⚡ Updated for Opus 4.5, Sonnet 4.5 & Haiku 4.5 — Three-tier model strategy for optimal performance
🎯 Agent Skills Enabled — 47 specialized skills extend Claude's capabilities across plugins with progressive disclosure
A comprehensive production-ready system combining 91 specialized AI agents, 15 multi-agent workflow orchestrators, 47 agent skills, and 45 development tools organized into 65 focused, single-purpose plugins for Claude Code.
This unified repository provides everything needed for intelligent automation and multi-agent orchestration across modern software development:
- 65 Focused Plugins - Granular, single-purpose plugins optimized for minimal token usage and composability
- 91 Specialized Agents - Domain experts with deep knowledge across architecture, languages, infrastructure, quality, data/AI, documentation, business operations, and SEO
- 47 Agent Skills - Modular knowledge packages with progressive disclosure for specialized expertise
- 15 Workflow Orchestrators - Multi-agent coordination systems for complex operations like full-stack development, security hardening, ML pipelines, and incident response
- 45 Development Tools - Optimized utilities including project scaffolding, security scanning, test automation, and infrastructure setup
- Granular Plugin Architecture: 65 focused plugins optimized for minimal token usage
- Comprehensive Tooling: 45 development tools including test generation, scaffolding, and security scanning
- 100% Agent Coverage: All plugins include specialized agents
- Agent Skills: 47 specialized skills following for progressive disclosure and token efficiency
- Clear Organization: 23 categories with 1-6 plugins each for easy discovery
- Efficient Design: Average 3.4 components per plugin (follows Anthropic's 2-8 pattern)
Each plugin is completely isolated with its own agents, commands, and skills:
- Install only what you need - Each plugin loads only its specific agents, commands, and skills
- Minimal token usage - No unnecessary resources loaded into context
- Mix and match - Compose multiple plugins for complex workflows
- Clear boundaries - Each plugin has a single, focused purpose
- Progressive disclosure - Skills load knowledge only when activated
Example: Installing python-development loads 3 Python agents, 1 scaffolding tool, and makes 5 skills available (~300 tokens), not the entire marketplace.
Add this marketplace to Claude Code:
/plugin marketplace add wshobson/agentsThis makes all 65 plugins available for installation, but does not load any agents or tools into your context.
Browse available plugins:
/pluginInstall the plugins you need:
# Essential development plugins
/plugin install python-development # Python with 5 specialized skills
/plugin install javascript-typescript # JS/TS with 4 specialized skills
/plugin install backend-development # Backend APIs with 3 architecture skills
# Infrastructure & operations
/plugin install kubernetes-operations # K8s with 4 deployment skills
/plugin install cloud-infrastructure # AWS/Azure/GCP with 4 cloud skills
# Security & quality
/plugin install security-scanning # SAST with security skill
/plugin install code-review-ai # AI-powered code review
# Full-stack orchestration
/plugin install full-stack-orchestration # Multi-agent workflowsEach installed plugin loads only its specific agents, commands, and skills into Claude's context.
- Plugin Reference - Complete catalog of all 65 plugins
- Agent Reference - All 91 agents organized by category
- Agent Skills - 47 specialized skills with progressive disclosure
- Usage Guide - Commands, workflows, and best practices
- Architecture - Design principles and patterns
- Installation - Get started in 2 steps
- Essential Plugins - Top plugins for immediate productivity
- Command Reference - All slash commands organized by category
- Multi-Agent Workflows - Pre-configured orchestration examples
- Model Configuration - Haiku/Sonnet hybrid orchestration
Specialized knowledge packages following Anthropic's progressive disclosure architecture:
Language Development:
- Python (5 skills): async patterns, testing, packaging, performance, UV package manager
- JavaScript/TypeScript (4 skills): advanced types, Node.js patterns, testing, modern ES6+
Infrastructure & DevOps:
- Kubernetes (4 skills): manifests, Helm charts, GitOps, security policies
- Cloud Infrastructure (4 skills): Terraform, multi-cloud, hybrid networking, cost optimization
- CI/CD (4 skills): pipeline design, GitHub Actions, GitLab CI, secrets management
Development & Architecture:
- Backend (3 skills): API design, architecture patterns, microservices
- LLM Applications (4 skills): LangChain, prompt engineering, RAG, evaluation
Blockchain & Web3 (4 skills): DeFi protocols, NFT standards, Solidity security, Web3 testing
And more: Framework migration, observability, payment processing, ML operations, security scanning
→ View complete skills documentation
Strategic model assignment for optimal performance and cost:
| Tier | Model | Agents | Use Case |
|---|---|---|---|
| Tier 1 | Opus 4.5 | 42 | Critical architecture, security, ALL code review, production coding (language pros, frameworks) |
| Tier 2 | Inherit | 42 | Complex tasks - user chooses model (AI/ML, backend, frontend/mobile, specialized) |
| Tier 3 | Sonnet | 51 | Support with intelligence (docs, testing, debugging, network, API docs, DX, legacy, payments) |
| Tier 4 | Haiku | 18 | Fast operational tasks (SEO, deployment, simple docs, sales, content, search) |
Why Opus 4.5 for Critical Agents?
- 80.9% on SWE-bench (industry-leading)
- 65% fewer tokens for complex tasks
- Best for architecture decisions and security audits
Tier 2 Flexibility (inherit):
Agents marked inherit use your session's default model, letting you balance cost and capability:
- Set via
claude --model opusorclaude --model sonnetwhen starting a session - Falls back to Sonnet 4.5 if no default specified
- Perfect for frontend/mobile developers who want cost control
- AI/ML engineers can choose Opus for complex model work
Cost Considerations:
- Opus 4.5: $5/$25 per million input/output tokens - Premium for critical work
- Sonnet 4.5: $3/$15 per million tokens - Balanced performance/cost
- Haiku 4.5: $1/$5 per million tokens - Fast, cost-effective operations
- Opus's 65% token reduction on complex tasks often offsets higher rate
- Use
inherittier to control costs for high-volume use cases
Orchestration patterns combine models for efficiency:
Opus (architecture) → Sonnet (development) → Haiku (deployment)
→ View model configuration details
/full-stack-orchestration:full-stack-feature "user authentication with OAuth2"Coordinates 7+ agents: backend-architect → database-architect → frontend-developer → test-automator → security-auditor → deployment-engineer → observability-engineer
/security-scanning:security-hardening --level comprehensiveMulti-agent security assessment with SAST, dependency scanning, and code review.
/python-development:python-scaffold fastapi-microserviceCreates production-ready FastAPI project with async patterns, activating skills:
async-python-patterns- AsyncIO and concurrencypython-testing-patterns- pytest and fixturesuv-package-manager- Fast dependency management
# Activates k8s skills automatically
"Create production Kubernetes deployment with Helm chart and GitOps"Uses kubernetes-architect agent with 4 specialized skills for production-grade configs.
23 categories, 65 plugins:
- 🎨 Development (4) - debugging, backend, frontend, multi-platform
- 📚 Documentation (3) - code docs, API specs, diagrams, C4 architecture
- 🔄 Workflows (3) - git, full-stack, TDD
- ✅ Testing (2) - unit testing, TDD workflows
- 🔍 Quality (3) - code review, comprehensive review, performance
- 🤖 AI & ML (4) - LLM apps, agent orchestration, context, MLOps
- 📊 Data (2) - data engineering, data validation
- 🗄️ Database (2) - database design, migrations
- 🚨 Operations (4) - incident response, diagnostics, distributed debugging, observability
- ⚡ Performance (2) - application performance, database/cloud optimization
- ☁️ Infrastructure (5) - deployment, validation, Kubernetes, cloud, CI/CD
- 🔒 Security (4) - scanning, compliance, backend/API, frontend/mobile
- 💻 Languages (7) - Python, JS/TS, systems, JVM, scripting, functional, embedded
- 🔗 Blockchain (1) - smart contracts, DeFi, Web3
- 💰 Finance (1) - quantitative trading, risk management
- 💳 Payments (1) - Stripe, PayPal, billing
- 🎮 Gaming (1) - Unity, Minecraft plugins
- 📢 Marketing (4) - SEO content, technical SEO, SEO analysis, content marketing
- 💼 Business (3) - analytics, HR/legal, customer/sales
- And more...
→ View complete plugin catalog
- Single responsibility - Each plugin does one thing well
- Minimal token usage - Average 3.4 components per plugin
- Composable - Mix and match for complex workflows
- 100% coverage - All 91 agents accessible across plugins
Three-tier architecture for token efficiency:
- Metadata - Name and activation criteria (always loaded)
- Instructions - Core guidance (loaded when activated)
- Resources - Examples and templates (loaded on demand)
claude-agents/
├── .claude-plugin/
│ └── marketplace.json # 65 plugins
├── plugins/
│ ├── python-development/
│ │ ├── agents/ # 3 Python experts
│ │ ├── commands/ # Scaffolding tool
│ │ └── skills/ # 5 specialized skills
│ ├── kubernetes-operations/
│ │ ├── agents/ # K8s architect
│ │ ├── commands/ # Deployment tools
│ │ └── skills/ # 4 K8s skills
│ └── ... (63 more plugins)
├── docs/ # Comprehensive documentation
└── README.md # This file
To add new agents, skills, or commands:
- Identify or create the appropriate plugin directory in
plugins/ - Create
.mdfiles in the appropriate subdirectory:agents/- For specialized agentscommands/- For tools and workflowsskills/- For modular knowledge packages
- Follow naming conventions (lowercase, hyphen-separated)
- Write clear activation criteria and comprehensive content
- Update the plugin definition in
.claude-plugin/marketplace.json
See Architecture Documentation for detailed guidelines.
MIT License - see LICENSE file for details.
