{"id":29806274,"url":"https://github.com/wshobson/agents","last_synced_at":"2025-10-31T03:07:37.702Z","repository":{"id":306356903,"uuid":"1025856648","full_name":"wshobson/agents","owner":"wshobson","description":"Intelligent automation and multi-agent orchestration for Claude Code","archived":false,"fork":false,"pushed_at":"2025-10-13T00:06:09.000Z","size":1245,"stargazers_count":17647,"open_issues_count":6,"forks_count":1953,"subscribers_count":198,"default_branch":"main","last_synced_at":"2025-10-13T14:18:21.518Z","etag":null,"topics":["agents","ai","ai-agents","anthropic","anthropic-claude","automation","claude","claude-code","claude-code-cli","claude-code-commands","claude-code-plugin","claude-code-plugins","claude-code-subagents","claudecode","claudecode-config","claudecode-subagents","orchestration","sub-agents","subagents","workflows"],"latest_commit_sha":null,"homepage":"https://sethhobson.com","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/wshobson.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":".github/CONTRIBUTING.md","funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":".github/CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"security-auditor.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null},"funding":{"github":"wshobson"}},"created_at":"2025-07-24T23:28:14.000Z","updated_at":"2025-10-13T14:11:39.000Z","dependencies_parsed_at":"2025-07-25T07:39:30.133Z","dependency_job_id":"5dda9853-9bea-4d2d-b4d5-9f8ad18c318a","html_url":"https://github.com/wshobson/agents","commit_stats":null,"previous_names":["wshobson/agents"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/wshobson/agents","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wshobson%2Fagents","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wshobson%2Fagents/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wshobson%2Fagents/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wshobson%2Fagents/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wshobson","download_url":"https://codeload.github.com/wshobson/agents/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wshobson%2Fagents/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":281920342,"owners_count":26584006,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-31T02:00:07.401Z","response_time":57,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agents","ai","ai-agents","anthropic","anthropic-claude","automation","claude","claude-code","claude-code-cli","claude-code-commands","claude-code-plugin","claude-code-plugins","claude-code-subagents","claudecode","claudecode-config","claudecode-subagents","orchestration","sub-agents","subagents","workflows"],"created_at":"2025-07-28T14:05:55.829Z","updated_at":"2025-10-31T03:07:37.696Z","avatar_url":"https://github.com/wshobson.png","language":null,"readme":"# Claude Code Plugins: Orchestration and Automation\n\n\u003e **⚡ Updated for Sonnet 4.5 \u0026 Haiku 4.5** — All agents optimized for latest models with hybrid orchestration\n\u003e\n\u003e **🎯 Agent Skills Enabled** — 47 specialized skills extend Claude's capabilities across plugins with progressive disclosure\n\nA comprehensive production-ready system combining **85 specialized AI agents**, **15 multi-agent workflow orchestrators**, **47 agent skills**, and **44 development tools** organized into **63 focused, single-purpose plugins** for [Claude Code](https://docs.claude.com/en/docs/claude-code/overview).\n\n## Overview\n\nThis unified repository provides everything needed for intelligent automation and multi-agent orchestration across modern software development:\n\n- **63 Focused Plugins** - Granular, single-purpose plugins optimized for minimal token usage and composability\n- **85 Specialized Agents** - Domain experts with deep knowledge across architecture, languages, infrastructure, quality, data/AI, documentation, business operations, and SEO\n- **47 Agent Skills** - Modular knowledge packages with progressive disclosure for specialized expertise\n- **15 Workflow Orchestrators** - Multi-agent coordination systems for complex operations like full-stack development, security hardening, ML pipelines, and incident response\n- **44 Development Tools** - Optimized utilities including project scaffolding, security scanning, test automation, and infrastructure setup\n\n### Key Features\n\n- **Granular Plugin Architecture**: 63 focused plugins optimized for minimal token usage\n- **Comprehensive Tooling**: 44 development tools including test generation, scaffolding, and security scanning\n- **100% Agent Coverage**: All plugins include specialized agents\n- **Agent Skills**: 47 specialized skills following for progressive disclosure and token efficiency\n- **Clear Organization**: 23 categories with 1-6 plugins each for easy discovery\n- **Efficient Design**: Average 3.4 components per plugin (follows Anthropic's 2-8 pattern)\n\n### How It Works\n\nEach plugin is completely isolated with its own agents, commands, and skills:\n\n- **Install only what you need** - Each plugin loads only its specific agents, commands, and skills\n- **Minimal token usage** - No unnecessary resources loaded into context\n- **Mix and match** - Compose multiple plugins for complex workflows\n- **Clear boundaries** - Each plugin has a single, focused purpose\n- **Progressive disclosure** - Skills load knowledge only when activated\n\n**Example**: Installing `python-development` loads 3 Python agents, 1 scaffolding tool, and makes 5 skills available (~300 tokens), not the entire marketplace.\n\n## Quick Start\n\n### Step 1: Add the Marketplace\n\nAdd this marketplace to Claude Code:\n\n```bash\n/plugin marketplace add wshobson/agents\n```\n\nThis makes all 63 plugins available for installation, but **does not load any agents or tools** into your context.\n\n### Step 2: Install Plugins\n\nBrowse available plugins:\n\n```bash\n/plugin\n```\n\nInstall the plugins you need:\n\n```bash\n# Essential development plugins\n/plugin install python-development          # Python with 5 specialized skills\n/plugin install javascript-typescript       # JS/TS with 4 specialized skills\n/plugin install backend-development         # Backend APIs with 3 architecture skills\n\n# Infrastructure \u0026 operations\n/plugin install kubernetes-operations       # K8s with 4 deployment skills\n/plugin install cloud-infrastructure        # AWS/Azure/GCP with 4 cloud skills\n\n# Security \u0026 quality\n/plugin install security-scanning           # SAST with security skill\n/plugin install code-review-ai             # AI-powered code review\n\n# Full-stack orchestration\n/plugin install full-stack-orchestration   # Multi-agent workflows\n```\n\nEach installed plugin loads **only its specific agents, commands, and skills** into Claude's context.\n\n## Documentation\n\n### Core Guides\n\n- **[Plugin Reference](docs/plugins.md)** - Complete catalog of all 63 plugins\n- **[Agent Reference](docs/agents.md)** - All 85 agents organized by category\n- **[Agent Skills](docs/agent-skills.md)** - 47 specialized skills with progressive disclosure\n- **[Usage Guide](docs/usage.md)** - Commands, workflows, and best practices\n- **[Architecture](docs/architecture.md)** - Design principles and patterns\n\n### Quick Links\n\n- [Installation](#quick-start) - Get started in 2 steps\n- [Essential Plugins](docs/plugins.md#quick-start---essential-plugins) - Top plugins for immediate productivity\n- [Command Reference](docs/usage.md#command-reference-by-category) - All slash commands organized by category\n- [Multi-Agent Workflows](docs/usage.md#multi-agent-workflow-examples) - Pre-configured orchestration examples\n- [Model Configuration](docs/agents.md#model-configuration) - Haiku/Sonnet hybrid orchestration\n\n## What's New\n\n### Agent Skills (47 skills across 14 plugins)\n\nSpecialized knowledge packages following Anthropic's progressive disclosure architecture:\n\n**Language Development:**\n- **Python** (5 skills): async patterns, testing, packaging, performance, UV package manager\n- **JavaScript/TypeScript** (4 skills): advanced types, Node.js patterns, testing, modern ES6+\n\n**Infrastructure \u0026 DevOps:**\n- **Kubernetes** (4 skills): manifests, Helm charts, GitOps, security policies\n- **Cloud Infrastructure** (4 skills): Terraform, multi-cloud, hybrid networking, cost optimization\n- **CI/CD** (4 skills): pipeline design, GitHub Actions, GitLab CI, secrets management\n\n**Development \u0026 Architecture:**\n- **Backend** (3 skills): API design, architecture patterns, microservices\n- **LLM Applications** (4 skills): LangChain, prompt engineering, RAG, evaluation\n\n**Blockchain \u0026 Web3** (4 skills): DeFi protocols, NFT standards, Solidity security, Web3 testing\n\n**And more:** Framework migration, observability, payment processing, ML operations, security scanning\n\n[→ View complete skills documentation](docs/agent-skills.md)\n\n### Hybrid Model Orchestration\n\nStrategic model assignment for optimal performance and cost:\n- **47 Haiku agents** - Fast execution for deterministic tasks\n- **97 Sonnet agents** - Complex reasoning and architecture\n\nOrchestration patterns combine models for efficiency:\n```\nSonnet (planning) → Haiku (execution) → Sonnet (review)\n```\n\n[→ View model configuration details](docs/agents.md#model-configuration)\n\n## Popular Use Cases\n\n### Full-Stack Feature Development\n\n```bash\n/full-stack-orchestration:full-stack-feature \"user authentication with OAuth2\"\n```\n\nCoordinates 7+ agents: backend-architect → database-architect → frontend-developer → test-automator → security-auditor → deployment-engineer → observability-engineer\n\n[→ View all workflow examples](docs/usage.md#multi-agent-workflow-examples)\n\n### Security Hardening\n\n```bash\n/security-scanning:security-hardening --level comprehensive\n```\n\nMulti-agent security assessment with SAST, dependency scanning, and code review.\n\n### Python Development with Modern Tools\n\n```bash\n/python-development:python-scaffold fastapi-microservice\n```\n\nCreates production-ready FastAPI project with async patterns, activating skills:\n- `async-python-patterns` - AsyncIO and concurrency\n- `python-testing-patterns` - pytest and fixtures\n- `uv-package-manager` - Fast dependency management\n\n### Kubernetes Deployment\n\n```bash\n# Activates k8s skills automatically\n\"Create production Kubernetes deployment with Helm chart and GitOps\"\n```\n\nUses kubernetes-architect agent with 4 specialized skills for production-grade configs.\n\n[→ View complete usage guide](docs/usage.md)\n\n## Plugin Categories\n\n**23 categories, 63 plugins:**\n\n- 🎨 **Development** (4) - debugging, backend, frontend, multi-platform\n- 📚 **Documentation** (2) - code docs, API specs, diagrams\n- 🔄 **Workflows** (3) - git, full-stack, TDD\n- ✅ **Testing** (2) - unit testing, TDD workflows\n- 🔍 **Quality** (3) - code review, comprehensive review, performance\n- 🤖 **AI \u0026 ML** (4) - LLM apps, agent orchestration, context, MLOps\n- 📊 **Data** (2) - data engineering, data validation\n- 🗄️ **Database** (2) - database design, migrations\n- 🚨 **Operations** (4) - incident response, diagnostics, distributed debugging, observability\n- ⚡ **Performance** (2) - application performance, database/cloud optimization\n- ☁️ **Infrastructure** (5) - deployment, validation, Kubernetes, cloud, CI/CD\n- 🔒 **Security** (4) - scanning, compliance, backend/API, frontend/mobile\n- 💻 **Languages** (7) - Python, JS/TS, systems, JVM, scripting, functional, embedded\n- 🔗 **Blockchain** (1) - smart contracts, DeFi, Web3\n- 💰 **Finance** (1) - quantitative trading, risk management\n- 💳 **Payments** (1) - Stripe, PayPal, billing\n- 🎮 **Gaming** (1) - Unity, Minecraft plugins\n- 📢 **Marketing** (4) - SEO content, technical SEO, SEO analysis, content marketing\n- 💼 **Business** (3) - analytics, HR/legal, customer/sales\n- And more...\n\n[→ View complete plugin catalog](docs/plugins.md)\n\n## Architecture Highlights\n\n### Granular Design\n\n- **Single responsibility** - Each plugin does one thing well\n- **Minimal token usage** - Average 3.4 components per plugin\n- **Composable** - Mix and match for complex workflows\n- **100% coverage** - All 85 agents accessible across plugins\n\n### Progressive Disclosure (Skills)\n\nThree-tier architecture for token efficiency:\n1. **Metadata** - Name and activation criteria (always loaded)\n2. **Instructions** - Core guidance (loaded when activated)\n3. **Resources** - Examples and templates (loaded on demand)\n\n### Repository Structure\n\n```\nclaude-agents/\n├── .claude-plugin/\n│   └── marketplace.json          # 63 plugins\n├── plugins/\n│   ├── python-development/\n│   │   ├── agents/               # 3 Python experts\n│   │   ├── commands/             # Scaffolding tool\n│   │   └── skills/               # 5 specialized skills\n│   ├── kubernetes-operations/\n│   │   ├── agents/               # K8s architect\n│   │   ├── commands/             # Deployment tools\n│   │   └── skills/               # 4 K8s skills\n│   └── ... (61 more plugins)\n├── docs/                          # Comprehensive documentation\n└── README.md                      # This file\n```\n\n[→ View architecture details](docs/architecture.md)\n\n## Contributing\n\nTo add new agents, skills, or commands:\n\n1. Identify or create the appropriate plugin directory in `plugins/`\n2. Create `.md` files in the appropriate subdirectory:\n   - `agents/` - For specialized agents\n   - `commands/` - For tools and workflows\n   - `skills/` - For modular knowledge packages\n3. Follow naming conventions (lowercase, hyphen-separated)\n4. Write clear activation criteria and comprehensive content\n5. Update the plugin definition in `.claude-plugin/marketplace.json`\n\nSee [Architecture Documentation](docs/architecture.md) for detailed guidelines.\n\n## Resources\n\n### Documentation\n- [Claude Code Documentation](https://docs.claude.com/en/docs/claude-code/overview)\n- [Plugins Guide](https://docs.claude.com/en/docs/claude-code/plugins)\n- [Subagents Guide](https://docs.claude.com/en/docs/claude-code/sub-agents)\n- [Agent Skills Guide](https://docs.claude.com/en/docs/agents-and-tools/agent-skills/overview)\n- [Slash Commands Reference](https://docs.claude.com/en/docs/claude-code/slash-commands)\n\n### This Repository\n- [Plugin Reference](docs/plugins.md)\n- [Agent Reference](docs/agents.md)\n- [Agent Skills Guide](docs/agent-skills.md)\n- [Usage Guide](docs/usage.md)\n- [Architecture](docs/architecture.md)\n\n## License\n\nMIT License - see [LICENSE](LICENSE) file for details.\n\n## Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=wshobson/agents\u0026type=date\u0026legend=top-left)](https://www.star-history.com/#wshobson/agents\u0026type=date\u0026legend=top-left)\n","funding_links":["https://github.com/sponsors/wshobson"],"categories":["Skills Catalog","Python","HarmonyOS","Awesome","Agent Collections","Claude Code Ecosystem","🔹 Claude Code Subagents","A01_文本生成_文本对话","Sub Agents","🆕 Latest \u0026 Featured Agent Collections (August 2025)","Repos","框架扩展","ai-ml","Agent Orchestration","Frameworks \u0026 Libraries","Personal Assistants \u0026 Conversational Agents","Comprehensive Skill Collections","🤖 Multi-Agent Orchestration \u0026 Collaboration","Subagents","Plugins"],"sub_categories":["Frontend (24)","Windows Manager","Production-Ready Collections","Agent Collections \u0026 Orchestration","大语言对话模型及数据","**Production-Ready Agent Collections**","Copilot Extensions \u0026 Alternatives","Chatbots","What are Claude Skills?","All Plugins"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwshobson%2Fagents","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwshobson%2Fagents","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwshobson%2Fagents/lists"}