How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

README - Prompt - OpenSmartRoute

Name: README
Author: pc-style

Prompt file imported from pc-style/MCF (.claude/commands/agent/README.md). Copyright stays with the author.

Multi-Agent Development Commands

This directory contains comprehensive agent-based development commands that leverage specialized AI agents for maximum efficiency and quality.

🚀 Available Commands

Core Development Commands

Command	Description	Use Case
`/agent:feature`	Multi-agent feature development from concept to implementation	Complete feature development with comprehensive analysis
`/agent:generate-ag`	Generate project-specific agents tailored to current codebase	Create specialized agents for your specific project needs
`/agent:brainstorm`	Collaborative ideation with multiple specialized agents	Generate innovative ideas and improvement opportunities
`/agent:redesign`	System redesign with modern architecture patterns	Architecture and component redesign with best practices
`/agent:debug`	Comprehensive debugging with multi-agent analysis	Complex issue resolution and root cause analysis
`/agent:optimize`	System optimization across multiple dimensions	Performance, security, and architecture optimization
`/agent:audit`	Comprehensive system auditing and compliance	Security, quality, performance, and compliance audits
`/agent:test`	Comprehensive testing strategy and implementation	Test design, implementation, and execution
`/agent:deploy`	Deployment pipeline design and CI/CD implementation	Infrastructure and deployment automation
`/agent:auto`	🚀 Fully automatic development team	Complete projects from concept to deployment
`/agent:help`	Complete guide to all agent commands	Documentation and usage examples

🧠 Agent Specializations

Core Analysis Agents

micro-analyzer: Lightweight code analysis with semantic understanding
semantic-navigator: Pure semantic code exploration and navigation
micro-researcher: Quick documentation and research tasks

Specialized Development Agents

api-designer: RESTful/GraphQL API design and implementation
perf-optimizer: Performance analysis and optimization
security-auditor: Security analysis and vulnerability detection
devops-engineer: Infrastructure, deployment, and automation

Utility Agents

micro-executor: Focused implementation tasks
docs-researcher: Comprehensive documentation research

⚡ Key Benefits

Efficiency Gains

50-70% token savings through context isolation
Parallel execution of specialized tasks
Focused expertise for higher quality results
Minimal context switching between different domains

Quality Improvements

Multi-perspective analysis from different specialists
Comprehensive coverage of all development aspects
Best practices integration from specialized knowledge
Risk mitigation through expert validation

Development Workflow

Structured approach to complex development tasks
Consistent methodology across different project types
Documentation generation as part of the process
Testing and validation built into workflows

🔄 Workflow Patterns

Feature Development Flow

Analysis → micro-analyzer + semantic-navigator
Design → api-designer + security-auditor
Implementation → micro-executor + perf-optimizer
Validation → security-auditor + micro-analyzer

Debugging Flow

Issue Analysis → micro-analyzer + semantic-navigator
Root Cause → perf-optimizer + security-auditor
Solution → micro-executor + api-designer
Validation → security-auditor + micro-analyzer

Optimization Flow

Baseline → perf-optimizer + micro-analyzer
Analysis → semantic-navigator + security-auditor
Implementation → micro-executor + devops-engineer
Validation → perf-optimizer + micro-analyzer

💡 Usage Examples

Feature Development

/agent:feature "user authentication system with OAuth2 and JWT tokens"
/agent:feature "real-time chat functionality with WebSocket support"
/agent:feature "admin dashboard with user management and analytics"

System Redesign

/agent:redesign "authentication system"
/agent:redesign "data persistence layer"
/agent:redesign "API gateway architecture"

Performance Optimization

/agent:optimize "database query performance"
/agent:optimize "frontend rendering speed"
/agent:optimize "API response times"

Comprehensive Auditing

/agent:audit "security vulnerabilities"
/agent:audit "performance bottlenecks"
/agent:audit "code quality and maintainability"

Fully Automatic Development

/agent:auto "build a complete e-commerce platform with user authentication and payment processing"
/agent:auto "implement a real-time chat system with WebSocket support and encryption"
/agent:auto "redesign our entire authentication system with OAuth2 and MFA"

🎯 Integration with MCF

Serena Integration

Use with /serena:overview for codebase understanding
Combine with /serena:find for symbol-level analysis
Integrate with /serena:analyze for detailed component analysis

Context Management

Use with /context:agent for complex multi-step tasks
Combine with /context:purge for efficient context management
Integrate with /context:bookmark for state preservation

Project Management

Use with /project:review for quality validation
Combine with /project:security for security assessment
Integrate with /project:deploy for deployment management

🚀 Getting Started

Quick Start

Try a simple feature: /agent:feature "simple user profile page"
Generate a project agent: /agent:generate-ag "testing specialist"
Brainstorm improvements: /agent:brainstorm "user experience"

Advanced Usage

Complex redesign: /agent:redesign "entire authentication system"
Performance audit: /agent:audit "full system performance"
Custom optimization: /agent:optimize "database and API layer"

Help and Documentation

Use /agent:help for comprehensive command guide
Check individual command files for detailed specifications
Monitor agent performance and adjust combinations as needed

📊 Monitoring & Analytics

Agent Performance

Track token usage and efficiency gains
Monitor agent combination effectiveness
Analyze development velocity improvements
Measure quality and security enhancements

Usage Patterns

Identify most valuable agent combinations
Optimize command usage for your workflow
Track development task completion rates
Measure time savings and quality improvements

🔧 Technical Details

Command Structure

All agent commands follow the pattern: /agent:<command> [arguments]

Agent Selection

Commands automatically select the most appropriate agent combinations based on the task type and requirements.

Context Management

Each agent operates with isolated context to maximize efficiency and minimize token usage.

Integration Points

All commands integrate seamlessly with existing MCF tools and Serena semantic analysis capabilities.

Your multi-agent development system is ready to supercharge your development workflow! 🎯

For more information, use /agent:help or check individual command documentation.

Install README and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

# Multi-Agent Development Commands This directory contains comprehensive agent-based development commands that leverage specialized AI agents for maximum efficiency and quality. ## 🚀 Available Commands ### **Core Development Commands** | Command | Description | Use Case | |---------|-------------|----------| | `/agent:feature` | Multi-agent feature development from concept to implementation | Complete feature development with comprehensive analysis | | `/agent:generate-ag` | Generate project-specific agents tailored to current codebase | Create specialized agents for your specific project needs | | `/agent:brainstorm` | Collaborative ideation with multiple specialized agents | Generate innovative ideas and improvement opportunities | | `/agent:redesign` | System redesign with modern architecture patterns | Architecture and component redesign with best practices | | `/agent:debug` | Comprehensive debugging with multi-agent analysis | Complex issue resolution and root cause analysis | | `/agent:optimize` | System optimization across multiple dimensions | Performance, security, and architecture optimization | | `/agent:audit` | Comprehensive system auditing and compliance | Security, quality, performance, and compliance audits | | `/agent:test` | Comprehensive testing strategy and implementation | Test design, implementation, and execution | | `/agent:deploy` | Deployment pipeline design and CI/CD implementation | Infrastructure and deployment automation | | `/agent:auto` | **🚀 Fully automatic development team** | Complete projects from concept to deployment | | `/agent:help` | Complete guide to all agent commands | Documentation and usage examples | ## 🧠 Agent Specializations ### **Core Analysis Agents** - **micro-analyzer**: Lightweight code analysis with semantic understanding - **semantic-navigator**: Pure semantic code exploration and navigation - **micro-researcher**: Quick documentation and research tasks ### **Specialized Development Agents** - **api-designer**: RESTful/GraphQL API design and implementation - **perf-optimizer**: Performance analysis and optimization - **security-auditor**: Security analysis and vulnerability detection - **devops-engineer**: Infrastructure, deployment, and automation ### **Utility Agents** - **micro-executor**: Focused implementation tasks - **docs-researcher**: Comprehensive documentation research ## ⚡ Key Benefits ### **Efficiency Gains** - **50-70% token savings** through context isolation - **Parallel execution** of specialized tasks - **Focused expertise** for higher quality results - **Minimal context switching** between different domains ### **Quality Improvements** - **Multi-perspective analysis** from different specialists - **Comprehensive coverage** of all development aspects - **Best practices integration** from specialized knowledge - **Risk mitigation** through expert validation ### **Development Workflow** - **Structured approach** to complex development tasks - **Consistent methodology** across different project types - **Documentation generation** as part of the process - **Testing and validation** built into workflows ## 🔄 Workflow Patterns ### **Feature Development Flow** 1. **Analysis** → micro-analyzer + semantic-navigator 2. **Design** → api-designer + security-auditor 3. **Implementation** → micro-executor + perf-optimizer 4. **Validation** → security-auditor + micro-analyzer ### **Debugging Flow** 1. **Issue Analysis** → micro-analyzer + semantic-navigator 2. **Root Cause** → perf-optimizer + security-auditor 3. **Solution** → micro-executor + api-designer 4. **Validation** → security-auditor + micro-analyzer ### **Optimization Flow** 1. **Baseline** → perf-optimizer + micro-analyzer 2. **Analysis** → semantic-navigator + security-auditor 3. **Implementation** → micro-executor + devops-engineer 4. **Validation** → perf-optimizer + micro-analyzer ## 💡 Usage Examples ### **Feature Development** ```bash /agent:feature "user authentication system with OAuth2 and JWT tokens" /agent:feature "real-time chat functionality with WebSocket support" /agent:feature "admin dashboard with user management and analytics" ``` ### **System Redesign** ```bash /agent:redesign "authentication system" /agent:redesign "data persistence layer" /agent:redesign "API gateway architecture" ``` ### **Performance Optimization** ```bash /agent:optimize "database query performance" /agent:optimize "frontend rendering speed" /agent:optimize "API response times" ``` ### **Comprehensive Auditing** ```bash /agent:audit "security vulnerabilities" /agent:audit "performance bottlenecks" /agent:audit "code quality and maintainability" ``` ### **Fully Automatic Development** ```bash /agent:auto "build a complete e-commerce platform with user authentication and payment processing" /agent:auto "implement a real-time chat system with WebSocket support and encryption" /agent:auto "redesign our entire authentication system with OAuth2 and MFA" ``` ## 🎯 Integration with MCF ### **Serena Integration** - Use with `/serena:overview` for codebase understanding - Combine with `/serena:find` for symbol-level analysis - Integrate with `/serena:analyze` for detailed component analysis ### **Context Management** - Use with `/context:agent` for complex multi-step tasks - Combine with `/context:purge` for efficient context management - Integrate with `/context:bookmark` for state preservation ### **Project Management** - Use with `/project:review` for quality validation - Combine with `/project:security` for security assessment - Integrate with `/project:deploy` for deployment management ## 🚀 Getting Started ### **Quick Start** 1. **Try a simple feature**: `/agent:feature "simple user profile page"` 2. **Generate a project agent**: `/agent:generate-ag "testing specialist"` 3. **Brainstorm improvements**: `/agent:brainstorm "user experience"` ### **Advanced Usage** 1. **Complex redesign**: `/agent:redesign "entire authentication system"` 2. **Performance audit**: `/agent:audit "full system performance"` 3. **Custom optimization**: `/agent:optimize "database and API layer"` ### **Help and Documentation** - Use `/agent:help` for comprehensive command guide - Check individual command files for detailed specifications - Monitor agent performance and adjust combinations as needed ## 📊 Monitoring & Analytics ### **Agent Performance** - Track token usage and efficiency gains - Monitor agent combination effectiveness - Analyze development velocity improvements - Measure quality and security enhancements ### **Usage Patterns** - Identify most valuable agent combinations - Optimize command usage for your workflow - Track development task completion rates - Measure time savings and quality improvements ## 🔧 Technical Details ### **Command Structure** All agent commands follow the pattern: `/agent:<command> [arguments]` ### **Agent Selection** Commands automatically select the most appropriate agent combinations based on the task type and requirements. ### **Context Management** Each agent operates with isolated context to maximize efficiency and minimize token usage. ### **Integration Points** All commands integrate seamlessly with existing MCF tools and Serena semantic analysis capabilities. --- **Your multi-agent development system is ready to supercharge your development workflow!** 🎯 For more information, use `/agent:help` or check individual command documentation.

{ "prompt": "# Multi-Agent Development Commands\n\nThis directory contains comprehensive agent-based development commands that leverage specialized AI agents for maximum efficiency and quality.\n\n## 🚀 Available Commands\n\n### **Core Development Commands**\n\n| Command | Description | Use Case |\n|---------|-------------|----------|\n| `/agent:feature` | Multi-agent feature development from concept to implementation | Complete feature development with comprehensive analysis |\n| `/agent:generate-ag` | Generate project-specific agents tailored to current codebase | Create specialized agents for your specific project needs |\n| `/agent:brainstorm` | Collaborative ideation with multiple specialized agents | Generate innovative ideas and improvement opportunities |\n| `/agent:redesign` | System redesign with modern architecture patterns | Architecture and component redesign with best practices |\n| `/agent:debug` | Comprehensive debugging with multi-agent analysis | Complex issue resolution and root cause analysis |\n| `/agent:optimize` | System optimization across multiple dimensions | Performance, security, and architecture optimization |\n| `/agent:audit` | Comprehensive system auditing and compliance | Security, quality, performance, and compliance audits |\n| `/agent:test` | Comprehensive testing strategy and implementation | Test design, implementation, and execution |\n| `/agent:deploy` | Deployment pipeline design and CI/CD implementation | Infrastructure and deployment automation |\n| `/agent:auto` | **🚀 Fully automatic development team** | Complete projects from concept to deployment |\n| `/agent:help` | Complete guide to all agent commands | Documentation and usage examples |\n\n## 🧠 Agent Specializations\n\n### **Core Analysis Agents**\n- **micro-analyzer**: Lightweight code analysis with semantic understanding\n- **semantic-navigator**: Pure semantic code exploration and navigation\n- **micro-researcher**: Quick documentation and research tasks\n\n### **Specialized Development Agents**\n- **api-designer**: RESTful/GraphQL API design and implementation\n- **perf-optimizer**: Performance analysis and optimization\n- **security-auditor**: Security analysis and vulnerability detection\n- **devops-engineer**: Infrastructure, deployment, and automation\n\n### **Utility Agents**\n- **micro-executor**: Focused implementation tasks\n- **docs-researcher**: Comprehensive documentation research\n\n## ⚡ Key Benefits\n\n### **Efficiency Gains**\n- **50-70% token savings** through context isolation\n- **Parallel execution** of specialized tasks\n- **Focused expertise** for higher quality results\n- **Minimal context switching** between different domains\n\n### **Quality Improvements**\n- **Multi-perspective analysis** from different specialists\n- **Comprehensive coverage** of all development aspects\n- **Best practices integration** from specialized knowledge\n- **Risk mitigation** through expert validation\n\n### **Development Workflow**\n- **Structured approach** to complex development tasks\n- **Consistent methodology** across different project types\n- **Documentation generation** as part of the process\n- **Testing and validation** built into workflows\n\n## 🔄 Workflow Patterns\n\n### **Feature Development Flow**\n1. **Analysis** → micro-analyzer + semantic-navigator\n2. **Design** → api-designer + security-auditor\n3. **Implementation** → micro-executor + perf-optimizer\n4. **Validation** → security-auditor + micro-analyzer\n\n### **Debugging Flow**\n1. **Issue Analysis** → micro-analyzer + semantic-navigator\n2. **Root Cause** → perf-optimizer + security-auditor\n3. **Solution** → micro-executor + api-designer\n4. **Validation** → security-auditor + micro-analyzer\n\n### **Optimization Flow**\n1. **Baseline** → perf-optimizer + micro-analyzer\n2. **Analysis** → semantic-navigator + security-auditor\n3. **Implementation** → micro-executor + devops-engineer\n4. **Validation** → perf-optimizer + micro-analyzer\n\n## 💡 Usage Examples\n\n### **Feature Development**\n```bash\n/agent:feature \"user authentication system with OAuth2 and JWT tokens\"\n/agent:feature \"real-time chat functionality with WebSocket support\"\n/agent:feature \"admin dashboard with user management and analytics\"\n```\n\n### **System Redesign**\n```bash\n/agent:redesign \"authentication system\"\n/agent:redesign \"data persistence layer\"\n/agent:redesign \"API gateway architecture\"\n```\n\n### **Performance Optimization**\n```bash\n/agent:optimize \"database query performance\"\n/agent:optimize \"frontend rendering speed\"\n/agent:optimize \"API response times\"\n```\n\n### **Comprehensive Auditing**\n```bash\n/agent:audit \"security vulnerabilities\"\n/agent:audit \"performance bottlenecks\"\n/agent:audit \"code quality and maintainability\"\n```\n\n### **Fully Automatic Development**\n```bash\n/agent:auto \"build a complete e-commerce platform with user authentication and payment processing\"\n/agent:auto \"implement a real-time chat system with WebSocket support and encryption\"\n/agent:auto \"redesign our entire authentication system with OAuth2 and MFA\"\n```\n\n## 🎯 Integration with MCF\n\n### **Serena Integration**\n- Use with `/serena:overview` for codebase understanding\n- Combine with `/serena:find` for symbol-level analysis\n- Integrate with `/serena:analyze` for detailed component analysis\n\n### **Context Management**\n- Use with `/context:agent` for complex multi-step tasks\n- Combine with `/context:purge` for efficient context management\n- Integrate with `/context:bookmark` for state preservation\n\n### **Project Management**\n- Use with `/project:review` for quality validation\n- Combine with `/project:security` for security assessment\n- Integrate with `/project:deploy` for deployment management\n\n## 🚀 Getting Started\n\n### **Quick Start**\n1. **Try a simple feature**: `/agent:feature \"simple user profile page\"`\n2. **Generate a project agent**: `/agent:generate-ag \"testing specialist\"`\n3. **Brainstorm improvements**: `/agent:brainstorm \"user experience\"`\n\n### **Advanced Usage**\n1. **Complex redesign**: `/agent:redesign \"entire authentication system\"`\n2. **Performance audit**: `/agent:audit \"full system performance\"`\n3. **Custom optimization**: `/agent:optimize \"database and API layer\"`\n\n### **Help and Documentation**\n- Use `/agent:help` for comprehensive command guide\n- Check individual command files for detailed specifications\n- Monitor agent performance and adjust combinations as needed\n\n## 📊 Monitoring & Analytics\n\n### **Agent Performance**\n- Track token usage and efficiency gains\n- Monitor agent combination effectiveness\n- Analyze development velocity improvements\n- Measure quality and security enhancements\n\n### **Usage Patterns**\n- Identify most valuable agent combinations\n- Optimize command usage for your workflow\n- Track development task completion rates\n- Measure time savings and quality improvements\n\n## 🔧 Technical Details\n\n### **Command Structure**\nAll agent commands follow the pattern: `/agent:<command> [arguments]`\n\n### **Agent Selection**\nCommands automatically select the most appropriate agent combinations based on the task type and requirements.\n\n### **Context Management**\nEach agent operates with isolated context to maximize efficiency and minimize token usage.\n\n### **Integration Points**\nAll commands integrate seamlessly with existing MCF tools and Serena semantic analysis capabilities.\n\n---\n\n**Your multi-agent development system is ready to supercharge your development workflow!** 🎯\n\nFor more information, use `/agent:help` or check individual command documentation.", "variables": [], "notes": "This directory contains comprehensive agent-based development commands that leverage specialized AI agents for maximum efficiency and quality.", "metadata": { "source": { "provider": "github-claude-commands", "repository": "https://github.com/pc-style/MCF", "path": ".claude/commands/agent/README.md", "ref": "f1a55359ba6dd208c4b08f60d3c3ffe1abd96f92", "url": "https://github.com/pc-style/MCF/blob/f1a55359ba6dd208c4b08f60d3c3ffe1abd96f92/.claude/commands/agent/README.md", "key": "pc-style/MCF/.claude/commands/agent/README.md" } } }

About

Multi-Agent Development Commands

🚀 Available Commands

Core Development Commands

🧠 Agent Specializations

Core Analysis Agents

Specialized Development Agents

Utility Agents

⚡ Key Benefits

Efficiency Gains

Quality Improvements

Development Workflow

🔄 Workflow Patterns

Feature Development Flow

Debugging Flow

Optimization Flow

💡 Usage Examples

Feature Development

System Redesign

Performance Optimization

Comprehensive Auditing

Fully Automatic Development

🎯 Integration with MCF

Serena Integration

Context Management

Project Management

🚀 Getting Started

Quick Start

Advanced Usage

Help and Documentation

📊 Monitoring & Analytics

Agent Performance

Usage Patterns

🔧 Technical Details

Command Structure

Agent Selection

Context Management

Integration Points

Install README and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Use it

Manifest

Reviews