Skip to content

About

Production-ready multi-agent system for Claude Code with specialized agents for architecture, product management, frontend, backend, QA, deployment, and operations

Resources

Stars

1 star

Watchers

0 watching

Forks

Latest commit

 

History

1 Commit

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 

Repository files navigation

Claude Agents Kit

A production-ready multi-agent system for Claude Code that orchestrates specialized agents for different development tasks. Optimized for cost, quality, and speed.

What's Included

Agents (8 total)

Agent Model Purpose
architect opus System design, execution plans, architecture decisions
product-manager opus Product strategy, prioritization, growth analysis
frontend sonnet React/Next.js UI development
python-backend sonnet FastAPI/Python backend development
deployment sonnet Railway deployments, cost management
qa haiku CI/CD validation, pre-commit checks
explore-light haiku Fast codebase exploration
ops haiku Server management, QA automation, git operations

Skills (1 total)

Skill Purpose
/explore User-invocable fast codebase exploration

Quick Start

  1. Copy to your project:

    cp -r .claude/ /path/to/your/project/
    cp CLAUDE.md /path/to/your/project/
  2. Customize for your stack (optional):

    • Update ops.md with your project paths
    • Update qa.md with your CI commands
    • Update deployment.md for your deployment platform
  3. Start using agents:

    # In Claude Code, the agents will be automatically available
    # Use Task tool with subagent_type to invoke them
    

Cost Optimization

The system uses a tiered model approach to minimize costs:

┌─────────────────────────────────────────────────────────────┐
│                    MODEL COST TIERS                          │
├─────────────────────────────────────────────────────────────┤
│                                                              │
│  HAIKU (1x baseline) - Use for:                             │
│  • explore-light: File search, code exploration             │
│  • ops: Server management, QA automation, git               │
│  • qa: CI/CD validation                                     │
│                                                              │
│  SONNET (~10x) - Use for:                                   │
│  • frontend: UI implementation                              │
│  • python-backend: API implementation                       │
│  • deployment: Infrastructure management                    │
│                                                              │
│  OPUS (~60x) - Use for:                                     │
│  • architect: Strategic decisions                           │
│  • product-manager: Product strategy                        │
│                                                              │
└─────────────────────────────────────────────────────────────┘

Expected savings: 30-40% vs. using expensive models for all tasks

Multi-Agent Workflow

User Request
    │
    ├──► Product Manager (evaluate UX, define specs)
    │
    ├──► Architect (create execution plan)
    │
    └──► [After plan approved]
         │
         ├──► Frontend Agent ─────┐
         │                        ├──► QA Agent (test everything)
         └──► Backend Agent ──────┘
                                  │
                                  ▼
                          Deployment Agent (deploy)

Agent Highlights

Architect Agent

  • Stage-based design (Early/Growth/Scale)
  • Creates execution plans for other agents
  • Cost optimization framework
  • Architecture Decision Records (ADRs)

Product Manager Agent

Synthesizes methodologies from:

  • Shreyas Doshi (LNO Framework, CPSR)
  • Marty Cagan (Four Risks Framework)
  • Sean Ellis (ICE Prioritization, PMF Test)
  • Gibson Biddle (DHM Model)
  • Julie Zhuo (Product Sense)
  • Brian Balfour (Four Fits Framework)

QA Agent

  • Next.js route conflict detection
  • TypeScript validation
  • Full CI simulation
  • API contract validation

Deployment Agent

  • Railway MCP integration
  • Sleep/wake lifecycle for cost savings
  • PR preview environments
  • Production deployment with approval

Customization

For Different Tech Stacks

The agents are configured for Next.js + FastAPI. To adapt:

  1. frontend.md - Change framework references
  2. python-backend.md - Switch to Django, Flask, Node.js, etc.
  3. ops.md - Update service commands
  4. qa.md - Update CI simulation
  5. deployment.md - Change from Railway to Vercel, AWS, etc.

Adding New Agents

Create .claude/agents/your-agent.md:

---
name: your-agent
description: What this agent does
tools: Read, Edit, Write, Bash, Grep, Glob
model: haiku | sonnet | opus
---

# Your Agent Name

[Instructions for the agent]

File Structure

.claude/
├── agents/
│   ├── architect.md
│   ├── deployment.md
│   ├── explore-light.md
│   ├── frontend.md
│   ├── ops.md
│   ├── product-manager.md
│   ├── python-backend.md
│   └── qa.md
└── skills/
    └── explore.md

CLAUDE.md          # Project standards and workflow documentation
README.md          # This file

License

MIT

Contributing

Contributions welcome! Please submit issues and pull requests.

About

Production-ready multi-agent system for Claude Code with specialized agents for architecture, product management, frontend, backend, QA, deployment, and operations

Resources

Stars

1 star

Watchers

0 watching

Forks

Releases

Packages

Contributors