claude-codex-settings

Installation

Prerequisites: Before installing, ensure you have Claude Code and required tools installed. See INSTALL.md for complete prerequisites.

Install agents, commands, hooks, skills, and MCP servers via Claude Code Plugins system:

# Add marketplace
/plugin marketplace add fcakyon/claude-codex-settings

# Install plugins (pick what you need)
/plugin install anthropic-essentials@claude-settings     # Anthropic feature-dev, frontend, CLAUDE.md, skills
/plugin install anthropic-creative-suite@claude-settings # Anthropic docs, theming, artifacts
/plugin install anthropic-plugin-dev@claude-settings     # Anthropic plugin development toolkit
/plugin install phd-skills@claude-settings               # Hypothesis design, paper review, citation checks
/plugin install react-skills@claude-settings             # React, Next.js, React Native best practices
/plugin install agent-browser@claude-settings            # Browser automation CLI
/plugin install web-design-guidelines@claude-settings    # UI review for accessibility, forms, performance
/plugin install github-dev@claude-settings               # Git workflow + GitHub MCP
/plugin install statusline-tools@claude-settings         # Session + 5H usage statusline
/plugin install ultralytics-dev@claude-settings          # Auto-formatting hooks
/plugin install notification-tools@claude-settings       # OS notifications
/plugin install azure-tools@claude-settings              # Azure MCP & Skills (40+ services)
/plugin install ccproxy-tools@claude-settings            # Use any LLM via ccproxy/LiteLLM
/plugin install claude-tools@claude-settings             # Sync CLAUDE.md + allowlist
/plugin install gcloud-tools@claude-settings             # GCloud MCP & Skills
/plugin install general-dev@claude-settings              # Code simplifier + utilities
/plugin install linear-tools@claude-settings             # Linear MCP & Skills
/plugin install mongodb-tools@claude-settings            # MongoDB MCP & Skills (read-only)
/plugin install paper-search-tools@claude-settings       # Paper Search MCP & Skills
/plugin install slack-tools@claude-settings              # Slack MCP & Skills
/plugin install supabase-tools@claude-settings           # Supabase MCP & Skills
/plugin install tavily-tools@claude-settings             # Tavily MCP & Skills

After installing MCP plugins, run /plugin-name:setup for configuration (e.g., /slack-tools:setup).

Then create symlink for cross-tool compatibility:

ln -sfn CLAUDE.md AGENTS.md

Restart Claude Code to activate.

Plugins

anthropic-essentials - Feature dev, frontend design, CLAUDE.md management, skill creation

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

Skills:

• frontend-design - Production-grade frontend interfaces with high design quality
• 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

anthropic-creative-suite - Documents, theming, web artifacts

Selected skills from anthropics/skills. Document skills are proprietary/source-available; others are Apache 2.0.

Skills:

• pdf - PDF processing (read, merge, split, create, OCR)
• docx - Word document creation and editing
• pptx - PowerPoint presentation building
• xlsx - Excel spreadsheet processing
• theme-factory - Generate themes and styling systems
• web-artifacts-builder - Build interactive web artifacts

anthropic-plugin-dev - Plugin development toolkit

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

phd-skills - Hypothesis design, paper review, citation checks

Academic research toolkit from fcakyon/phd-skills. Experiment design, literature review, paper writing, citation verification, and reviewer defense for PhD workflows.

Skills:

• dataset-curation - Dataset preparation and annotation guidelines
• experiment-design - Experiment setup and ablation planning
• latex-setup - LaTeX project configuration
• literature-research - Literature search and review
• paper-verification - Citation and claim verification
• paper-writing - Academic paper drafting
• research-publishing - Submission and publishing workflow
• reviewer-defense - Reviewer response preparation

Agents:

• experiment-analyzer - Analyze experiment results and suggest next steps
• paper-auditor - Audit paper for consistency and completeness

Commands:

• /factcheck - Verify citations and claims
• /fortify - Strengthen paper against reviewer critiques
• /gaps - Find gaps in literature coverage
• /setup - Configure phd-skills
• /xray - Deep analysis of a paper

react-skills - React, Next.js, and React Native best practices

Cherry-picked skills from vercel-labs/agent-skills. 64 React/Next.js rules and 35+ React Native/Expo rules covering performance, rendering, state, animations, and navigation.

Skills:

• react-best-practices - React and Next.js performance patterns: waterfalls, bundle size, server components, re-renders, rendering, JS performance, advanced patterns
• react-native - React Native and Expo: list virtualization, animations with Reanimated, native navigation, UI patterns, state management, monorepo config

agent-browser - Browser Automation CLI for AI Agents

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:

• agent-browser - Browser automation: navigation, forms, clicking, screenshots, auth, sessions, profiling, video recording

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

web-design-guidelines - UI code review for web interface guidelines

Review UI code for compliance with Web Interface Guidelines. Full ruleset inlined for offline use.

Skills:

• web-design-review - Check code against 16 rule categories: accessibility, focus states, forms, animation, typography, content handling, images, performance, navigation, touch, safe areas, dark mode, locale, hydration safety, hover states, anti-patterns

github-dev - Git workflow agents + commands

Git and GitHub automation. Run /github-dev:setup 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-workflow - Commit process and message format
• pr-workflow - PR creation workflow
• pr-comment-workflow - PR comment style and resolution
• setup - GitHub CLI troubleshooting

Commands:

• /commit-staged - Commit staged changes
• /create-pr - Create pull request
• /review-pr - Review pull request
• /resolve-pr-comments - Address unresolved PR comments
• /update-pr-summary - Update PR description
• /clean-gone-branches - Clean deleted branches
• /github-dev:setup - Configure GitHub CLI

Hooks:

• git_commit_confirm.py - Confirmation before git commit
• gh_pr_create_confirm.py - Confirmation before gh pr create

statusline-tools - Session + 5H Usage Statusline

Cross-platform statusline showing session context %, cost, and account-wide 5H usage with time until reset. Run /statusline-tools:setup after install.

Skills:

• setup - Statusline configuration guide

Commands:

• /statusline-tools:setup - Configure statusline

ultralytics-dev - Auto-formatting hooks

Auto-formatting hooks for Python, JavaScript, Markdown, and Bash.

Hooks:

• format_python_docstrings.py - Google-style docstring formatter
• python_code_quality.py - Python code quality with ruff
• prettier_formatting.py - JavaScript/TypeScript/CSS/JSON
• markdown_formatting.py - Markdown formatting
• bash_formatting.py - Bash script formatting

notification-tools - OS notifications

Desktop notifications when Claude Code completes tasks.

Hooks:

• notify.sh - OS notifications on task completion

azure-tools - Azure MCP & Skills

40+ Azure services with Azure CLI authentication. 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

ccproxy-tools - Use Claude Code with any LLM

Configure Claude Code to use ccproxy/LiteLLM with Claude Pro/Max subscription, GitHub Copilot, or other providers. Run /ccproxy-tools:setup after install.

Commands:

• /ccproxy-tools:setup - Configure ccproxy/LiteLLM

Skills:

• setup - Troubleshooting guide

claude-tools - Sync CLAUDE.md + allowlist + context refresh

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

Hooks:

• sync_marketplace_to_plugins.py - Syncs marketplace.json to plugin.json

gcloud-tools - GCloud MCP & Skills

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

general-dev - Code simplifier + utilities

Code quality agent and utility hooks.

Agent:

• code-simplifier - Ensures code follows conventions

Hooks:

• enforce_rg_over_grep.py - Suggest ripgrep

linear-tools - Linear MCP & Skills

Issue tracking with OAuth. Run /linear-tools:setup after install.

Skills:

• linear-usage - Best practices for Linear
• setup - Troubleshooting guide

Commands:

• /linear-tools:setup - Configure Linear MCP

MCP: .mcp.json | Linear MCP Docs

mongodb-tools - MongoDB MCP & Skills

Database exploration (read-only). Run /mongodb-tools:setup after install.

Skills:

• mongodb-usage - Best practices for MongoDB
• setup - Troubleshooting guide

Commands:

• /mongodb-tools:setup - Configure MongoDB MCP

MCP: .mcp.json | mongodb-js/mongodb-mcp-server

paper-search-tools - Paper Search MCP & Skills

Search papers across arXiv, PubMed, IEEE, Scopus, ACM. Run /paper-search-tools:setup after install. Requires Docker.

Skills:

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

Commands:

• /paper-search-tools:setup - Configure Paper Search MCP

MCP: .mcp.json | mcp/paper-search

slack-tools - Slack MCP & Skills

Message search and channel history. Run /slack-tools:setup after install.

Skills:

• slack-usage - Best practices for Slack MCP
• setup - Troubleshooting guide

Commands:

• /slack-tools:setup - Configure Slack MCP

MCP: .mcp.json | ubie-oss/slack-mcp-server

supabase-tools - Supabase MCP & Skills

Database management with OAuth. Run /supabase-tools:setup after install.

Skills:

• supabase-usage - Best practices for Supabase MCP
• setup - Troubleshooting guide

Commands:

• /supabase-tools:setup - Configure Supabase MCP

MCP: .mcp.json | supabase-community/supabase-mcp

tavily-tools - Tavily MCP & Skills

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

---

Configuration

Claude Code

Configuration in .claude/settings.json:

• Model: OpusPlan mode (plan: Opus 4.6, execute: Opus 4.6, fast: Sonnet 4.6) - source
• Environment: bash working directory, telemetry disabled, MCP output limits
• Permissions: bash commands, git operations, MCP tools
• Statusline: Custom usage tracking powered by ccusage
• Plugins: All plugins enabled

Z.ai (85% cheaper)

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

• Main model: GLM-5-Turbo (dialogue, planning, coding, complex reasoning)
• Fast model: GLM-4.7-Flash (file search, syntax checking)
• Cost savings: 85% cheaper than Claude 4.6 - source
• API key: Get from z.ai/model-api

Kimi K2.5

Run Claude Code with Kimi K2.5 via Anthropic-compatible API - source:

• Model: kimi-k2.5 - High-speed thinking, 256K context
• 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-k2.5
export ANTHROPIC_DEFAULT_OPUS_MODEL=kimi-k2.5
export ANTHROPIC_DEFAULT_SONNET_MODEL=kimi-k2.5
export ANTHROPIC_DEFAULT_HAIKU_MODEL=kimi-k2.5
export CLAUDE_CODE_SUBAGENT_MODEL=kimi-k2.5
export ENABLE_TOOL_SEARCH=false

OpenAI Codex

Configuration in ~/.codex/config.toml:

• Model: gpt-5.4 with model_reasoning_effort set to "high"
• Provider: Azure via responses API surface
• Auth: Project-specific base URL with env_key authentication

ccproxy (Use Claude Code with Any LLM)

Assign any API or model to any task type via ccproxy:

• MAX/Pro subscription: Uses OAuth from your Claude subscription (no API keys)
• Any provider: OpenAI, Gemini, Perplexity, local LLMs, or any OpenAI-compatible API
• Fully customizable: Assign different models to default, thinking, planning, background tasks
• SDK support: Works with Anthropic SDK and LiteLLM SDK beyond Claude Code

VSCode

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

Statusline

Simple statusline plugin that uses the official usage API to show account-wide block usage and reset time in real-time. Works for both API and subscription users.

Setup

/plugin marketplace add fcakyon/claude-codex-settings
/plugin install statusline-tools@claude-settings
/statusline-tools:setup

Color coding:

• 🟢 <50% usage / <1h until reset
• 🟡 50-70% usage / 1-3.5h until reset
• 🔴 70%+ usage / >3.5h until reset

See Claude Code statusline docs for details.

TODO

• App dokploy tools plugin with dokploy-mcp server and deployment best practices skill
• Add more comprehsensive fullstack-dev plugin with various ocnfigurable skills:
  • Backend: FastAPI, NodeJS
  • Auth: Clerk (Auth, Email), Firebase/Firestore (Auth, DB), Supabase+Resend (Auth, DB, Email) RBAC with org:admin and org:member roles
  • Styling: Tailwind CSS v4, shadcn/ui components, Radix UI primitives
  • Monitoring: Sentry (errors, APM, session replay, structured logs)
  • Analytics: Web Vitals + Google Analytics
• Publish claudesettings.com as a comprehensive documentation for installing, using and sharing useful Claude-Code settings
• Rename plugins names to mongodb-skills, github-skills ...instead of mongodb-tools, github-dev ... for better UX
• Add worktree support to github-dev create-pr and commit-staged commands for easier work on multiple branches of the same repo simultaneously
• Add current repo branch and worktree info into statusline-tools plugin

References

• Claude Code - Official CLI for Claude
• Anthropic Skills - Official skill examples

Thank you for the support!