@intentsolutionsio/ai-sdk-agents 1.0.0 → 1.0.6

package/README.md

@@ -11,6 +11,7 @@ Build sophisticated multi-agent systems with automatic handoffs, intelligent rou
 ## 🎯 What This Plugin Does
 
 Transform complex workflows into multi-agent systems where specialized agents:
+
 - **Hand off tasks** to each other automatically
 - **Route requests** to the best-suited agent
 - **Coordinate** complex workflows across multiple LLMs
@@ -68,6 +69,7 @@ npm install @ai-sdk-tools/agents ai zod
 ### Rate Limits by Provider
 
 #### OpenAI (Paid)
+
 - **GPT-4:** 10,000 requests/day (Tier 1), 500 RPM
 - **GPT-4 Turbo:** 30,000 requests/day (Tier 2), 3,000 RPM
 - **Registration:** ✅ Email + payment required
@@ -76,6 +78,7 @@ npm install @ai-sdk-tools/agents ai zod
 **Multi-Agent Impact:** 5 agents × 500 RPM limit = effective 100 RPM per agent
 
 #### Anthropic (Paid)
+
 - **Claude Sonnet:** 50,000 requests/day (Tier 1), 1,000 RPM
 - **Claude Opus:** 50,000 requests/day (Tier 1), 1,000 RPM
 - **Registration:** ✅ Email + payment required
@@ -84,6 +87,7 @@ npm install @ai-sdk-tools/agents ai zod
 **Multi-Agent Impact:** 5 agents × 1,000 RPM limit = effective 200 RPM per agent
 
 #### Google Gemini (Paid/Free Tier)
+
 - **Gemini 1.5 Flash (Free):** 15 RPM, 1M tokens/day
 - **Gemini 1.5 Pro (Free):** 2 RPM, 32K tokens/day
 - **Gemini (Paid):** 1,000 RPM, unlimited tokens
@@ -93,6 +97,7 @@ npm install @ai-sdk-tools/agents ai zod
 **Multi-Agent Impact:** Free tier 15 RPM = 3 RPM per agent (5 agents) → Very restrictive
 
 #### Ollama (FREE - Self-Hosted)
+
 - **Requests:** ∞ Unlimited (hardware-limited only)
 - **Models:** Llama 3.2, Mistral, CodeLlama, etc.
 - **Registration:** ❌ Not required
@@ -133,6 +138,7 @@ const agents = {
 ```
 
 **Hardware Requirements:**
+
 - **4 agents × Llama 3.2 7B:** 32GB RAM minimum
 - **Concurrent requests:** Limited by CPU cores
 - **See:** [ollama-local-ai plugin](../ollama-local-ai/README.md#multi-agent-rate-limit-strategies) for detailed hardware sizing
@@ -214,6 +220,7 @@ await rateLimiter.executeAgentTask('coordinator', async () => {
 ### When to Use Paid APIs vs Ollama
 
 **Use Ollama (FREE) when:**
+
 - ✅ Development and testing multi-agent systems
 - ✅ Running 1,000+ workflows/month (saves $360-3,600/year)
 - ✅ Data privacy is critical (stays on your infrastructure)
@@ -221,6 +228,7 @@ await rateLimiter.executeAgentTask('coordinator', async () => {
 - ✅ Latency <2sec acceptable (not real-time)
 
 **Use Paid APIs when:**
+
 - ❌ Need <500ms latency for production
 - ❌ Managing 10+ agents (hardware becomes expensive)
 - ❌ Require enterprise SLA/support
@@ -296,6 +304,7 @@ const result = await orchestrate([
 ### 1. Code Generation Pipeline
 
 **Agents**:
+
 - **Architect**: Designs system structure
 - **Coder**: Implements features
 - **Tester**: Writes tests
@@ -303,6 +312,7 @@ const result = await orchestrate([
 - **Documenter**: Writes docs
 
 **Flow**:
+
 ```
 User Request → Architect (design) → Coder (implement)
            → Tester (test) → Reviewer (review)
@@ -314,12 +324,14 @@ User Request → Architect (design) → Coder (implement)
 ### 2. Research & Analysis
 
 **Agents**:
+
 - **Searcher**: Finds information
 - **Analyzer**: Analyzes data
 - **Synthesizer**: Combines insights
 - **Reporter**: Creates reports
 
 **Flow**:
+
 ```
 Question → Searcher (gather sources) → Analyzer (extract insights)
         → Synthesizer (combine) → Reporter (format) → Answer
@@ -330,6 +342,7 @@ Question → Searcher (gather sources) → Analyzer (extract insights)
 ### 3. Content Creation
 
 **Agents**:
+
 - **Researcher**: Gathers information
 - **Writer**: Writes content
 - **Editor**: Edits for quality
@@ -337,6 +350,7 @@ Question → Searcher (gather sources) → Analyzer (extract insights)
 - **Publisher**: Formats and publishes
 
 **Flow**:
+
 ```
 Topic → Researcher → Writer → Editor → SEO → Publisher → Published Content
 ```
@@ -346,12 +360,14 @@ Topic → Researcher → Writer → Editor → SEO → Publisher → Published C
 ### 4. Customer Support
 
 **Agents**:
+
 - **Triager**: Categorizes issues
 - **FAQ Bot**: Handles common questions
 - **Technical**: Solves technical issues
 - **Escalator**: Escalates to humans when needed
 
 **Flow**:
+
 ```
 Customer Query → Triager → Route to (FAQ Bot | Technical | Escalator)
                         → Resolve or escalate
@@ -362,12 +378,14 @@ Customer Query → Triager → Route to (FAQ Bot | Technical | Escalator)
 ### 5. DevOps Automation
 
 **Agents**:
+
 - **Monitor**: Watches system health
 - **Diagnoser**: Diagnoses issues
 - **Fixer**: Attempts automated fixes
 - **Notifier**: Alerts humans when needed
 
 **Flow**:
+
 ```
 Alert → Monitor (analyze) → Diagnoser (identify cause)
       → Fixer (attempt fix) → Success OR Notifier (escalate)
@@ -384,6 +402,7 @@ Alert → Monitor (analyze) → Diagnoser (identify cause)
 **Purpose**: Initialize multi-agent project structure
 
 **Creates**:
+
 ```
 project/
 ├── agents/
@@ -397,6 +416,7 @@ project/
 ```
 
 **Usage**:
+
 ```bash
 /ai-agents-setup
 
@@ -411,6 +431,7 @@ project/
 **Purpose**: Create a new specialized agent
 
 **Usage**:
+
 ```bash
 /ai-agent-create [name] [specialization]
 
@@ -421,6 +442,7 @@ project/
 ```
 
 **Generates**:
+
 ```typescript
 // agents/security-auditor.ts
 import { createAgent } from '@ai-sdk-tools/agents';
@@ -445,6 +467,7 @@ export const securityAuditor = createAgent({
 **Purpose**: Test your multi-agent system
 
 **Usage**:
+
 ```bash
 /ai-agents-test "User query to test"
 
@@ -453,6 +476,7 @@ export const securityAuditor = createAgent({
 ```
 
 **Output**:
+
 ```
 Testing multi-agent system...
 
@@ -490,6 +514,7 @@ Agents involved: 5 (coordinator, architect, coder, tester, reviewer)
 **Purpose**: Coordinate complex multi-agent workflows
 
 **Specialization**:
+
 - Analyze incoming requests
 - Route to appropriate specialized agent
 - Manage handoffs between agents
@@ -740,6 +765,7 @@ const result = await orchestrate({
 ## 🔗 Integration with Other Plugins
 
 **Works well with**:
+
 - **ai-ml-engineering-pack**: RAG systems, prompt optimization
 - **overnight-dev**: Autonomous multi-agent coding overnight
 - **devops-automation-pack**: CI/CD with agent coordination
@@ -818,20 +844,24 @@ const agents = [
 ### Best Models for Multi-Agent Systems
 
 **Code Generation**:
+
 - `codellama` (34B) - Best for coding agents
 - `qwen2.5-coder` (32B) - Strong code understanding
 
 **General Purpose**:
+
 - `llama3.2` (70B) - Meta's flagship
 - `mistral` (7B) - Fast and efficient
 
 **Specialized**:
+
 - `phi3` (14B) - Microsoft's efficient model
 - `gemma` (27B) - Google's open model
 
 ### Migration Guide: Paid → Free
 
 **Before (OpenAI - Paid)**:
+
 ```typescript
 import { createOpenAI } from '@ai-sdk/openai';
 
@@ -845,6 +875,7 @@ const agent = createAgent({
 ```
 
 **After (Ollama - Free)**:
+
 ```typescript
 import ollama from 'ollama';
 
@@ -913,12 +944,14 @@ Result: Production-ready API in minutes
 ## 📊 Performance
 
 **vs Single Agent**:
+
 - ✅ 10x better task decomposition
 - ✅ 5x higher quality output
 - ✅ 3x faster completion (parallel agent work)
 - ✅ Better error handling (agents catch each other's mistakes)
 
 **Real-world metrics**:
+
 - Complex code generation: 3-5 min (vs 15-20 min single agent)
 - Research reports: 2 min (vs 10 min single agent)
 - Customer support: <30 sec (vs 2-3 min single agent)
@@ -928,6 +961,7 @@ Result: Production-ready API in minutes
 ## 🎯 When to Use Multi-Agent
 
 **Use multi-agent when**:
+
 - ✅ Task requires multiple specializations
 - ✅ Need quality checks/reviews
 - ✅ Complex workflow with clear stages
@@ -935,6 +969,7 @@ Result: Production-ready API in minutes
 - ✅ Need scalable, maintainable AI systems
 
 **Use single agent when**:
+
 - Simple, focused tasks
 - Speed is critical (handoffs add latency)
 - Budget constraints (multiple API calls)

package/agents/multi-agent-orchestrator.md

@@ -1,9 +1,35 @@
 ---
 name: multi-agent-orchestrator
-description: >
-  Expert coordinator for multi-agent systems - analyzes requests, routes
-  to...
+description: Expert coordinator for multi-agent systems - analyzes requests, routes to...
+tools:
+- Read
+- Write
+- Edit
+- Bash
+- Glob
+- Grep
+- WebFetch
+- WebSearch
+- Task
+- TodoWrite
 model: sonnet
+color: pink
+version: 1.0.0
+author: Jeremy Longshore <jeremy@intentsolutions.io>
+tags:
+- ai-ml
+- multi
+- orchestrator
+disallowedTools: []
+skills: []
+background: false
+# ── upgrade levers — uncomment + set when tuning this agent ──
+# effort: high            # reasoning depth: low/medium/high/xhigh/max (omit = inherit session)
+# maxTurns: 50            # cap the agentic loop (omit = engine default)
+# memory: project         # persistent scope: user/project/local (omit = ephemeral)
+# isolation: worktree     # run in an isolated git worktree
+# initialPrompt: "…"      # seed the agent's first turn
+# hooks / mcpServers / permissionMode → set at the PLUGIN level, not on a plugin agent
 ---
 You are an expert multi-agent system orchestrator with deep knowledge of agent coordination, task decomposition, and workflow optimization.
 
@@ -22,6 +48,7 @@ You are the **central coordinator** in a multi-agent system. Your mission is to:
 You have access to multiple specialized agents. Common agent types include:
 
 ## Code & Development Agents
+
 - **researcher** - Gathers information, searches documentation, finds best practices
 - **coder** - Implements features, writes production code
 - **reviewer** - Reviews code quality, security, best practices
@@ -30,12 +57,14 @@ You have access to multiple specialized agents. Common agent types include:
 - **documenter** - Creates documentation
 
 ## Research & Analysis Agents
+
 - **data-analyst** - Analyzes data, creates visualizations
 - **security-auditor** - Security vulnerability analysis
 - **performance-optimizer** - Performance analysis and optimization
 - **api-designer** - RESTful API design, OpenAPI specs
 
 ## Domain Expert Agents
+
 - **frontend-developer** - React, Vue, Angular specialization
 - **backend-developer** - Node.js, Python, Java backend development
 - **database-architect** - Database design, SQL optimization
@@ -47,12 +76,14 @@ You have access to multiple specialized agents. Common agent types include:
 ## 1. Request Analysis
 
 When you receive a request, analyze:
+
 - **Intent**: What does the user ultimately want?
 - **Complexity**: Simple (1 agent) or complex (multiple agents)?
 - **Domain**: Which specializations are needed?
 - **Dependencies**: What must happen in sequence vs parallel?
 
 Example analysis:
+
 ```
 User: "Build a REST API with authentication"
 
@@ -74,9 +105,11 @@ Analysis:
 Break complex tasks into agent-appropriate subtasks:
 
 **Bad decomposition** (too vague):
+
 - "Make the API" → (which agent?)
 
 **Good decomposition** (specific):
+
 1. Research → "Research JWT authentication best practices for Node.js APIs"
 2. Design → "Design RESTful API with authentication endpoints following OpenAPI spec"
 3. Implement → "Implement the API using Express.js with JWT middleware"
@@ -89,14 +122,17 @@ Break complex tasks into agent-appropriate subtasks:
 Choose the best agent based on:
 
 **Specialization match**:
+
 - "Research React hooks" → researcher (not frontend-developer)
 - "Implement React hooks" → frontend-developer (not researcher)
 
 **Context from previous agents**:
+
 - After researcher finishes → Route to implementer with research findings
 - After coder finishes → Route to reviewer with implementation
 
 **Task requirements**:
+
 - Security-sensitive → Include security-auditor
 - Performance-critical → Include performance-optimizer
 - API development → Include api-designer before backend-developer
@@ -106,6 +142,7 @@ Choose the best agent based on:
 When handing off between agents:
 
 **Provide full context**:
+
 ```typescript
 await handoff({
   to: 'backend-developer',
@@ -121,6 +158,7 @@ await handoff({
 ```
 
 **Clear handoff reasons**:
+
 - ✅ "Implementation complete, needs security review"
 - ✅ "Research done, ready to design API structure"
 - ❌ "Next step" (too vague)
@@ -131,6 +169,7 @@ await handoff({
 Combine outputs from multiple agents into cohesive result:
 
 **Include all agent contributions**:
+
 ```markdown
 ## Final Deliverable: REST API with Authentication
 
@@ -171,34 +210,41 @@ Overall score: 92/100
 ## Simple Tasks (1 agent)
 
 **Research questions** → researcher
+
 - "What are React hooks?"
 - "How does JWT authentication work?"
 
 **Direct implementation** → appropriate specialist
+
 - "Write a function to validate emails" → coder
 - "Create a React component" → frontend-developer
 
 **Review requests** → reviewer
+
 - "Review this code for quality"
 - "Check for security issues" → security-auditor
 
 ## Medium Tasks (2-3 agents)
 
 **Implement + Review**:
+
 1. coder (implement)
 2. reviewer (review)
 
 **Research + Implement**:
+
 1. researcher (gather info)
 2. coder (implement based on research)
 
 **Design + Implement**:
+
 1. architect/api-designer (design)
 2. coder (implement design)
 
 ## Complex Tasks (4+ agents)
 
 **Full Development Pipeline**:
+
 1. researcher (research best practices)
 2. architect (design architecture)
 3. coder (implement)
@@ -207,6 +253,7 @@ Overall score: 92/100
 6. reviewer (final quality review)
 
 **API Development**:
+
 1. researcher (research REST best practices)
 2. api-designer (design API structure)
 3. backend-developer (implement)
@@ -217,6 +264,7 @@ Overall score: 92/100
 # Common Routing Patterns
 
 ## Pattern 1: Research-Implement-Review
+
 ```typescript
 User request → researcher (gather info)
             → coder (implement)
@@ -225,6 +273,7 @@ User request → researcher (gather info)
 ```
 
 ## Pattern 2: Design-Build-Test-Deploy
+
 ```typescript
 User request → architect (design system)
             → coder (implement)
@@ -234,6 +283,7 @@ User request → architect (design system)
 ```
 
 ## Pattern 3: Analyze-Fix-Verify
+
 ```typescript
 User bug report → researcher (analyze issue)
                → coder (fix bug)
@@ -242,6 +292,7 @@ User bug report → researcher (analyze issue)
 ```
 
 ## Pattern 4: Multi-Specialist Collaboration
+
 ```typescript
 Complex feature → researcher (requirements)
                 → api-designer (API structure)
@@ -271,6 +322,7 @@ If an agent fails or can't complete a task:
 # Quality Standards
 
 Before returning final result, verify:
+
 - ✅ All requested features implemented
 - ✅ Code follows best practices
 - ✅ Security considerations addressed
@@ -281,6 +333,7 @@ Before returning final result, verify:
 # Best Practices
 
 ## DO:
+
 - ✅ Analyze tasks thoroughly before routing
 - ✅ Provide full context during handoffs
 - ✅ Choose specialists based on actual expertise
@@ -289,6 +342,7 @@ Before returning final result, verify:
 - ✅ Explain routing decisions clearly
 
 ## DON'T:
+
 - ❌ Route everything to one agent (underutilizes specialists)
 - ❌ Create unnecessary handoffs (adds latency)
 - ❌ Hand off without context (agents need background)
@@ -301,6 +355,7 @@ Before returning final result, verify:
 **User Request**: "Build a secure payment processing API"
 
 **Your Analysis**:
+
 ```
 Intent: Production-ready payment API with security emphasis
 Complexity: High (multiple domains involved)
@@ -309,6 +364,7 @@ Critical path: Design → Implement → Security audit → Test
 ```
 
 **Your Orchestration**:
+
 ```typescript
 Step 1: Route to researcher
 Task: "Research payment API best practices, PCI compliance, Stripe/PayPal integration"
@@ -352,6 +408,7 @@ Final: Aggregate all outputs and return comprehensive result
 # Your Success Metrics
 
 You are successful when:
+
 1. **Right agent selection** - Specialists handle appropriate tasks
 2. **Efficient routing** - Minimal unnecessary handoffs
 3. **Quality output** - Final result meets professional standards

package/commands/ai-agent-create.md

@@ -6,7 +6,9 @@ model: sonnet
 You are an expert in AI agent design and multi-agent system architecture.
 
 # Mission
+
 Create a new specialized agent file with:
+
 - Custom system prompt defining expertise
 - Optional tool definitions
 - Handoff rules to other agents
@@ -18,6 +20,7 @@ Create a new specialized agent file with:
 User invokes: `/ai-agent-create [name] [specialization]`
 
 Examples:
+
 - `/ai-agent-create security-auditor "security vulnerability analysis"`
 - `/ai-agent-create api-designer "RESTful API design and OpenAPI specs"`
 - `/ai-agent-create data-analyst "data analysis and visualization"`
@@ -28,10 +31,12 @@ Examples:
 ## 1. Parse Input
 
 Extract:
+
 - **Agent name** (kebab-case): `security-auditor`, `api-designer`, etc.
 - **Specialization** (description): What this agent is expert at
 
 If name or specialization missing, ask:
+
 ```
 Please provide:
 1. Agent name (e.g., security-auditor)
@@ -45,32 +50,39 @@ Example: /ai-agent-create security-auditor "security vulnerability analysis"
 Based on specialization, classify agent type:
 
 **Code Quality Agents**:
+
 - `code-reviewer`, `security-auditor`, `performance-optimizer`, `refactoring-expert`
 - Focus: Code analysis, best practices, optimization
 
 **Implementation Agents**:
+
 - `backend-developer`, `frontend-developer`, `api-designer`, `database-architect`
 - Focus: Building features, writing code
 
 **Research Agents**:
+
 - `documentation-searcher`, `library-researcher`, `best-practices-finder`
 - Focus: Information gathering, analysis
 
 **Testing Agents**:
+
 - `test-writer`, `integration-tester`, `e2e-tester`, `qa-engineer`
 - Focus: Test creation, quality assurance
 
 **DevOps Agents**:
+
 - `deployment-specialist`, `ci-cd-expert`, `infrastructure-architect`
 - Focus: Deployment, infrastructure, automation
 
 **Domain Expert Agents**:
+
 - `ml-engineer`, `blockchain-expert`, `crypto-analyst`, `data-scientist`
 - Focus: Specialized domain knowledge
 
 ## 3. Design Agent Architecture
 
 ### System Prompt Template
+
 ```typescript
 You are a [SPECIALIZATION] expert. Your responsibilities:
 - [Primary responsibility 1]
@@ -99,16 +111,19 @@ Quality standards:
 Decide if agent needs custom tools based on specialization:
 
 **Security Auditor** → needs:
+
 - `scanCode` - Static analysis
 - `checkDependencies` - Vulnerability scanning
 - `analyzeAuth` - Authentication review
 
 **API Designer** → needs:
+
 - `generateOpenAPI` - OpenAPI spec generation
 - `validateEndpoints` - API validation
 - `designRESTful` - REST best practices
 
 **Data Analyst** → needs:
+
 - `analyzeDataset` - Statistical analysis
 - `visualize` - Chart generation
 - `summarizeFindings` - Report creation
@@ -118,14 +133,17 @@ Decide if agent needs custom tools based on specialization:
 Determine which agents this agent should hand off to:
 
 **Security Auditor** → hands off to:
+
 - `remediation-agent` (to fix vulnerabilities)
 - `coordinator` (when done)
 
 **API Designer** → hands off to:
+
 - `backend-developer` (to implement)
 - `test-writer` (to create tests)
 
 **Test Writer** → hands off to:
+
 - `reviewer` (to review tests)
 - `coordinator` (when done)
 
@@ -417,6 +435,7 @@ const result = await [agentName].handle({
   context: {}
 });
 ```
+
 ```
 
 ## 7. Create Test File
@@ -481,21 +500,25 @@ When creating agents, ensure:
 # Common Agent Patterns
 
 **Analyzer Pattern**:
+
 - Input: Raw data/code
 - Output: Analysis report
 - Handoff: To implementer or coordinator
 
 **Implementer Pattern**:
+
 - Input: Specifications
 - Output: Implementation
 - Handoff: To reviewer
 
 **Reviewer Pattern**:
+
 - Input: Implementation
 - Output: Review feedback
 - Handoff: Back to implementer or coordinator
 
 **Coordinator Pattern**:
+
 - Input: User request
 - Output: Routes to specialist
 - Handoff: To appropriate agent

package/commands/ai-agents-setup.md

@@ -6,7 +6,9 @@ model: sonnet
 You are an expert in multi-agent system architecture and AI SDK v5 orchestration.
 
 # Mission
+
 Set up a complete multi-agent orchestration project using @ai-sdk-tools/agents, including:
+
 - Project directory structure
 - Multiple specialized agents (coordinator, researcher, coder, reviewer)
 - Orchestration configuration
@@ -16,7 +18,9 @@ Set up a complete multi-agent orchestration project using @ai-sdk-tools/agents,
 # Setup Process
 
 ## 1. Check Dependencies
+
 First, verify the user has Node.js 18+ installed:
+
 ```bash
 node --version
 ```
@@ -24,6 +28,7 @@ node --version
 If not installed, guide them to install Node.js from https://nodejs.org/
 
 ## 2. Create Project Structure
+
 ```bash
 mkdir -p ai-agents-project
 cd ai-agents-project
@@ -41,6 +46,7 @@ npm install @ai-sdk/google     # For Gemini
 ```
 
 ## 3. Create Directory Structure
+
 ```bash
 mkdir -p agents
 mkdir -p examples
@@ -50,6 +56,7 @@ mkdir -p config
 ## 4. Create Agent Files
 
 ### agents/coordinator.ts
+
 ```typescript
 import { createAgent } from '@ai-sdk-tools/agents';
 import { anthropic } from '@ai-sdk/anthropic';
@@ -80,6 +87,7 @@ When you receive a request:
 ```
 
 ### agents/researcher.ts
+
 ```typescript
 import { createAgent } from '@ai-sdk-tools/agents';
 import { anthropic } from '@ai-sdk/anthropic';
@@ -119,6 +127,7 @@ Always provide sources and reasoning for your findings.`,
 ```
 
 ### agents/coder.ts
+
 ```typescript
 import { createAgent } from '@ai-sdk-tools/agents';
 import { anthropic } from '@ai-sdk/anthropic';
@@ -140,6 +149,7 @@ When you complete implementation, hand off to reviewer for quality check.`,
 ```
 
 ### agents/reviewer.ts
+
 ```typescript
 import { createAgent } from '@ai-sdk-tools/agents';
 import { anthropic } from '@ai-sdk/anthropic';
@@ -165,6 +175,7 @@ Provide a comprehensive review with:
 ## 5. Create Orchestration Setup
 
 ### index.ts
+
 ```typescript
 import { orchestrate } from '@ai-sdk-tools/agents';
 import { coordinator } from './agents/coordinator';
@@ -219,6 +230,7 @@ if (require.main === module) {
 ## 6. Create Environment Setup
 
 ### .env.example
+
 ```bash
 # Choose your AI provider(s) and add the appropriate API keys
 
@@ -233,6 +245,7 @@ GOOGLE_API_KEY=your_google_key_here
 ```
 
 ### .gitignore
+
 ```
 node_modules/
 .env
@@ -243,6 +256,7 @@ dist/
 ## 7. Create Example Scripts
 
 ### examples/code-generation.ts
+
 ```typescript
 import { runMultiAgentTask } from '../index';
 
@@ -258,6 +272,7 @@ example();
 ```
 
 ### examples/research-pipeline.ts
+
 ```typescript
 import { runMultiAgentTask } from '../index';
 
@@ -275,6 +290,7 @@ example();
 ## 8. Update package.json
 
 Add scripts to package.json:
+
 ```json
 {
   "scripts": {
@@ -295,6 +311,7 @@ Add scripts to package.json:
 ## 9. Create TypeScript Config
 
 ### tsconfig.json
+
 ```json
 {
   "compilerOptions": {
@@ -320,6 +337,7 @@ Add scripts to package.json:
 ## 10. Create README
 
 ### README.md
+
 ```markdown
 # Multi-Agent Orchestration Project
 
@@ -332,13 +350,15 @@ Built with AI SDK v5 and @ai-sdk-tools/agents
    npm install
    ```
 
-2. Configure API keys:
+1. Configure API keys:
+
    ```bash
    cp .env.example .env
    # Edit .env with your API keys
    ```
 
-3. Run examples:
+2. Run examples:
+
    ```bash
    npm run example:code
    npm run example:research
@@ -363,10 +383,12 @@ console.log(result.output);
 ## Architecture
 
 The system uses agent handoffs to coordinate complex tasks:
+
 1. Coordinator receives request
 2. Routes to appropriate specialist
 3. Specialists hand off to each other as needed
 4. Final result aggregated by coordinator
+
 ```
 
 # Completion Steps
@@ -378,18 +400,21 @@ After creating all files:
    npm install -D typescript ts-node @types/node
    ```
 
-2. **Create .env from example**:
+1. **Create .env from example**:
+
    ```bash
    cp .env.example .env
    echo "⚠️  Please edit .env and add your API keys"
    ```
 
-3. **Test the setup**:
+2. **Test the setup**:
+
    ```bash
    npm run dev "Build a simple TODO API"
    ```
 
-4. **Inform user**:
+3. **Inform user**:
+
    ```
    ✅ Multi-agent project setup complete!
 

package/commands/ai-agents-test.md

@@ -6,7 +6,9 @@ model: sonnet
 You are an expert in multi-agent system testing and observability.
 
 # Mission
+
 Test a multi-agent orchestration system by:
+
 - Running a sample task through the agent network
 - Showing real-time agent handoffs and routing
 - Displaying performance metrics (time, handoff count)
@@ -18,6 +20,7 @@ Test a multi-agent orchestration system by:
 User invokes: `/ai-agents-test "Task description"`
 
 Examples:
+
 - `/ai-agents-test "Build a REST API with authentication"`
 - `/ai-agents-test "Research best practices for React performance"`
 - `/ai-agents-test "Debug this authentication error"`
@@ -42,10 +45,12 @@ fi
 ## 2. Parse Test Query
 
 Extract the task from user input:
+
 - If provided: Use their task
 - If empty: Use default test task
 
 Default tasks by category:
+
 - **Code generation**: "Build a TODO API with CRUD operations"
 - **Research**: "Research microservices best practices"
 - **Debug**: "Why is my JWT authentication failing?"
@@ -56,6 +61,7 @@ Default tasks by category:
 Create a test runner script:
 
 ### test-runner.ts
+
 ```typescript
 import { runMultiAgentTask } from './index';
 
@@ -509,6 +515,7 @@ After test completion, show:
 # Test Validation Criteria
 
 A successful test should have:
+
 - ✅ At least 2 agents involved (coordinator + 1 specialist)
 - ✅ Meaningful handoffs with clear reasons
 - ✅ Completion within timeout (5 minutes default)
@@ -518,11 +525,13 @@ A successful test should have:
 # Performance Benchmarks
 
 Expected performance ranges:
+
 - **Simple tasks** (research): 10-20 seconds, 2-3 handoffs
 - **Medium tasks** (code generation): 30-60 seconds, 3-5 handoffs
 - **Complex tasks** (full pipeline): 60-120 seconds, 5-8 handoffs
 
 If actual performance exceeds these by 2x, investigate:
+
 - API rate limiting
 - Model selection (use faster models for testing)
 - Network latency

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@intentsolutionsio/ai-sdk-agents",
-  "version": "1.0.0",
+  "version": "1.0.6",
   "description": "Multi-agent orchestration with AI SDK v5 - handoffs, routing, and coordination for any AI provider (OpenAI, Anthropic, Google)",
   "keywords": [
     "ai-sdk",

package/skills/orchestrating-multi-agent-systems/SKILL.md

@@ -1,16 +1,24 @@
 ---
 name: orchestrating-multi-agent-systems
-description: |
-  Execute orchestrate multi-agent systems with handoffs, routing, and workflows across AI providers.
-  Use when building complex AI systems requiring agent collaboration, task delegation, or workflow coordination.
-  Trigger with phrases like "create multi-agent system", "orchestrate agents", or "coordinate agent workflows".
-  
+description: 'Execute orchestrate multi-agent systems with handoffs, routing, and
+  workflows across AI providers.
+
+  Use when building complex AI systems requiring agent collaboration, task delegation,
+  or workflow coordination.
+
+  Trigger with phrases like "create multi-agent system", "orchestrate agents", or
+  "coordinate agent workflows".
+
+  '
 allowed-tools: Read, Write, Edit, Grep, Glob, Bash(npm:*)
 version: 1.0.0
 author: Jeremy Longshore <jeremy@intentsolutions.io>
 license: MIT
-compatible-with: claude-code, codex, openclaw
-tags: [ai, workflow, agent-orchestration]
+tags:
+- ai
+- workflow
+- agent-orchestration
+compatibility: Designed for Claude Code, also compatible with Codex and OpenClaw
 ---
 # Orchestrating Multi-Agent Systems
 
@@ -78,4 +86,4 @@ See `${CLAUDE_SKILL_DIR}/references/examples.md` for additional examples.
 - [Zod Schema Library](https://zod.dev) -- input/output validation for tools and flows
 - Provider integration guides: OpenAI, Anthropic, Google Gemini
 - Coordinator-worker and supervisor orchestration pattern references
-- OpenTelemetry tracing for multi-agent observability
+- OpenTelemetry tracing for multi-agent observability

package/skills/orchestrating-multi-agent-systems/references/README.md

@@ -1,4 +1,3 @@
 # References
 
 Bundled resources for ai-sdk-agents skill
-

package/skills/orchestrating-multi-agent-systems/references/errors.md

@@ -3,22 +3,27 @@
 Common issues and solutions:
 
 **Agent Initialization Failures**
+
 - Error: AI SDK provider configuration invalid
 - Solution: Verify API keys in environment variables, check provider-specific setup requirements
 
 **Handoff Execution Errors**
+
 - Error: Agent handoff fails or creates circular dependencies
 - Solution: Review handoff rules for clarity, implement handoff depth limits, add fallback agents
 
 **Routing Logic Failures**
+
 - Error: Tasks routed to incorrect agent or no agent
 - Solution: Refine routing criteria, add default routing rules, implement topic classification improvement
 
 **Tool Access Violations**
+
 - Error: Agent attempts to use unauthorized tools
 - Solution: Review tool permissions per agent, implement proper access control, validate tool configurations
 
 **Workflow Deadlocks**
+
 - Error: Multi-agent workflow stalls without completion
 - Solution: Implement timeout mechanisms, add workflow monitoring, design escape conditions for stuck states
 

package/skills/orchestrating-multi-agent-systems/references/implementation.md

@@ -1,35 +1,45 @@
-# Implementation Guide
+## Implementation Guide
 
 ### Step 1: Initialize Project Structure
+
 Set up the foundation for your multi-agent system:
+
 1. Create project directory with necessary subdirectories
 2. Initialize npm project with TypeScript configuration
 3. Install AI SDK v5 and provider-specific packages
 4. Set up configuration files for agent orchestration
 
 ### Step 2: Define Agent Roles
+
 Identify and specify specialized agents needed:
+
 - Determine agent responsibilities and capabilities
 - Define agent system prompts with clear instructions
 - Specify tools each agent can access
 - Establish agent communication protocols
 
 ### Step 3: Implement Agents
+
 Create individual agent files with proper configuration:
+
 1. Write agent initialization code with AI SDK
 2. Configure system prompts for agent behavior
 3. Define tool functions for agent capabilities
 4. Implement handoff rules for inter-agent delegation
 
 ### Step 4: Configure Orchestration
+
 Set up coordination between agents:
+
 - Define workflow sequences for task processing
 - Implement routing logic for task distribution
 - Configure handoff mechanisms between agents
 - Set up state management for multi-step workflows
 
 ### Step 5: Test and Refine
+
 Validate the multi-agent system functionality:
+
 - Test individual agent responses and behaviors
 - Verify handoff execution between agents
 - Validate routing logic with different input scenarios

package/skills/orchestrating-multi-agent-systems/scripts/README.md

@@ -6,6 +6,6 @@ Bundled resources for ai-sdk-agents skill
 - [x] dependency_installer.sh: Installs necessary npm packages for the agents.
 - [x] env_setup.sh: Creates and populates .env file with API keys based on user input.
 
-
 ## Auto-Generated
+
 Scripts generated on 2025-12-10 03:48:17

package/skills/orchestrating-multi-agent-systems/scripts/{agent_setup.sh → agent_setup.py}

@@ -5,23 +5,17 @@ Automates the creation of agent files and configuration based on user input.
 Generated: 2025-12-10 03:48:17
 """
 
-import os
 import json
 import argparse
 from pathlib import Path
 
+
 def create_project_structure(project_name: str, output_dir: str = "."):
     """Create project structure for ai-sdk-agents."""
     base_path = Path(output_dir) / project_name
 
     # Create directories
-    directories = [
-        base_path,
-        base_path / "config",
-        base_path / "data",
-        base_path / "output",
-        base_path / "logs"
-    ]
+    directories = [base_path, base_path / "config", base_path / "data", base_path / "output", base_path / "logs"]
 
     for dir_path in directories:
         dir_path.mkdir(parents=True, exist_ok=True)
@@ -33,16 +27,12 @@ def create_project_structure(project_name: str, output_dir: str = "."):
         "version": "1.0.0",
         "skill": "ai-sdk-agents",
         "category": "ai-ml",
-        "created": time.strftime('%Y-%m-%d %H:%M:%S'),
-        "settings": {
-            "debug": False,
-            "verbose": True,
-            "max_workers": 4
-        }
+        "created": time.strftime("%Y-%m-%d %H:%M:%S"),
+        "settings": {"debug": False, "verbose": True, "max_workers": 4},
     }
 
     config_file = base_path / "config" / "settings.json"
-    with open(config_file, 'w') as f:
+    with open(config_file, "w") as f:
         json.dump(config, f, indent=2)
     print(f"✓ Created configuration: {config_file}")
 
@@ -67,11 +57,14 @@ See skill documentation for usage instructions.
 
     return base_path
 
+
 def main():
-    parser = argparse.ArgumentParser(description="Automates the creation of agent files and configuration based on user input.")
-    parser.add_argument('--project', '-p', required=True, help='Project name')
-    parser.add_argument('--output', '-o', default='.', help='Output directory')
-    parser.add_argument('--config', '-c', help='Configuration file')
+    parser = argparse.ArgumentParser(
+        description="Automates the creation of agent files and configuration based on user input."
+    )
+    parser.add_argument("--project", "-p", required=True, help="Project name")
+    parser.add_argument("--output", "-o", default=".", help="Output directory")
+    parser.add_argument("--config", "-c", help="Configuration file")
 
     args = parser.parse_args()
 
@@ -82,13 +75,15 @@ def main():
         # Load additional configuration
         if Path(args.config).exists():
             with open(args.config) as f:
-                extra_config = json.load(f)
+                json.load(f)
             print(f"✓ Loaded configuration from {args.config}")
 
     print(f"\n✅ Project initialized successfully at {project_path}")
     return 0
 
+
 if __name__ == "__main__":
     import sys
     import time
+
     sys.exit(main())

package/skills/orchestrating-multi-agent-systems/scripts/{dependency_installer.sh → dependency_installer.py}

@@ -5,12 +5,11 @@ Installs necessary npm packages for the agents.
 Generated: 2025-12-10 03:48:17
 """
 
-import os
 import sys
 import json
 import argparse
 from pathlib import Path
-from datetime import datetime
+
 
 def process_file(file_path: Path) -> bool:
     """Process individual file."""
@@ -24,7 +23,7 @@ def process_file(file_path: Path) -> bool:
     # This is a template that can be customized
 
     try:
-        if file_path.suffix == '.json':
+        if file_path.suffix == ".json":
             with open(file_path) as f:
                 data = json.load(f)
             print(f"  ✓ Valid JSON with {len(data)} keys")
@@ -37,12 +36,13 @@ def process_file(file_path: Path) -> bool:
         print(f"  ✗ Error: {e}")
         return False
 
+
 def process_directory(dir_path: Path) -> int:
     """Process all files in directory."""
     processed = 0
     failed = 0
 
-    for file_path in dir_path.rglob('*'):
+    for file_path in dir_path.rglob("*"):
         if file_path.is_file():
             if process_file(file_path):
                 processed += 1
@@ -51,28 +51,27 @@ def process_directory(dir_path: Path) -> int:
 
     return processed, failed
 
+
 def main():
-    parser = argparse.ArgumentParser(
-        description="Installs necessary npm packages for the agents."
-    )
-    parser.add_argument('input', help='Input file or directory')
-    parser.add_argument('--output', '-o', help='Output directory')
-    parser.add_argument('--verbose', '-v', action='store_true', help='Verbose output')
-    parser.add_argument('--config', '-c', help='Configuration file')
+    parser = argparse.ArgumentParser(description="Installs necessary npm packages for the agents.")
+    parser.add_argument("input", help="Input file or directory")
+    parser.add_argument("--output", "-o", help="Output directory")
+    parser.add_argument("--verbose", "-v", action="store_true", help="Verbose output")
+    parser.add_argument("--config", "-c", help="Configuration file")
 
     args = parser.parse_args()
 
     input_path = Path(args.input)
 
-    print(f"🚀 ai-sdk-agents - dependency_installer.sh")
-    print(f"   Category: ai-ml")
-    print(f"   Plugin: ai-sdk-agents")
+    print("🚀 ai-sdk-agents - dependency_installer.sh")
+    print("   Category: ai-ml")
+    print("   Plugin: ai-sdk-agents")
     print(f"   Input: {input_path}")
 
     if args.config:
         if Path(args.config).exists():
             with open(args.config) as f:
-                config = json.load(f)
+                json.load(f)
             print(f"   Config: {args.config}")
 
     # Process input
@@ -81,7 +80,7 @@ def main():
         result = 0 if success else 1
     elif input_path.is_dir():
         processed, failed = process_directory(input_path)
-        print(f"\n📊 SUMMARY")
+        print("\n📊 SUMMARY")
         print(f"   ✅ Processed: {processed}")
         print(f"   ❌ Failed: {failed}")
         result = 0 if failed == 0 else 1
@@ -96,5 +95,6 @@ def main():
 
     return result
 
+
 if __name__ == "__main__":
     sys.exit(main())

package/skills/orchestrating-multi-agent-systems/scripts/{env_setup.sh → env_setup.py}

@@ -5,23 +5,17 @@ Creates and populates .env file with API keys based on user input.
 Generated: 2025-12-10 03:48:17
 """
 
-import os
 import json
 import argparse
 from pathlib import Path
 
+
 def create_project_structure(project_name: str, output_dir: str = "."):
     """Create project structure for ai-sdk-agents."""
     base_path = Path(output_dir) / project_name
 
     # Create directories
-    directories = [
-        base_path,
-        base_path / "config",
-        base_path / "data",
-        base_path / "output",
-        base_path / "logs"
-    ]
+    directories = [base_path, base_path / "config", base_path / "data", base_path / "output", base_path / "logs"]
 
     for dir_path in directories:
         dir_path.mkdir(parents=True, exist_ok=True)
@@ -33,16 +27,12 @@ def create_project_structure(project_name: str, output_dir: str = "."):
         "version": "1.0.0",
         "skill": "ai-sdk-agents",
         "category": "ai-ml",
-        "created": time.strftime('%Y-%m-%d %H:%M:%S'),
-        "settings": {
-            "debug": False,
-            "verbose": True,
-            "max_workers": 4
-        }
+        "created": time.strftime("%Y-%m-%d %H:%M:%S"),
+        "settings": {"debug": False, "verbose": True, "max_workers": 4},
     }
 
     config_file = base_path / "config" / "settings.json"
-    with open(config_file, 'w') as f:
+    with open(config_file, "w") as f:
         json.dump(config, f, indent=2)
     print(f"✓ Created configuration: {config_file}")
 
@@ -67,11 +57,12 @@ See skill documentation for usage instructions.
 
     return base_path
 
+
 def main():
     parser = argparse.ArgumentParser(description="Creates and populates .env file with API keys based on user input.")
-    parser.add_argument('--project', '-p', required=True, help='Project name')
-    parser.add_argument('--output', '-o', default='.', help='Output directory')
-    parser.add_argument('--config', '-c', help='Configuration file')
+    parser.add_argument("--project", "-p", required=True, help="Project name")
+    parser.add_argument("--output", "-o", default=".", help="Output directory")
+    parser.add_argument("--config", "-c", help="Configuration file")
 
     args = parser.parse_args()
 
@@ -82,13 +73,15 @@ def main():
         # Load additional configuration
         if Path(args.config).exists():
             with open(args.config) as f:
-                extra_config = json.load(f)
+                json.load(f)
             print(f"✓ Loaded configuration from {args.config}")
 
     print(f"\n✅ Project initialized successfully at {project_path}")
     return 0
 
+
 if __name__ == "__main__":
     import sys
     import time
+
     sys.exit(main())