claude-modular

by oxygen-fragmentVerified

Production-ready modular Claude Code framework with 30+ commands, token optimization, and MCP server integration. Achieves 2-10x productivity gains through systematic command organization and hierarchical configuration.

285
Stars
43
Forks
8/23/2026
Added
View on GitHubDownload ZIP

⚠️ Third-Party Software Notice

This skill is third-party open-source software developed and hosted independently on GitHub. SkillTip is an informational directory and does not control or maintain the underlying repository. Any security checks displayed are automated and limited in scope. Review the source code before installing.

Read the Terms of Service

Installation

Add to your Claude Code skills directory:

# Add to your Claude Code skills
git clone https://github.com/oxygen-fragment/claude-modular

Getting Started

Guides for using skills like claude-modular.

Security Report

Verified

Last scanned: —

{
  "status": "PASSED",
  "issues": []
}

README.md

Claude Code Modular Framework

A comprehensive, production-ready modular framework template for Claude Code that achieves 2-10x productivity gains through proven patterns, token optimization, and systematic development workflows.

🚀 Quick Start

1. Clone and Setup

git clone https://github.com/your-username/claude-modular.git
cd claude-modular
cp templates/CLAUDE.md.template CLAUDE.md
# Edit CLAUDE.md with your project-specific details

2. Initialize Your Project

# Copy the .claude directory to your project root
cp -r .claude /path/to/your/project/

# Customize configuration for your environment
cd /path/to/your/project/.claude/config
# Edit settings.json, development.json, etc.

3. Start Using Commands

# In your project with Claude Code
/project:setup-environment
/project:create-feature user-authentication
/test:generate-tests
/dev:code-review

📚 Features

✅ Token Optimization (50-80% savings)

  • Progressive disclosure - Load only necessary context
  • Modular instructions - Just-in-time command loading
  • Context compression - Efficient context management
  • Smart boundaries - Automatic context switching

✅ 20+ Production-Ready Commands

  • Project Management - Feature creation, component scaffolding
  • Development Workflow - Code review, refactoring, debugging
  • Testing Automation - Test generation, coverage analysis
  • Deployment - Release preparation, staging deployment, rollback
  • Documentation - API docs, README updates, architecture review

✅ Environment-Specific Configuration

  • Development - Relaxed rules, verbose logging
  • Staging - Quality gates, review requirements
  • Production - Strict security, multi-factor auth

✅ Security-First Design

  • Secret scanning prevention
  • Permission validation for sensitive operations
  • Audit logging for compliance
  • Environment variable management

🏗️ Architecture

Directory Structure

your-project/
├── .claude/                    # Framework configuration
│   ├── config/                 # Environment-specific settings
│   │   ├── settings.json       # Base configuration
│   │   ├── development.json    # Dev environment
│   │   ├── staging.json        # Staging environment
│   │   └── production.json     # Production environment
│   └── commands/               # Modular command library
│       ├── project/            # Project management
│       ├── development/        # Development workflow
│       ├── testing/            # Testing automation
│       ├── deployment/         # Deployment operations
│       └── documentation/      # Documentation generation
├── CLAUDE.md                   # Your project-specific configuration
└── [your project files]

Command Structure

Each command follows a proven XML structure:

<instructions>
  <context>When and why to use this command</context>
  <requirements>Prerequisites and dependencies</requirements>
  <execution>Step-by-step implementation</execution>
  <validation>Quality checks and acceptance criteria</validation>
  <examples>Concrete usage examples</examples>
</instructions>

📖 Command Reference

Project Management

  • /project:create-feature - Full feature scaffolding with tests and docs
  • /project:scaffold-component - Component creation with boilerplate
  • /project:setup-environment - Development environment initialization

Development Workflow

  • /dev:code-review - Structured code review with automated analysis
  • /dev:refactor-analysis - Code improvement recommendations
  • /dev:debug-session - Systematic debugging and problem solving

Testing

  • /test:generate-tests - Comprehensive test suite generation
  • /test:coverage-analysis - Test coverage assessment and improvement
  • /test:integration-tests - Integration test creation and execution

Deployment

  • /deploy:prepare-release - Release preparation with quality gates
  • /deploy:deploy-staging - Staging deployment with validation
  • /deploy:rollback-procedure - Emergency rollback execution

Documentation

  • /docs:api-docs - API documentation generation
  • /docs:update-readme - README maintenance and updates
  • /docs:architecture-review - Architecture documentation and review

⚙️ Configuration

Environment Configuration

The framework supports layered configuration inheritance:

// Base settings.json
{
  "defaults": {
    "max_tokens_per_session": 50000,
    "progressive_disclosure": true
  }
}

// development.json overrides
{
  "extends": "./settings.json",
  "overrides": {
    "defaults": {
      "max_tokens_per_session": 100000
    }
  }
}

Security Configuration

{
  "security": {
    "require_env_vars": true,
    "audit_logging": true,
    "permission_validation": true,
    "secret_scanning": true
  }
}

🔧 Customization

Creating Custom Commands

  1. Create a new command file in appropriate category
  2. Follow the XML structure template
  3. Include comprehensive examples
  4. Test with realistic scenarios

Adapting for Your Stack

  1. Edit templates/CLAUDE.md.template with your technologies
  2. Update command examples for your build tools
  3. Customize quality gates for your requirements
  4. Add stack-specific validation rules

📊 Performance Metrics

Token Optimization Results

  • 50-80% token savings vs monolithic setups
  • Sub-30-second setup time for new projects
  • 20+ core commands covering 80% of workflows
  • Progressive disclosure reduces context overhead

Quality Improvements

  • Consistent code review quality
  • Automated testing coverage
  • Standardized deployment procedures
  • Comprehensive documentation generation

🛠️ Integration

MCP Server Support

  • Memory MCP - Context persistence between sessions
  • Git MCP - Version control integration
  • Filesystem MCP - File operations and watching
  • Linear MCP - Issue tracking integration
  • Notion MCP - Documentation synchronization

CI/CD Integration

  • GitHub Actions support
  • Quality gate enforcement
  • Automated testing pipelines
  • Deployment automation

📚 Examples

Basic Usage

# Setup new project
/project:setup-environment

# Create a feature
/project:create-feature user-authentication --type=service

# Review code
/dev:code-review --focus=security,performance

# Deploy to staging
/deploy:deploy-staging

Advanced Workflows

# Complex feature development
/project:create-feature payment-processing --framework=express --database=postgresql

# Comprehensive testing
/test:generate-tests --types=unit,integration,e2e
/test:coverage-analysis --target=90%

# Production deployment
/deploy:prepare-release --type=major
/deploy:deploy-staging --validate
/deploy:rollback-procedure --preserve-data

🤝 Contributing

  1. Fork the repository
  2. Create feature branch: git checkout -b feature/new-command
  3. Add your command following the XML structure
  4. Include comprehensive examples and tests
  5. Update documentation
  6. Submit pull request

📄 License

MIT License - see LICENSE file for details.

🙏 Acknowledgments

Based on research papers:

  • "The modular Claude Code implementation playbook"
  • "Optimizing Agentic Development Workflows with Claude Code"

📞 Support


If you want to help me out you can ko-fi

Start building better, faster, and more consistently with Claude Code's modular framework.

Frequently Asked Questions

What is claude-modular?

claude-modular is an open-source mcp servers skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by oxygen-fragment. Production-ready modular Claude Code framework with 30+ commands, token optimization, and MCP server integration. Achieves 2-10x productivity gains through systematic command organization and hierarchical configuration. It has 285 GitHub stars.

Is claude-modular safe to use?

Yes. claude-modular passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install claude-modular?

Clone the repository with "git clone https://github.com/oxygen-fragment/claude-modular" and add it to your Claude Code skills directory (see the Installation section above).

Are there alternatives to claude-modular?

Yes. SkillsLLM lists many other MCP Servers skills you can browse and compare side by side. Open the MCP Servers category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh claude-modular against similar tools.

Comments (0)

No comments yet. Be the first to share your thoughts!

n8n

by n8n-io

12

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

201,88160,308TypeScript
MCP Serversapisai-tools
View details

Scrapling

by D4Vinci

🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!

75,9137,581Python
MCP Servers
View details

TrendRadar

by sansan0

⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载,你的 AI 舆情监控助手与热点筛选工具!聚合多平台热点 + RSS 订阅,支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机,也支持接入 MCP 架构,赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ,数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。

61,65224,883Python
MCP Servers
View details

context7

by upstash

Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

61,0602,938TypeScript
MCP Servers
View details

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

39,9393,219C
MCP Servers
View details

Developers Also Liked

Based on votes and bookmarks from developers who liked this skill

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI Agentsai-agentsanthropicclaude-code
View details
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI Agentsai-agentsbrainstorming
View details

n8n

by n8n-io

12

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

201,88160,308TypeScript
MCP Serversapisai-tools
View details

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI Agentsai-agentsanthropicclaude-code
View details

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI Agentsclaude-codeai-tools
View details