Awesome Claude Agents - AI Development Team 🚀

Supercharge Claude Code with a team of specialized AI agents that work together to build complete features, debug complex issues, and handle any technology stack with expert-level knowledge.

⚠️ Important Notice

This project is experimental and token-intensive. I'm actively testing these agents with Claude subscription - expect high token consumption during complex workflows. Multi-agent orchestration can consume 10-50k tokens per complex feature. Use with caution and monitor your usage.

🚀 Quick Start (3 Minutes)

Prerequisites

• Claude Code CLI installed and authenticated
• Claude subscription - required for intensive agent workflows
• Active project directory with your codebase
• Optional: Context7 MCP for enhanced documentation access

1. Install the Agents

git clone https://github.com/vijaythecoder/awesome-claude-agents.git

Option A: Symlink (Recommended - auto-updates)

macOS/Linux:

# Create agents directory if it doesn't exist (preserves existing agents)
mkdir -p ~/.claude/agents

# Symlink the awesome-claude-agents collection
ln -sf "$(pwd)/awesome-claude-agents/agents/" ~/.claude/agents/awesome-claude-agents

Windows (PowerShell):

# Create agents directory
New-Item -Path "$env:USERPROFILE\.claude\agents" -ItemType Directory -Force

# Create symlink
cmd /c mklink /D "$env:USERPROFILE\.claude\agents\awesome-claude-agents" "$(Get-Location)\awesome-claude-agents\agents"

Option B: Copy (Static - no auto-updates)

# Create agents directory if it doesn't exist
mkdir -p ~/.claude/agents

# Copy all agents
cp -r awesome-claude-agents/agents ~/.claude/agents/awesome-claude-agents

2. Verify Installation

claude /agents
# Should show all 24 agents.

3. Initialize Your Project

Navigate to your project directory and run the following command to configure your AI team:

claude "use @agent-team-configurator and optimize my project to best use the available subagents."

4. Start Building

claude "use @agent-tech-lead-orchestrator and build a user authentication system"

Your AI team will automatically detect your stack and use the right specialists!

🎯 How Auto-Configuration Works

The @agent-team-configurator automatically sets up your perfect AI development team. When invoked, it:

1. Locates CLAUDE.md - Finds existing project configuration and preserves all your custom content outside the "AI Team Configuration" section
2. Detects Technology Stack - Inspects package.json, composer.json, requirements.txt, go.mod, Gemfile, and build configs to understand your project
3. Discovers Available Agents - Scans ~/.claude/agents/ and .claude/ folders, building a capability table of all available specialists
4. Selects Specialists - Prefers framework-specific agents over universal ones, always includes @agent-code-reviewer and @agent-performance-optimizer for quality assurance
5. Updates CLAUDE.md - Creates a timestamped "AI Team Configuration" section with your detected stack and a Task|Agent|Notes mapping table
6. Provides Usage Guidance - Shows you the detected stack, selected agents, and gives sample commands to start building

👥 Meet Your AI Development Team

🎭 Orchestrators (3 agents)

• Tech Lead Orchestrator - Senior technical lead who analyzes complex projects and coordinates multi-step development tasks
• Project Analyst - Technology stack detection specialist who enables intelligent agent routing
• Team Configurator - AI team setup expert who detects your stack and configures optimal agent mappings

💼 Framework Specialists (13 agents)

• Laravel (2 agents)
  • Backend Expert - Comprehensive Laravel development with MVC, services, and Eloquent patterns
  • Eloquent Expert - Advanced ORM optimization, complex queries, and database performance
• Django (3 agents)
  • Backend Expert - Models, views, services following current Django conventions
  • API Developer - Django REST Framework and GraphQL implementations
  • ORM Expert - Query optimization and database performance for Django applications
• Rails (3 agents)
  • Backend Expert - Full-stack Rails development following conventions
  • API Developer - RESTful APIs and GraphQL with Rails patterns
  • ActiveRecord Expert - Complex queries and database optimization
• React (2 agents)
  • Component Architect - Modern React patterns, hooks, and component design
  • Next.js Expert - SSR, SSG, ISR, and full-stack Next.js applications
• Vue (3 agents)
  • Component Architect - Vue 3 Composition API and component patterns
  • Nuxt Expert - SSR, SSG, and full-stack Nuxt applications
  • State Manager - Pinia and Vuex state architecture

🌐 Universal Experts (4 agents)

• Backend Developer - Polyglot backend development across multiple languages and frameworks
• Frontend Developer - Modern web technologies and responsive design for any framework
• API Architect - RESTful design, GraphQL, and framework-agnostic API architecture
• Tailwind Frontend Expert - Tailwind CSS styling, utility-first development, and responsive components

🔧 Core Team (4 agents)

• Code Archaeologist - Explores, documents, and analyzes unfamiliar or legacy codebases
• Code Reviewer - Rigorous security-aware reviews with severity-tagged reports
• Performance Optimizer - Identifies bottlenecks and applies optimizations for scalable systems
• Documentation Specialist - Crafts comprehensive READMEs, API specs, and technical documentation

Total: 24 specialized agents working together to build your projects!

Browse all agents →

🔥 Why Teams Beat Solo AI

• Specialized Expertise: Each agent masters their domain with deep, current knowledge
• Real Collaboration: Agents coordinate seamlessly, sharing context and handing off tasks
• Tailored Solutions: Get code that matches your exact stack and follows its best practices
• Parallel Execution: Multiple specialists work simultaneously for faster delivery

📈 The Impact

• Ship Faster - Complete features in minutes, not days
• Better Code Quality - Every line follows best practices
• Learn As You Code - See how experts approach problems
• Scale Confidently - Architecture designed for growth

📚 Learn More

• Creating Custom Agents - Build specialists for your needs
• Best Practices - Get the most from your AI team

💬 Join The Community

• ⭐ Star this repo to show support
• 🐛 Report issues
• 💡 Share ideas
• 🎉 Success stories

📄 License

MIT License - Use freely in your projects!

Star History

---

TalentDelta provenance record (added at packaging)

• Packaged for: TalentDelta catalogue (draft; gated by review)
• Upstream: vijaythecoder/awesome-claude-agents
• Pinned commit: 2050f3c60fcfea497f7b6b3ec6566cc316367a7e (2025-10-29)
• Licence: MITMIT License at the repository root, 'Copyright (c) 2024 Awesome Claude Agents Contributors'. Permissive: use, modification and redistribution allowed with attribution; no per-file headers to preserve. Shipped byte-identical to the pin; no scrubbing applied.
• Upstream author credit: vijaythecoder (Vijay Tupakula)
• Runtime: Claude Code (project-local .claude/agents layout or agents/ copied directly); any agent host that reads markdown subagent definitions
• Changes made at packaging: this section was appended to README.md. No upstream path is excluded. No file was added, removed, renamed or edited; every file is byte-identical to the pinned commit.
• Safety read of the packaged archive (packaging time, 2026-10-12): Leak scan of the packaged archive: 9 pattern hits. 8 api-key-shaped matches sit inside Python, Django and Rails code examples in agent definitions — method calls and lookups on variables named api_key, with no literal values — and 1 email match is the contribution address the upstream repository publishes in its own CONTRIBUTING.md. No credentials, keys or personal data; nothing is scrubbed because nothing needed scrubbing.

Packaging notes (TalentDelta)

• Whole-repository pack: 41 files, 0.2 MB — no exclusion list applies.
• Team-shaped rather than catalogue-shaped: the orchestrators carry the assignment rules the specialists rely on, which is why they ship together with CLAUDE.md.
• One definition repeats a name upstream: agents/specialized/vue/vue-state-manager.md still declares the name vue-component-architect, so the 33 files yield 32 distinct names. Both are kept byte-identical to upstream.
• Counts re-derived from the built archive.