mirror of
https://github.com/wshobson/agents.git
synced 2026-03-18 09:37:15 +00:00
30 KiB
30 KiB
Claude Code Workflows & Agents
A comprehensive production-ready system combining 83 specialized AI agents, 15 multi-agent workflow orchestrators, and 42 development tools for Claude Code.
Overview
This unified repository provides everything needed for intelligent automation and multi-agent orchestration across modern software development:
- 83 Specialized Agents - Domain experts with deep knowledge (architecture, languages, infrastructure, quality, data/AI, business)
- 15 Workflow Orchestrators - Multi-agent coordination systems for complex operations
- 42 Development Tools - Focused utilities for specific tasks
System Requirements
Architecture & System Design
Core Architecture
| Agent | Model | Description |
|---|---|---|
| backend-architect | opus | RESTful API design, microservice boundaries, database schemas |
| frontend-developer | sonnet | React components, responsive layouts, client-side state management |
| graphql-architect | opus | GraphQL schemas, resolvers, federation architecture |
| architect-reviewer | opus | Architectural consistency analysis and pattern validation |
| cloud-architect | opus | AWS/Azure/GCP infrastructure design and cost optimization |
| hybrid-cloud-architect | opus | Multi-cloud strategies across cloud and on-premises environments |
| kubernetes-architect | opus | Cloud-native infrastructure with Kubernetes and GitOps |
UI/UX & Mobile
| Agent | Model | Description |
|---|---|---|
| ui-ux-designer | sonnet | Interface design, wireframes, design systems |
| ui-visual-validator | sonnet | Visual regression testing and UI verification |
| mobile-developer | sonnet | React Native and Flutter application development |
| ios-developer | sonnet | Native iOS development with Swift/SwiftUI |
| flutter-expert | sonnet | Advanced Flutter development with state management |
Programming Languages
Systems & Low-Level
| Agent | Model | Description |
|---|---|---|
| c-pro | sonnet | System programming with memory management and OS interfaces |
| cpp-pro | sonnet | Modern C++ with RAII, smart pointers, STL algorithms |
| rust-pro | sonnet | Memory-safe systems programming with ownership patterns |
| golang-pro | sonnet | Concurrent programming with goroutines and channels |
Web & Application
| Agent | Model | Description |
|---|---|---|
| javascript-pro | sonnet | Modern JavaScript with ES6+, async patterns, Node.js |
| typescript-pro | sonnet | Advanced TypeScript with type systems and generics |
| python-pro | sonnet | Python development with advanced features and optimization |
| ruby-pro | sonnet | Ruby with metaprogramming, Rails patterns, gem development |
| php-pro | sonnet | Modern PHP with frameworks and performance optimization |
Enterprise & JVM
| Agent | Model | Description |
|---|---|---|
| java-pro | sonnet | Modern Java with streams, concurrency, JVM optimization |
| scala-pro | sonnet | Enterprise Scala with functional programming and distributed systems |
| csharp-pro | sonnet | C# development with .NET frameworks and patterns |
Specialized Platforms
| Agent | Model | Description |
|---|---|---|
| elixir-pro | sonnet | Elixir with OTP patterns and Phoenix frameworks |
| django-pro | sonnet | Django development with ORM and async views |
| fastapi-pro | sonnet | FastAPI with async patterns and Pydantic |
| unity-developer | sonnet | Unity game development and optimization |
| minecraft-bukkit-pro | sonnet | Minecraft server plugin development |
| sql-pro | sonnet | Complex SQL queries and database optimization |
Infrastructure & Operations
DevOps & Deployment
| Agent | Model | Description |
|---|---|---|
| devops-troubleshooter | sonnet | Production debugging, log analysis, deployment troubleshooting |
| deployment-engineer | sonnet | CI/CD pipelines, containerization, cloud deployments |
| terraform-specialist | opus | Infrastructure as Code with Terraform modules and state management |
| dx-optimizer | sonnet | Developer experience optimization and tooling improvements |
Database Management
| Agent | Model | Description |
|---|---|---|
| database-optimizer | opus | Query optimization, index design, migration strategies |
| database-admin | sonnet | Database operations, backup, replication, monitoring |
| database-architect | opus | Database design from scratch, technology selection, schema modeling |
Incident Response & Network
| Agent | Model | Description |
|---|---|---|
| incident-responder | opus | Production incident management and resolution |
| network-engineer | sonnet | Network debugging, load balancing, traffic analysis |
Quality Assurance & Security
Code Quality & Review
| Agent | Model | Description |
|---|---|---|
| code-reviewer | opus | Code review with security focus and production reliability |
| security-auditor | opus | Vulnerability assessment and OWASP compliance |
| backend-security-coder | opus | Secure backend coding practices, API security implementation |
| frontend-security-coder | opus | XSS prevention, CSP implementation, client-side security |
| mobile-security-coder | opus | Mobile security patterns, WebView security, biometric auth |
Testing & Debugging
| Agent | Model | Description |
|---|---|---|
| test-automator | sonnet | Comprehensive test suite creation (unit, integration, e2e) |
| tdd-orchestrator | sonnet | Test-Driven Development methodology guidance |
| debugger | sonnet | Error resolution and test failure analysis |
| error-detective | sonnet | Log analysis and error pattern recognition |
Performance & Observability
| Agent | Model | Description |
|---|---|---|
| performance-engineer | opus | Application profiling and optimization |
| observability-engineer | opus | Production monitoring, distributed tracing, SLI/SLO management |
| search-specialist | haiku | Advanced web research and information synthesis |
Data & AI
Data Engineering & Analytics
| Agent | Model | Description |
|---|---|---|
| data-scientist | opus | Data analysis, SQL queries, BigQuery operations |
| data-engineer | sonnet | ETL pipelines, data warehouses, streaming architectures |
Machine Learning & AI
| Agent | Model | Description |
|---|---|---|
| ai-engineer | opus | LLM applications, RAG systems, prompt pipelines |
| ml-engineer | opus | ML pipelines, model serving, feature engineering |
| mlops-engineer | opus | ML infrastructure, experiment tracking, model registries |
| prompt-engineer | opus | LLM prompt optimization and engineering |
Documentation & Technical Writing
| Agent | Model | Description |
|---|---|---|
| docs-architect | opus | Comprehensive technical documentation generation |
| api-documenter | sonnet | OpenAPI/Swagger specifications and developer docs |
| reference-builder | haiku | Technical references and API documentation |
| tutorial-engineer | sonnet | Step-by-step tutorials and educational content |
| mermaid-expert | sonnet | Diagram creation (flowcharts, sequences, ERDs) |
Business & Operations
Business Analysis & Finance
| Agent | Model | Description |
|---|---|---|
| business-analyst | sonnet | Metrics analysis, reporting, KPI tracking |
| quant-analyst | opus | Financial modeling, trading strategies, market analysis |
| risk-manager | sonnet | Portfolio risk monitoring and management |
Marketing & Sales
| Agent | Model | Description |
|---|---|---|
| content-marketer | sonnet | Blog posts, social media, email campaigns |
| sales-automator | haiku | Cold emails, follow-ups, proposal generation |
Support & Legal
| Agent | Model | Description |
|---|---|---|
| customer-support | sonnet | Support tickets, FAQ responses, customer communication |
| hr-pro | opus | HR operations, policies, employee relations |
| legal-advisor | opus | Privacy policies, terms of service, legal documentation |
Specialized Domains
| Agent | Model | Description |
|---|---|---|
| blockchain-developer | sonnet | Web3 apps, smart contracts, DeFi protocols |
| payment-integration | sonnet | Payment processor integration (Stripe, PayPal) |
| legacy-modernizer | sonnet | Legacy code refactoring and modernization |
| context-manager | haiku | Multi-agent context management |
SEO & Content Optimization
| Agent | Model | Description |
|---|---|---|
| seo-content-auditor | sonnet | Content quality analysis, E-E-A-T signals assessment |
| seo-meta-optimizer | haiku | Meta title and description optimization |
| seo-keyword-strategist | haiku | Keyword analysis and semantic variations |
| seo-structure-architect | haiku | Content structure and schema markup |
| seo-snippet-hunter | haiku | Featured snippet formatting |
| seo-content-refresher | haiku | Content freshness analysis |
| seo-cannibalization-detector | haiku | Keyword overlap detection |
| seo-authority-builder | sonnet | E-E-A-T signal analysis |
| seo-content-writer | sonnet | SEO-optimized content creation |
| seo-content-planner | haiku | Content planning and topic clusters |
Model Configuration
Agents are assigned to specific Claude models based on task complexity and computational requirements. The system uses three model tiers:
Model Distribution Summary
| Model | Agent Count | Use Case |
|---|---|---|
| Haiku | 11 | Quick, focused tasks with minimal computational overhead |
| Sonnet | 50 | Standard development and specialized engineering tasks |
| Opus | 22 | Complex reasoning, architecture, and critical analysis |
Haiku Model Agents
| Category | Agents |
|---|---|
| Context & Reference | context-manager, reference-builder, sales-automator, search-specialist |
| SEO Optimization | seo-meta-optimizer, seo-keyword-strategist, seo-structure-architect, seo-snippet-hunter, seo-content-refresher, seo-cannibalization-detector, seo-content-planner |
Sonnet Model Agents
| Category | Count | Agents |
|---|---|---|
| Programming Languages | 18 | All language-specific agents (JavaScript, Python, Java, C++, etc.) |
| Frontend & UI | 5 | frontend-developer, ui-ux-designer, ui-visual-validator, mobile-developer, ios-developer |
| Infrastructure | 8 | devops-troubleshooter, deployment-engineer, dx-optimizer, database-admin, network-engineer, flutter-expert, api-documenter, tutorial-engineer |
| Quality & Testing | 4 | test-automator, tdd-orchestrator, debugger, error-detective |
| Business & Support | 6 | business-analyst, risk-manager, content-marketer, customer-support, mermaid-expert, legacy-modernizer |
| Data & Content | 5 | data-engineer, payment-integration, seo-content-auditor, seo-authority-builder, seo-content-writer |
Opus Model Agents
| Category | Count | Agents |
|---|---|---|
| Architecture & Design | 7 | architect-reviewer, backend-architect, cloud-architect, hybrid-cloud-architect, kubernetes-architect, graphql-architect, terraform-specialist |
| Critical Analysis | 6 | code-reviewer, security-auditor, performance-engineer, observability-engineer, incident-responder, database-optimizer |
| AI/ML Complex | 5 | ai-engineer, ml-engineer, mlops-engineer, data-scientist, prompt-engineer |
| Business Critical | 4 | docs-architect, hr-pro, legal-advisor, quant-analyst |
Installation
Plugin Marketplace (Recommended - Available October 9, 2025)
Install workflow-based plugin collections directly from the Claude Code plugin marketplace:
# Add the marketplace
/plugin marketplace add wshobson/agents
# Browse available plugins
/plugin list
# Install workflow-based plugins
/plugin install full-stack-development
/plugin install security-hardening
/plugin install data-ml-pipeline
/plugin install incident-response
# Install infrastructure/specialist plugins
/plugin install cloud-infrastructure
/plugin install language-specialists
/plugin install seo-content-suite
Manual Installation
cd ~/.claude
git clone https://github.com/wshobson/agents.git
All agents, workflows, and tools will be automatically available to Claude Code.
Repository Structure
agents/
├── agents/ # 83 specialized AI agents
│ ├── backend-architect.md
│ ├── frontend-developer.md
│ └── ... (all agent definitions)
├── workflows/ # 15 multi-agent orchestrators
│ ├── feature-development.md
│ ├── full-stack-feature.md
│ ├── security-hardening.md
│ └── ... (workflow commands)
├── tools/ # 42 development utilities
│ ├── api-scaffold.md
│ ├── security-scan.md
│ └── ... (tool commands)
└── README.md
Workflow Commands
Multi-agent orchestration systems that coordinate complex, cross-domain tasks:
Core Development Workflows
| Command | Purpose | Agent Coordination |
|---|---|---|
feature-development |
End-to-end feature implementation | Backend, frontend, testing, deployment |
full-stack-feature |
Complete multi-tier implementation | Backend API, frontend UI, mobile, database |
full-review |
Multi-perspective code analysis | Architecture, security, performance, quality |
smart-fix |
Intelligent problem resolution | Dynamic agent selection based on issue type |
tdd-cycle |
Test-driven development orchestration | Test writer, implementer, refactoring specialist |
Process Automation Workflows
| Command | Purpose | Scope |
|---|---|---|
git-workflow |
Version control process automation | Branching strategies, commit standards, PR templates |
improve-agent |
Agent optimization | Prompt engineering, performance tuning |
legacy-modernize |
Codebase modernization | Architecture migration, dependency updates |
multi-platform |
Cross-platform development | Web, mobile, desktop coordination |
workflow-automate |
CI/CD pipeline automation | Build, test, deploy, monitor |
Advanced Orchestration Workflows
| Command | Primary Focus | Specialized Agents |
|---|---|---|
security-hardening |
Security-first development | Threat modeling, vulnerability assessment |
data-driven-feature |
ML-powered functionality | Data science, feature engineering, model deployment |
ml-pipeline |
End-to-end ML infrastructure | MLOps, data engineering, model serving |
performance-optimization |
System-wide optimization | Profiling, caching, query optimization |
incident-response |
Production issue resolution | Diagnostics, root cause analysis, hotfix deployment |
Development Tools
Focused, single-purpose utilities for specific development operations:
AI and Machine Learning
langchain-agent- LangChain agent developmentai-assistant- AI-powered development assistanceai-review- AI-based code review
API Development
api-scaffold- API endpoint scaffoldingapi-mock- API mocking and testing
Testing & Quality
tdd-red- Red phase (failing tests)tdd-green- Green phase (passing implementation)tdd-refactor- Refactor phasetest-harness- Test infrastructure setup
Security & Compliance
security-scan- Vulnerability scanningcompliance-check- Compliance validation
Infrastructure & Operations
k8s-manifest- Kubernetes manifest generationdocker-optimize- Docker optimizationmonitor-setup- Monitoring infrastructuredeploy-checklist- Deployment validation
Code Quality
code-explain- Code explanationcode-migrate- Code migrationrefactor-clean- Code refactoringpr-enhance- Pull request enhancement
And 20+ more tools for debugging, documentation, data validation, cost optimization, and developer workflows
Usage
Workflow Invocation
# Full-stack feature development
/workflows:feature-development implement OAuth2 authentication
# Security hardening
/workflows:security-hardening perform security audit and remediation
# ML pipeline
/workflows:ml-pipeline build recommendation system with monitoring
# Incident response
/workflows:incident-response debug production memory leak
Tool Invocation
# API scaffolding
/tools:api-scaffold create user management endpoints
# Security scanning
/tools:security-scan perform vulnerability assessment
# Documentation generation
/tools:doc-generate create API documentation
Direct Agent Access
Agents are automatically available and can be explicitly invoked:
"Use backend-architect to design the authentication API"
"Have security-auditor scan for OWASP vulnerabilities"
"Get performance-engineer to optimize this bottleneck"
Agent Categories
Architecture & System Design (7 agents)
backend-architect, cloud-architect, kubernetes-architect, hybrid-cloud-architect, graphql-architect, terraform-specialist, architect-review
Programming Languages (15 agents)
javascript-pro, typescript-pro, python-pro, golang-pro, rust-pro, java-pro, csharp-pro, c-pro, cpp-pro, ruby-pro, php-pro, scala-pro, elixir-pro, django-pro, fastapi-pro
Infrastructure & Operations (9 agents)
devops-troubleshooter, deployment-engineer, database-admin, database-optimizer, database-architect, network-engineer, incident-responder, performance-engineer, observability-engineer
Security & Quality (9 agents)
code-reviewer, security-auditor, backend-security-coder, frontend-security-coder, mobile-security-coder, test-automator, tdd-orchestrator, debugger, error-detective
Frontend & Mobile (7 agents)
frontend-developer, ui-ux-designer, ui-visual-validator, mobile-developer, ios-developer, flutter-expert, unity-developer
Data & AI (6 agents)
data-scientist, data-engineer, ml-engineer, mlops-engineer, ai-engineer, prompt-engineer
Documentation (5 agents)
docs-architect, api-documenter, reference-builder, tutorial-engineer, mermaid-expert
Business & Operations (6 agents)
business-analyst, hr-pro, legal-advisor, customer-support, sales-automator, content-marketer
SEO & Content (10 agents)
seo-content-writer, seo-content-auditor, seo-keyword-strategist, seo-meta-optimizer, seo-structure-architect, seo-snippet-hunter, seo-content-refresher, seo-cannibalization-detector, seo-authority-builder, seo-content-planner
Specialized Domains (7 agents)
blockchain-developer, quant-analyst, risk-manager, payment-integration, minecraft-bukkit-pro, legacy-modernizer, context-manager
Utilities (3 agents)
search-specialist, dx-optimizer, sql-pro
Multi-Agent Orchestration Examples
Full-Stack Development
/workflows:full-stack-feature implement user dashboard with analytics
Orchestrates: backend-architect → graphql-architect → frontend-developer → mobile-developer → test-automator → security-auditor → performance-engineer → deployment-engineer
Security Hardening
/workflows:security-hardening implement security best practices
Orchestrates: security-auditor → backend-security-coder → frontend-security-coder → mobile-security-coder → test-automator
Data/ML Pipeline
/workflows:ml-pipeline build customer churn prediction model
Orchestrates: data-scientist → data-engineer → ml-engineer → mlops-engineer → ai-engineer → performance-engineer
Incident Response
/workflows:incident-response debug high CPU usage in production
Orchestrates: incident-responder → devops-troubleshooter → debugger → error-detective → observability-engineer
Model Configuration
Agents are assigned to specific Claude models based on task complexity:
| Model | Count | Use Cases |
|---|---|---|
| Opus | 22 | Complex architecture, critical analysis, security audits, business operations |
| Sonnet | 50 | Standard development, engineering tasks, quality assurance |
| Haiku | 11 | Quick focused tasks, SEO optimization, reference building |
Common Workflow Patterns
Feature Development
"Implement user authentication"
→ backend-architect → frontend-developer → test-automator → security-auditor
Performance Optimization
"Optimize checkout process"
→ performance-engineer → database-optimizer → frontend-developer
Production Incidents
"Debug high memory usage"
→ incident-responder → devops-troubleshooter → error-detective → performance-engineer
Infrastructure Setup
"Set up disaster recovery"
→ database-admin → database-optimizer → terraform-specialist
ML Pipeline Development
"Build ML pipeline with monitoring"
→ mlops-engineer → ml-engineer → data-engineer → performance-engineer
Subagent Format
Each subagent is defined as a Markdown file with frontmatter:
---
name: subagent-name
description: Activation criteria for this subagent
model: haiku|sonnet|opus # Optional: Model selection
tools: tool1, tool2 # Optional: Tool restrictions
---
System prompt defining the subagent's expertise and behavior
Model Selection Criteria
- haiku: Simple, deterministic tasks with minimal reasoning
- sonnet: Standard development and engineering tasks
- opus: Complex analysis, architecture, and critical operations
Agent Orchestration Patterns
Sequential Processing
backend-architect → frontend-developer → test-automator → security-auditor
Parallel Execution
performance-engineer + database-optimizer → Merged optimization
Conditional Routing
debugger → [backend-architect | frontend-developer | devops-troubleshooter]
Validation Pipeline
feature-development → security-auditor → performance-engineer → Validated release
Migration from Commands Repository
Architecture & Planning
| Task | Recommended Agent | Key Capabilities |
|---|---|---|
| API Design | backend-architect |
RESTful APIs, microservices, database schemas |
| Cloud Infrastructure | cloud-architect |
AWS/Azure/GCP design, scalability planning |
| UI/UX Design | ui-ux-designer |
Interface design, wireframes, design systems |
| System Architecture | architect-reviewer |
Pattern validation, consistency analysis |
Development by Language
| Language Category | Agents | Primary Use Cases |
|---|---|---|
| Systems Programming | c-pro, cpp-pro, rust-pro, golang-pro |
OS interfaces, embedded systems, high performance |
| Web Development | javascript-pro, typescript-pro, python-pro, ruby-pro, php-pro |
Full-stack web applications, APIs, scripting |
| Enterprise | java-pro, csharp-pro, scala-pro |
Large-scale applications, enterprise systems |
| Mobile | ios-developer, flutter-expert, mobile-developer |
Native and cross-platform mobile apps |
| Specialized | elixir-pro, django-pro, fastapi-pro, unity-developer, minecraft-bukkit-pro |
Domain-specific development |
Operations & Infrastructure
| Task | Recommended Agent | Key Capabilities |
|---|---|---|
| Production Issues | devops-troubleshooter |
Log analysis, deployment debugging |
| Critical Incidents | incident-responder |
Outage response, immediate mitigation |
| Database Performance | database-optimizer |
Query optimization, indexing strategies |
| Database Operations | database-admin |
Backup, replication, disaster recovery |
| Infrastructure as Code | terraform-specialist |
Terraform modules, state management |
| Network Issues | network-engineer |
Network debugging, load balancing |
Quality & Security
| Task | Recommended Agent | Key Capabilities |
|---|---|---|
| Code Review | code-reviewer |
Security focus, best practices |
| Security Audit | security-auditor |
Vulnerability scanning, OWASP compliance |
| Test Creation | test-automator |
Unit, integration, E2E test suites |
| Performance Issues | performance-engineer |
Profiling, optimization |
| Bug Investigation | debugger |
Error resolution, root cause analysis |
Data & Machine Learning
| Task | Recommended Agent | Key Capabilities |
|---|---|---|
| Data Analysis | data-scientist |
SQL queries, statistical analysis |
| LLM Applications | ai-engineer |
RAG systems, prompt pipelines |
| ML Development | ml-engineer |
Model training, feature engineering |
| ML Operations | mlops-engineer |
ML infrastructure, experiment tracking |
Documentation & Business
| Task | Recommended Agent | Key Capabilities |
|---|---|---|
| Technical Docs | docs-architect |
Comprehensive documentation generation |
| API Documentation | api-documenter |
OpenAPI/Swagger specifications |
| Business Metrics | business-analyst |
KPI tracking, reporting |
| Legal Compliance | legal-advisor |
Privacy policies, terms of service |
Best Practices
Task Delegation
- Automatic selection - Let Claude Code analyze context and select optimal agents
- Clear requirements - Specify constraints, tech stack, and quality standards
- Trust specialization - Each agent is optimized for their specific domain
Multi-Agent Workflows
- High-level requests - Allow agents to coordinate complex multi-step tasks
- Context preservation - Ensure agents have necessary background information
- Integration review - Verify how different agents' outputs work together
Explicit Control
- Direct invocation - Specify agents when you need particular expertise
- Strategic combination - Use multiple specialists for validation
- Review patterns - Request specific review workflows (e.g., "security-auditor reviews API design")
Performance Optimization
- Monitor effectiveness - Track which agents work best for your use cases
- Iterative refinement - Use agent feedback to improve requirements
- Complexity matching - Align task complexity with agent capabilities
Contributing
To add new agents, workflows, or tools:
- Create a new
.mdfile in theagents/directory with appropriate frontmatter - Use lowercase, hyphen-separated naming convention
- Write clear activation criteria in the description
- Define comprehensive system prompt with expertise areas
Troubleshooting
Agent Not Activating
- Ensure request clearly indicates the domain
- Be specific about task type and requirements
- Use explicit invocation if automatic selection fails
Unexpected Agent Selection
- Provide more context about tech stack
- Include specific requirements in request
- Use direct agent naming for precise control
Conflicting Recommendations
- Normal behavior - specialists have different priorities
- Request reconciliation between specific agents
- Consider trade-offs based on project requirements
Missing Context
- Include background information in requests
- Reference previous work or patterns
- Provide project-specific constraints
License
MIT License - see LICENSE file for details.