Skip to content

supatest-ai/awesome-claude-code-sub-agents

Repository files navigation

Awesome Claude Code Agents πŸ€–

A comprehensive collection of specialized Claude Code agents for software development, designed as expert consultants that provide architectural guidance, decision frameworks, and best practices. Each agent focuses on helping you make informed technology choices and design decisions rather than generating code.

πŸš€ Quick Start

Setting Up Claude Code Agents

  1. Install Claude Code: Follow the official installation guide

  2. Clone this repository:

    git clone https://github.com/supatest-ai/awesome-claude-code-agents.git
    cd awesome-claude-code-agents
  3. Copy agent files: Copy the agent .md files to your Claude Code agents directory:

    cp */*.md ~/.config/claude-code/agents/
  4. Verify installation: List available agents:

    claude-code agents list

How to Use Agents

Claude Code agents can be invoked in several ways:

  1. Automatic Invocation: Agents with PROACTIVELY in their description will be automatically invoked based on context
  2. Manual Invocation: Use @agent-name in your messages to explicitly invoke an agent
  3. Task-Specific: Agents will be suggested based on the files you're working with and the tasks you're performing

For more details, see the Claude Code documentation.

πŸ“ Repository Structure

awesome-claude-code-agents/
β”œβ”€β”€ README.md                          # This file
β”œβ”€β”€ CONTRIBUTING.md                    # Contribution guidelines
β”œβ”€β”€ languages/                         # Programming language experts
β”‚   β”œβ”€β”€ python-expert.md
β”‚   β”œβ”€β”€ javascript-typescript-expert.md
β”‚   β”œβ”€β”€ java-expert.md
β”‚   β”œβ”€β”€ go-expert.md
β”‚   β”œβ”€β”€ csharp-expert.md
β”‚   β”œβ”€β”€ rust-expert.md
β”‚   β”œβ”€β”€ ruby-expert.md
β”‚   β”œβ”€β”€ php-expert.md
β”‚   β”œβ”€β”€ swift-expert.md
β”‚   └── kotlin-expert.md
β”œβ”€β”€ frameworks/                        # Framework specialists
β”‚   β”œβ”€β”€ react-architect.md
β”‚   β”œβ”€β”€ vue-specialist.md
β”‚   β”œβ”€β”€ angular-expert.md
β”‚   β”œβ”€β”€ django-expert.md
β”‚   └── spring-boot-expert.md
β”œβ”€β”€ development-workflows/             # Development workflow experts
β”‚   └── code-review-master.md
β”œβ”€β”€ architecture/                      # System architecture specialists
β”‚   β”œβ”€β”€ design-patterns-expert.md
β”‚   β”œβ”€β”€ microservices-architect.md
β”‚   └── clean-architecture-expert.md
β”œβ”€β”€ testing/                          # Testing and quality assurance
β”‚   β”œβ”€β”€ test-automation-specialist.md
β”‚   └── performance-testing-expert.md
β”œβ”€β”€ performance/                      # Performance specialists
β”‚   └── performance-optimization-specialist.md
β”œβ”€β”€ data-science/                     # Data science and analytics
β”‚   └── python-data-scientist.md
β”œβ”€β”€ llm-engineering/                 # LLM engineering and operations
β”‚   β”œβ”€β”€ prompt-engineering-specialist.md
β”‚   β”œβ”€β”€ rag-architecture-expert.md
β”‚   β”œβ”€β”€ llmops-engineer.md
β”‚   β”œβ”€β”€ multi-agent-systems-architect.md
β”‚   β”œβ”€β”€ llm-finetuning-expert.md
β”‚   └── llm-observability-specialist.md
β”œβ”€β”€ ai-ml/                           # AI and machine learning
β”‚   └── machine-learning-engineer.md
β”œβ”€β”€ devops/                          # DevOps and infrastructure
β”‚   β”œβ”€β”€ aws-cloud-architect.md
β”‚   β”œβ”€β”€ docker-specialist.md
β”‚   β”œβ”€β”€ kubernetes-expert.md
β”‚   └── terraform-infrastructure-expert.md
β”œβ”€β”€ industries/                      # Industry domain experts
β”‚   β”œβ”€β”€ fintech-security-expert.md
β”‚   └── healthcare-hipaa-expert.md
β”œβ”€β”€ templates/                       # Agent templates for custom agents
β”‚   β”œβ”€β”€ basic-agent-template.md
β”‚   └── advanced-agent-template.md
└── docs/                           # Additional documentation
    β”œβ”€β”€ agent-development-guide.md
    β”œβ”€β”€ best-practices.md
    └── examples/

🎯 Agent Philosophy

🧠 Guidance-First Approach

Our agents function as specialized architectural consultants rather than code generators. They help you:

  • Make Technology Decisions: When to use React vs Vue, PostgreSQL vs MongoDB
  • Choose Architecture Patterns: Microservices vs monolith, CQRS vs traditional CRUD
  • Optimize Performance: Caching strategies, database tuning, scaling approaches
  • Navigate Ecosystems: Library selection, version management, best practices
  • Solve Design Problems: Code organization, testing strategies, deployment patterns

πŸ“ Agent Design Principles

  • Decision Frameworks: Clear when/why/how guidance for technology choices
  • Architectural Focus: System design and structural decisions over syntax
  • Production-Ready: Enterprise-grade patterns and real-world considerations
  • Ecosystem Navigation: Modern tooling and library selection guidance
  • Best Practices: Security, performance, and maintainability built-in

🎯 Agent Categories

πŸ”€ Languages

Ecosystem guides for programming languages focusing on framework selection, performance optimization, and architectural decisions.

  • Python Expert - Ecosystem guidance for Python 3.8+, framework selection (Django/FastAPI/Flask), and performance optimization
  • JavaScript/TypeScript Expert - Modern JS/TS tooling decisions, build system selection, and performance patterns
  • Java Expert - Java 17+ ecosystem choices, Spring vs alternatives, JVM optimization, and enterprise patterns
  • Go Expert - Go project architecture, library selection, concurrency patterns, and performance optimization
  • Haskell Expert - Advanced functional programming, type system features, STM, and performance optimization
  • Clojure Expert - Functional programming, immutable data structures, concurrency primitives, and ClojureScript

πŸ—οΈ Frameworks

Architecture specialists for popular frameworks focusing on project structure, state management decisions, and performance optimization.

  • React Architect - React 18+ architectural decisions, state management selection, performance optimization, and testing strategies
  • Vue Specialist - Vue 3 Composition API architecture, Pinia vs alternatives, performance patterns, and modern tooling
  • Angular Expert - Angular 17+ architectural patterns, state management, RxJS optimization, and enterprise scaling
  • Django Expert - Django architecture decisions, DRF vs alternatives, async patterns, and production deployment
  • Spring Boot Expert - Spring Boot 3+ architectural choices, reactive programming decisions, and microservices patterns

πŸ”„ Development Workflows

Agents focused on development workflows, code quality, and team collaboration with comprehensive automation and best practices.

Development Workflow

  • Git Workflow Expert - Advanced Git strategies, branching models (Git Flow, GitHub Flow), merge conflict resolution, and hooks automation
  • CI/CD Pipeline Architect - GitHub Actions, GitLab CI, Jenkins pipelines, testing automation, and deployment strategies
  • Project Setup Wizard - Multi-language project scaffolding, tooling configuration, and development environment setup
  • Code Quality Guardian - Linting, formatting, pre-commit hooks, quality gates, and technical debt management
  • Documentation Specialist - README optimization, API docs, architectural decision records, and documentation automation
  • Dependency Manager - Package management, security auditing, version updates, and license compliance

Team Collaboration

  • Code Review Master - Comprehensive code review focusing on security, performance, maintainability, and best practices
  • Agile Sprint Planner - User story creation, sprint planning, estimation techniques, and backlog management
  • Technical Debt Analyst - Technical debt identification, refactoring strategies, and priority assessment

Testing & Quality

  • Test Strategy Architect - Testing pyramid, test planning, coverage analysis, and test automation frameworks
  • Security Audit Expert - Security scanning, vulnerability assessment, penetration testing, and secure coding practices
  • Performance Profiler - Performance testing, bottleneck identification, load testing, and optimization strategies

Release & Deployment

  • Release Manager - Release planning, changelog generation, version management, and rollback strategies
  • Environment Manager - Development, staging, production environments, and infrastructure configuration management

πŸ›οΈ Architecture

System architecture specialists focusing on pattern selection, design decisions, and scalability strategies.

  • Design Patterns Expert - Pattern selection guidance, when to use specific patterns, anti-pattern avoidance, and architectural decisions
  • Microservices Architect - Microservices vs monolith decisions, service decomposition strategies, and distributed systems patterns
  • Clean Architecture Expert - Architectural boundaries, dependency management, and enterprise application design

πŸ§ͺ Testing

Comprehensive testing strategies and quality assurance practices.

⚑ Performance

Performance specialists focused on optimization and scalability.

πŸš€ DevOps

Infrastructure architecture specialists focusing on deployment strategies, scalability decisions, and operational excellence.

  • Docker Specialist - Containerization strategy, optimization patterns, security considerations, and production deployment decisions
  • Kubernetes Expert - Orchestration architecture, deployment strategies, scaling patterns, and operational excellence
  • AWS Cloud Architect - Service selection framework, architectural patterns, cost optimization, and Well-Architected principles
  • Terraform Infrastructure Expert - Infrastructure as Code patterns, state management strategies, and multi-cloud architecture

🧠 LLM Engineering

Specialized agents for Large Language Model engineering, operations, and production systems with focus on modern LLM application development.

  • Prompt Engineering Specialist - Advanced prompt design, optimization techniques, few-shot learning, chain-of-thought reasoning, and evaluation frameworks
  • RAG Architecture Expert - Retrieval-Augmented Generation systems, vector databases, document processing, and hybrid search strategies
  • LLMOps Engineer - Production LLM deployment, model serving, scaling strategies, cost optimization, and operational monitoring
  • Multi-Agent Systems Architect - Complex agent orchestration, coordination patterns, collaborative workflows, and distributed AI systems
  • LLM Fine-tuning Expert - Parameter-efficient fine-tuning (PEFT), LoRA/QLoRA techniques, dataset preparation, and training optimization
  • LLM Observability Specialist - Comprehensive monitoring, performance tracking, cost analysis, quality assessment, and system health for LLM applications

πŸ€– Data Science & AI

Data science and machine learning specialists for analytics, modeling, and production ML systems.

  • Python Data Scientist - Data exploration, statistical analysis, feature engineering, and machine learning workflows
  • Machine Learning Engineer - MLOps, model deployment, monitoring, drift detection, and production ML infrastructure

🏒 Industries

Domain experts for specific industries with specialized knowledge and compliance requirements.

  • FinTech Security Expert - Financial services security, PCI DSS compliance, KYC/AML, secure payment processing, and regulatory standards
  • Healthcare HIPAA Expert - Healthcare technology, HIPAA compliance, medical data security, HL7 FHIR, and patient privacy

✨ What Makes These Agents Different

🎯 Decision-Focused Architecture

Unlike traditional code-generation agents, our agents are designed as specialized consultants that help you make informed architectural and technology decisions:

Traditional Agents:          Our Agents:
"Here's React code"    β†’     "When to choose React vs Vue vs Angular"
"FastAPI example"      β†’     "Django vs FastAPI vs Flask decision matrix"  
"Docker config"        β†’     "Containerization strategy and patterns"
"AWS Lambda code"      β†’     "Serverless vs container deployment decisions"

πŸ“Š Research-Based Design

Based on analysis of successful Claude Code agent repositories, our agents follow proven patterns:

  • 300-800 lines: Focused, actionable content (vs 2000+ line tutorials)
  • 80/20 Guidance/Code: Decision frameworks over implementations
  • Production-Ready: Enterprise patterns and real-world considerations
  • Model-Optimized: Sonnet for complex decisions, Haiku for simple tasks

πŸ—οΈ Architectural Consultant Approach

Each agent acts as a domain expert consultant providing:

  • Technology Selection: When/why to choose specific tools and frameworks
  • Architecture Patterns: System design and structural decisions
  • Performance Optimization: Scaling strategies and bottleneck identification
  • Best Practices: Security, maintainability, and operational excellence
  • Ecosystem Navigation: Modern tooling and version management

🎨 Agent Design Philosophy

Each agent in this collection follows these design principles:

🎯 Focused Expertise

  • Single Responsibility: Each agent has a clear, focused area of expertise
  • Deep Knowledge: Comprehensive understanding of their domain with modern best practices
  • Practical Examples: Production-ready code examples and real-world scenarios

πŸš€ Modern Best Practices

  • Current Technologies: Up-to-date with latest versions and features
  • Security First: Security considerations and best practices built-in
  • Performance Oriented: Optimization patterns and performance considerations

πŸ“š Comprehensive Documentation

  • Clear Instructions: Step-by-step guidance and usage examples
  • Code Samples: Extensive, well-commented code examples
  • Testing Strategies: Comprehensive testing approaches and examples

πŸ”§ Production Ready

  • Error Handling: Robust error handling and edge case management
  • Scalability: Patterns that work at scale
  • Maintainability: Clean, readable, and maintainable code practices

πŸ› οΈ Agent YAML Format

All agents follow the Claude Code subagent format with YAML frontmatter:

---
name: agent-name
description: Brief description with PROACTIVELY keyword for auto-invocation
tools: Read, Write, Edit, Bash, Grep, Glob, MultiEdit
---

Required Fields:

  • name: Unique identifier for the agent (kebab-case)
  • description: Clear description of agent capabilities and when to use it
  • tools: List of Claude Code tools the agent can access

Best Practices:

  • Use PROACTIVELY in description for agents that should be auto-invoked
  • Be specific about when and how the agent should be used
  • Include the most relevant tools for the agent's domain

🀝 Contributing

We welcome contributions from the community! See our Contributing Guidelines for details on:

  • Adding new agents
  • Improving existing agents
  • Reporting issues
  • Suggesting enhancements

Quick Contribution Steps:

  1. Fork the repository
  2. Create a new agent using our templates
  3. Follow our best practices guide
  4. Submit a pull request

πŸ“– Additional Resources

πŸ“„ License

This project is licensed under the MIT License - see the LICENSE file for details.

πŸ™ Acknowledgments

This project builds upon the excellent work of the open-source community. Special thanks to:

  • The Claude Code team at Anthropic
  • Contributors to popular frameworks and libraries referenced in our agents
  • The broader developer community for sharing knowledge and best practices

⭐ Support

If you find this collection helpful, please consider:

  • ⭐ Starring the repository
  • πŸ› Reporting issues or bugs
  • πŸ’‘ Suggesting new agents or improvements
  • 🀝 Contributing to the project
  • πŸ“’ Sharing with other developers

Built with ❀️ for the developer community

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •