Read Google Analytics and Search Console from your terminal to check how people use an app and find it in search.

• Set up read access with a read-only service account or a guided Google sign-in.
• Compare version adoption, product events and search traffic around releases.
• Distinguish reporting delays, missing tracking and failed access from zero use.

Uses third-party CLIs backed by Google's APIs. Requires Google API access.

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

Skill	Description	ZIP
setup	Set up and verify Google reporting access
google-telemetry	Read product and search telemetry through API wrappers

</details> <details> <summary><strong>seo-skills</strong> - Audit search visibility, structured data, and site architecture</summary>

Claude Code	Codex CLI	Antigravity CLI
claude plugin install seo-skills@claude-settings	codex plugin add seo-skills@claude-settings	uv run .github/scripts/antigravity.py install seo-skills

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/seo-skills --skill '*'

Locally maintained SEO workflows, originally adapted from Vercel’s SEO skills. Run a bounded, framework-independent audit of crawl access, sitemaps, canonical and locale links, metadata, and share images. Findings include evidence and separate confirmed failures from review items and unchecked work. Visual quality, search intent, real indexing, and Core Web Vitals still need their own checks. Upstream sync cannot overwrite these local skills or scripts.

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

Skill	Description	ZIP
seo-audit	Prioritized technical, on-page, content, and credibility audit
programmatic-seo	Plan template-driven page sets without thin content
schema	Add and validate JSON-LD structured data
site-architecture	Plan hierarchy, navigation, URLs, and internal links

</details>

---

<details> <summary><strong>openship-skills</strong> - Deploy self-hosted OpenShip apps with the CLI and openship.json</summary>

Claude Code	Codex CLI	Cursor	Antigravity CLI
claude plugin install openship-skills@claude-settings	codex plugin add openship-skills@claude-settings	Run cursor-agent, enter /plugin, and install by name	uv run .github/scripts/antigravity.py install openship-skills

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/openship-skills --skill '*'

Deploy applications to your own OpenShip instance with guidance drawn from its official documentation and source code.

• Use native CLI commands first, with API calls for missing functionality.
• Design small openship.json files for builds, services, domains, and storage.
• Verify the active deployment and public URL after deployment.
• Keep server upgrades, backups, and restoration separate from application deploys.

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

Skill	Description	ZIP
openship-deploy	Deploy and operate self-hosted OpenShip through the CLI
openship-config	Design and validate openship.json

References are tied to one upstream release. The two skills work together and can also be downloaded separately.

</details> <details> <summary><strong>reusable-app-components</strong> - Reuse tested app journeys with code, design and integration checks</summary>

Claude Code	Codex CLI	Cursor	Antigravity CLI
claude plugin install reusable-app-components@claude-settings	codex plugin add reusable-app-components@claude-settings	Run cursor-agent, enter /plugin, and install by name	uv run .github/scripts/antigravity.py install reusable-app-components

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/reusable-app-components --skill '*'

Reuse an app journey together with its code, integration rules and proof of behavior. The auth recipe covers email and Google login:

• Keep returning-account sign-in and a same-tab fallback when popups or the Google script are unavailable.
• Resume the original action while preserving the app's sessions, roles and signup policy.
• Use a configurable Muvisafe-inspired panel or keep the host design, with auth behavior independent of the shell.
• Adapt the React component, test it locally, then verify the real provider in each app.
• Track production references separately from extractions and pending migrations.

Skill	Purpose	ZIP
app-auth	Email signup, verification and recovery, Google login, shared panel and QA journeys	Available after the next release
email-design	Brand themes, transactional copy, HTML and text layouts, and inbox checks	Available after the next release
opendesk-support	OpenDesk chat identity, product AI, knowledge sync and support API operations	Available after the next release

Use email-design to theme verification, reset, billing and notification emails with the app’s existing mail service. The layout keeps brand colors and wording separate and includes text alternatives and preview checks.

The proposed PocketBase/Go auth, mail and OpenShip standard is included as migration guidance. It is not a shipped shared backend library.

Pairs naturally with frontend-design-skills and qa.

</details> <details> <summary><strong>qa</strong> - Test real app journeys with saved sessions</summary>

• Discover website, extension, Android, backend and database components.
• Generate project-owned QA skills and executable journeys under .agents.
• Reuse authorized login sessions, test real playback and keep QA analytics out of user reports.
• Drive real touch gestures on an emulated phone, speak scripted phrases into voice apps and confirm the replies play.
• Drive native macOS permission journeys with exact windows and file drags, keeping real grants separate from CI and reporting blocked coverage honestly.

Install this plugin from the marketplace after publication. For a local checkout, run npm ci --prefix plugins/qa and npm link from plugins/qa. Then use project-qa setup --root /path/to/project.

Skill	Purpose
setup	Discover components and build project-specific real journeys
run-qa	Run tracked journeys and inspect evidence

Pairs naturally with reusable-app-components.

</details> <details> <summary><strong>test-audit</strong> - Keep only tests that catch real bugs, and prune ones that just restate the code</summary>

Claude Code	Codex CLI	Cursor	Antigravity CLI
claude plugin install test-audit@claude-settings	codex plugin add test-audit@claude-settings	Run cursor-agent, enter /plugin, and install by name	uv run .github/scripts/antigravity.py install test-audit

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/test-audit --skill '*'

The test review playbook from openclaw/openclaw, adapted to work in any repository.

• Before a new test lands, it must name the bug it catches and why existing tests miss it.
• Finds tests that copy source, mock the behavior they assert, or repeat a stronger test.
• Deletes test-only exports and dead code once their last test is gone.
• A campaign mode prunes a whole subsystem's tests with a per-test ledger and a final review for lost coverage.

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

Skill	Description	ZIP
test-audit	Gate new tests and prune low-value or duplicate ones

</details>

Configuration

<details> <summary><strong>Claude Code</strong></summary>

Configuration in .claude/settings.json:

• Model: Opus 5.5 with high effort, always-on thinking, and ultracode (multi-agent workflows)
• Environment: bash working directory, telemetry disabled, MCP output limits
• Permissions: bash commands, git operations, MCP tools
• Auto mode: auto permission mode with a custom autoMode classifier block in .claude/settings.json - see the auto mode config reference for what each rule section does, and run claude auto-mode defaults to print the current built-in block and allow rules
• Advisor: the built-in advisor tool uses Fable 5.1. For a review outside the Claude family, use codex-advisor
• Plugins: codex-advisor is enabled in both Claude Code and Codex. Claude Code also enables intelligent-compact. Standalone fable-advisor stays enabled only in Codex

</details> <details> <summary><strong>Z.ai GLM-5.3 (1M context)</strong></summary>

Configuration in .claude/settings-zai.json using Z.ai GLM models via Anthropic-compatible API:

• Main model: GLM-5.3 with 1M context (dialogue, planning, coding, complex reasoning)
• Fast model: GLM-5.3-Flash (file search, syntax checking)
• Cost savings: much cheaper than frontier Claude models
• API key: Get from z.ai/model-api

For Codex CLI, see the recipe at .codex/config-zai.toml. Z.ai serves a Responses endpoint at /api/v1, so no local proxy is needed.

</details> <details> <summary><strong>Kimi K3 (Fable5-level accuracy)</strong></summary>

Run Claude Code with Kimi K3 via Anthropic-compatible API - source:

• Model: kimi-k3[1m] - native vision, thinking mode, 1M context
• Fast models: kimi-k2.7-code (sonnet), kimi-k2.6 (haiku) - cheaper 256K tiers
• API key: Get from platform.moonshot.ai

export ANTHROPIC_BASE_URL=https://api.moonshot.ai/anthropic
export ANTHROPIC_AUTH_TOKEN="your-moonshot-api-key"
export ANTHROPIC_MODEL="kimi-k3[1m]"
export ANTHROPIC_DEFAULT_OPUS_MODEL="kimi-k3[1m]"
export ANTHROPIC_DEFAULT_SONNET_MODEL="kimi-k2.7-code"
export ANTHROPIC_DEFAULT_HAIKU_MODEL="kimi-k2.6"
export ANTHROPIC_DEFAULT_FABLE_MODEL="kimi-k3[1m]"
export CLAUDE_CODE_SUBAGENT_MODEL="kimi-k3[1m]"
export ENABLE_TOOL_SEARCH=false

Or use the settings file: .claude/settings-kimi.json

For Codex CLI, use Kimi K3 through the local Responses proxy in .codex/config-kimi.toml. The recipe uses Kimi Code model ID k3. Use k3-256k in both the proxy command and config when 256K context is enough.

</details> <details> <summary><strong>MiniMax M3 (1M context)</strong></summary>

Run Claude Code with MiniMax M3 via Anthropic-compatible API - source:

• Model: MiniMax-M3[1m] - 1M context window (512K guaranteed minimum, [1m] unlocks the full window)
• Fast model: MiniMax-M2.7-highspeed - high-throughput variant
• API key: Get from minimax.io

export ANTHROPIC_BASE_URL=https://api.minimax.io/anthropic
export ANTHROPIC_AUTH_TOKEN="your-minimax-api-key"
export ANTHROPIC_MODEL=MiniMax-M3[1m]
export ANTHROPIC_DEFAULT_OPUS_MODEL=MiniMax-M3[1m]
export ANTHROPIC_DEFAULT_SONNET_MODEL=MiniMax-M3[1m]
export ANTHROPIC_DEFAULT_HAIKU_MODEL=MiniMax-M2.7-highspeed
export CLAUDE_CODE_AUTO_COMPACT_WINDOW=400000
export ENABLE_TOOL_SEARCH=false

Or use the settings file: .claude/settings-minimax.json

For Codex CLI, see the recipe at .codex/config-minimax.toml. Note that Codex requires a local Responses API proxy since MiniMax only exposes chat completions.

</details> <details> <summary><strong>OpenAI Codex</strong></summary>

Configuration in ~/.codex/config.toml:

• Model: gpt-6.1-sol with model_reasoning_effort set to "high"
• Sandbox: workspace-write with network access enabled
• Auto mode: the "Approve for me" option under /approvals, set by approvals_reviewer = "auto_review". A reviewer subagent judges each escalation against the [auto_review] policy block in .codex/config.toml instead of stopping to ask you, so it trades tokens for far fewer prompts. The policy mirrors the autoMode block in .claude/settings.json
• Plugins: a curated set enabled from this marketplace (simplify, github-dev, python-skills, and more)

</details> <details> <summary><strong>VSCode</strong></summary>

Settings in .vscode/settings.json:

• GitHub Copilot: Custom instructions for automated commit messages and PR descriptions
• Python: Ruff formatting with auto-save and format-on-save enabled
• Terminal: Cross-platform compatibility configurations
• Thinking display: point claudeCode.claudeProcessWrapper at a small wrapper that forces --thinking-display summarized, so thinking tokens still show in the extension (works around 2.1.111+ dropping the flag)

<details> <summary><code>~/.local/bin/claude-wrapper</code> (chmod +x)</summary>

#!/bin/bash
# Workaround for VS Code Claude Code extension 2.1.111+ not passing
# --thinking-display to the binary on Opus 4.7 (API default changed
# to "omitted", so thinking blocks arrive empty).
exec "$@" --thinking-display summarized

</details> </details>

TODO

Visual demos:

• Add before/after comparison slider images or GIFs for each plugin showing the value visually

Zero-MCP goal:

• Replace MCP-based plugins with CLI alternatives where possible (mongodb, tavily, gcloud, azure)

New plugins/skills:

• Payments: Stripe best practices, Polar billing and local dev
• Payments: Paddle billing and checkout skills
• Deployment: Cloudflare platform skill
• Deployment: Hetzner Cloud CLI skill
• Deployment: Dokploy deployment skill
• Frontend design: Anthropic + OpenAI + Vercel skills (bundled as frontend-design-skills)
• Frontend: TanStack (Router, Query, Table, Form)
• Real-time: LiveKit voice/video agent skill
• Documents: Google Docs, PPTX, DOCX, Excel from OpenAI (bundled as openai-office-skills)
• Auth: Clerk, Firebase patterns
• Fullstack: FastAPI, NodeJS backends, Tailwind CSS v4, shadcn/ui, Sentry monitoring, Web Vitals

Static website:

• Publish agentplugins.net as a plugin catalog site with search, category filtering, per-tool install snippets, and GitHub Pages hosting
• SEO: Vercel's suggested SEO guidelines

References

• Claude Code - Official CLI for Claude
• Claude Code Plugins - Plugin format reference
• Anthropic Skills - Official skill examples
• OpenAI Codex - Official CLI for Codex
• Codex Plugins - Plugin format reference
• Antigravity CLI - Official CLI for Antigravity
• Antigravity Plugins - Plugin format reference
• Cursor Plugins - Plugin format reference
• AGENTS.md - Cross-tool agent specification
• Agent Skills - Open format for giving agents new capabilities

Thank you for the support!

<h3 align="center">Contributors</h3> <p align="center"> <a href="https://github.com/fcakyon/claude-codex-settings/graphs/contributors"> <img src="https://contrib.rocks/image?repo=fcakyon/claude-codex-settings" /> </a> </p>