codehava-agent-kit 1.0.1 → 2.0.0

package/templates/.agent/skills/claude-api/typescript/claude-api/tool-use.md

@@ -0,0 +1,477 @@
+# Tool Use — TypeScript
+
+For conceptual overview (tool definitions, tool choice, tips), see [shared/tool-use-concepts.md](../../shared/tool-use-concepts.md).
+
+## Tool Runner (Recommended)
+
+**Beta:** The tool runner is in beta in the TypeScript SDK.
+
+Use `betaZodTool` with Zod schemas to define tools with a `run` function, then pass them to `client.beta.messages.toolRunner()`:
+
+```typescript
+import Anthropic from "@anthropic-ai/sdk";
+import { betaZodTool } from "@anthropic-ai/sdk/helpers/beta/zod";
+import { z } from "zod";
+
+const client = new Anthropic();
+
+const getWeather = betaZodTool({
+  name: "get_weather",
+  description: "Get current weather for a location",
+  inputSchema: z.object({
+    location: z.string().describe("City and state, e.g., San Francisco, CA"),
+    unit: z.enum(["celsius", "fahrenheit"]).optional(),
+  }),
+  run: async (input) => {
+    // Your implementation here
+    return `72°F and sunny in ${input.location}`;
+  },
+});
+
+// The tool runner handles the agentic loop and returns the final message
+const finalMessage = await client.beta.messages.toolRunner({
+  model: "claude-opus-4-6",
+  max_tokens: 4096,
+  tools: [getWeather],
+  messages: [{ role: "user", content: "What's the weather in Paris?" }],
+});
+
+console.log(finalMessage.content);
+```
+
+**Key benefits of the tool runner:**
+
+- No manual loop — the SDK handles calling tools and feeding results back
+- Type-safe tool inputs via Zod schemas
+- Tool schemas are generated automatically from Zod definitions
+- Iteration stops automatically when Claude has no more tool calls
+
+---
+
+## Manual Agentic Loop
+
+Use this when you need fine-grained control (custom logging, conditional tool execution, streaming individual iterations, human-in-the-loop approval):
+
+```typescript
+import Anthropic from "@anthropic-ai/sdk";
+
+const client = new Anthropic();
+const tools: Anthropic.Tool[] = [...]; // Your tool definitions
+let messages: Anthropic.MessageParam[] = [{ role: "user", content: userInput }];
+
+while (true) {
+  const response = await client.messages.create({
+    model: "claude-opus-4-6",
+    max_tokens: 4096,
+    tools: tools,
+    messages: messages,
+  });
+
+  if (response.stop_reason === "end_turn") break;
+
+  // Server-side tool hit iteration limit; re-send to continue
+  if (response.stop_reason === "pause_turn") {
+    messages = [
+      { role: "user", content: userInput },
+      { role: "assistant", content: response.content },
+    ];
+    continue;
+  }
+
+  const toolUseBlocks = response.content.filter(
+    (b): b is Anthropic.ToolUseBlock => b.type === "tool_use",
+  );
+
+  messages.push({ role: "assistant", content: response.content });
+
+  const toolResults: Anthropic.ToolResultBlockParam[] = [];
+  for (const tool of toolUseBlocks) {
+    const result = await executeTool(tool.name, tool.input);
+    toolResults.push({
+      type: "tool_result",
+      tool_use_id: tool.id,
+      content: result,
+    });
+  }
+
+  messages.push({ role: "user", content: toolResults });
+}
+```
+
+### Streaming Manual Loop
+
+Use `client.messages.stream()` + `finalMessage()` instead of `.create()` when you need streaming within a manual loop. Text deltas are streamed on each iteration; `finalMessage()` collects the complete `Message` so you can inspect `stop_reason` and extract tool-use blocks:
+
+```typescript
+import Anthropic from "@anthropic-ai/sdk";
+
+const client = new Anthropic();
+const tools: Anthropic.Tool[] = [...];
+let messages: Anthropic.MessageParam[] = [{ role: "user", content: userInput }];
+
+while (true) {
+  const stream = client.messages.stream({
+    model: "claude-opus-4-6",
+    max_tokens: 4096,
+    tools,
+    messages,
+  });
+
+  // Stream text deltas on each iteration
+  stream.on("text", (delta) => {
+    process.stdout.write(delta);
+  });
+
+  // finalMessage() resolves with the complete Message — no need to
+  // manually wire up .on("message") / .on("error") / .on("abort")
+  const message = await stream.finalMessage();
+
+  if (message.stop_reason === "end_turn") break;
+
+  // Server-side tool hit iteration limit; re-send to continue
+  if (message.stop_reason === "pause_turn") {
+    messages = [
+      { role: "user", content: userInput },
+      { role: "assistant", content: message.content },
+    ];
+    continue;
+  }
+
+  const toolUseBlocks = message.content.filter(
+    (b): b is Anthropic.ToolUseBlock => b.type === "tool_use",
+  );
+
+  messages.push({ role: "assistant", content: message.content });
+
+  const toolResults: Anthropic.ToolResultBlockParam[] = [];
+  for (const tool of toolUseBlocks) {
+    const result = await executeTool(tool.name, tool.input);
+    toolResults.push({
+      type: "tool_result",
+      tool_use_id: tool.id,
+      content: result,
+    });
+  }
+
+  messages.push({ role: "user", content: toolResults });
+}
+```
+
+> **Important:** Don't wrap `.on()` events in `new Promise()` to collect the final message — use `stream.finalMessage()` instead. The SDK handles all error/abort/completion states internally.
+
+> **Error handling in the loop:** Use the SDK's typed exceptions (e.g., `Anthropic.RateLimitError`, `Anthropic.APIError`) — see [Error Handling](./README.md#error-handling) for examples. Don't check error messages with string matching.
+
+> **SDK types:** Use `Anthropic.MessageParam`, `Anthropic.Tool`, `Anthropic.ToolUseBlock`, `Anthropic.ToolResultBlockParam`, `Anthropic.Message`, etc. for all API-related data structures. Don't redefine equivalent interfaces.
+
+---
+
+## Handling Tool Results
+
+```typescript
+const response = await client.messages.create({
+  model: "claude-opus-4-6",
+  max_tokens: 1024,
+  tools: tools,
+  messages: [{ role: "user", content: "What's the weather in Paris?" }],
+});
+
+for (const block of response.content) {
+  if (block.type === "tool_use") {
+    const result = await executeTool(block.name, block.input);
+
+    const followup = await client.messages.create({
+      model: "claude-opus-4-6",
+      max_tokens: 1024,
+      tools: tools,
+      messages: [
+        { role: "user", content: "What's the weather in Paris?" },
+        { role: "assistant", content: response.content },
+        {
+          role: "user",
+          content: [
+            { type: "tool_result", tool_use_id: block.id, content: result },
+          ],
+        },
+      ],
+    });
+  }
+}
+```
+
+---
+
+## Tool Choice
+
+```typescript
+const response = await client.messages.create({
+  model: "claude-opus-4-6",
+  max_tokens: 1024,
+  tools: tools,
+  tool_choice: { type: "tool", name: "get_weather" },
+  messages: [{ role: "user", content: "What's the weather in Paris?" }],
+});
+```
+
+---
+
+## Code Execution
+
+### Basic Usage
+
+```typescript
+import Anthropic from "@anthropic-ai/sdk";
+
+const client = new Anthropic();
+
+const response = await client.messages.create({
+  model: "claude-opus-4-6",
+  max_tokens: 4096,
+  messages: [
+    {
+      role: "user",
+      content:
+        "Calculate the mean and standard deviation of [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]",
+    },
+  ],
+  tools: [{ type: "code_execution_20260120", name: "code_execution" }],
+});
+```
+
+### Upload Files for Analysis
+
+```typescript
+import Anthropic, { toFile } from "@anthropic-ai/sdk";
+import { createReadStream } from "fs";
+
+const client = new Anthropic();
+
+// 1. Upload a file
+const uploaded = await client.beta.files.upload({
+  file: await toFile(createReadStream("sales_data.csv"), undefined, {
+    type: "text/csv",
+  }),
+  betas: ["files-api-2025-04-14"],
+});
+
+// 2. Pass to code execution
+// Code execution is GA; Files API is still beta (pass via RequestOptions)
+const response = await client.messages.create(
+  {
+    model: "claude-opus-4-6",
+    max_tokens: 4096,
+    messages: [
+      {
+        role: "user",
+        content: [
+          {
+            type: "text",
+            text: "Analyze this sales data. Show trends and create a visualization.",
+          },
+          { type: "container_upload", file_id: uploaded.id },
+        ],
+      },
+    ],
+    tools: [{ type: "code_execution_20260120", name: "code_execution" }],
+  },
+  { headers: { "anthropic-beta": "files-api-2025-04-14" } },
+);
+```
+
+### Retrieve Generated Files
+
+```typescript
+import path from "path";
+import fs from "fs";
+
+const OUTPUT_DIR = "./claude_outputs";
+await fs.promises.mkdir(OUTPUT_DIR, { recursive: true });
+
+for (const block of response.content) {
+  if (block.type === "bash_code_execution_tool_result") {
+    const result = block.content;
+    if (result.type === "bash_code_execution_result" && result.content) {
+      for (const fileRef of result.content) {
+        if (fileRef.type === "bash_code_execution_output") {
+          const metadata = await client.beta.files.retrieveMetadata(
+            fileRef.file_id,
+          );
+          const response = await client.beta.files.download(fileRef.file_id);
+          const fileBytes = Buffer.from(await response.arrayBuffer());
+          const safeName = path.basename(metadata.filename);
+          if (!safeName || safeName === "." || safeName === "..") {
+            console.warn(`Skipping invalid filename: ${metadata.filename}`);
+            continue;
+          }
+          const outputPath = path.join(OUTPUT_DIR, safeName);
+          await fs.promises.writeFile(outputPath, fileBytes);
+          console.log(`Saved: ${outputPath}`);
+        }
+      }
+    }
+  }
+}
+```
+
+### Container Reuse
+
+```typescript
+// First request: set up environment
+const response1 = await client.messages.create({
+  model: "claude-opus-4-6",
+  max_tokens: 4096,
+  messages: [
+    {
+      role: "user",
+      content: "Install tabulate and create data.json with sample user data",
+    },
+  ],
+  tools: [{ type: "code_execution_20260120", name: "code_execution" }],
+});
+
+// Reuse container
+const containerId = response1.container.id;
+
+const response2 = await client.messages.create({
+  container: containerId,
+  model: "claude-opus-4-6",
+  max_tokens: 4096,
+  messages: [
+    {
+      role: "user",
+      content: "Read data.json and display as a formatted table",
+    },
+  ],
+  tools: [{ type: "code_execution_20260120", name: "code_execution" }],
+});
+```
+
+---
+
+## Memory Tool
+
+### Basic Usage
+
+```typescript
+const response = await client.messages.create({
+  model: "claude-opus-4-6",
+  max_tokens: 2048,
+  messages: [
+    {
+      role: "user",
+      content: "Remember that my preferred language is TypeScript.",
+    },
+  ],
+  tools: [{ type: "memory_20250818", name: "memory" }],
+});
+```
+
+### SDK Memory Helper
+
+Use `betaMemoryTool` with a `MemoryToolHandlers` implementation:
+
+```typescript
+import {
+  betaMemoryTool,
+  type MemoryToolHandlers,
+} from "@anthropic-ai/sdk/helpers/beta/memory";
+
+const handlers: MemoryToolHandlers = {
+  async view(command) { ... },
+  async create(command) { ... },
+  async str_replace(command) { ... },
+  async insert(command) { ... },
+  async delete(command) { ... },
+  async rename(command) { ... },
+};
+
+const memory = betaMemoryTool(handlers);
+
+const runner = client.beta.messages.toolRunner({
+  model: "claude-opus-4-6",
+  max_tokens: 2048,
+  tools: [memory],
+  messages: [{ role: "user", content: "Remember my preferences" }],
+});
+
+for await (const message of runner) {
+  console.log(message);
+}
+```
+
+For full implementation examples, use WebFetch:
+
+- `https://github.com/anthropics/anthropic-sdk-typescript/blob/main/examples/tools-helpers-memory.ts`
+
+---
+
+## Structured Outputs
+
+### JSON Outputs (Zod — Recommended)
+
+```typescript
+import Anthropic from "@anthropic-ai/sdk";
+import { z } from "zod";
+import { zodOutputFormat } from "@anthropic-ai/sdk/helpers/zod";
+
+const ContactInfoSchema = z.object({
+  name: z.string(),
+  email: z.string(),
+  plan: z.string(),
+  interests: z.array(z.string()),
+  demo_requested: z.boolean(),
+});
+
+const client = new Anthropic();
+
+const response = await client.messages.parse({
+  model: "claude-opus-4-6",
+  max_tokens: 1024,
+  messages: [
+    {
+      role: "user",
+      content:
+        "Extract: Jane Doe (jane@co.com) wants Enterprise, interested in API and SDKs, wants a demo.",
+    },
+  ],
+  output_config: {
+    format: zodOutputFormat(ContactInfoSchema),
+  },
+});
+
+console.log(response.parsed_output.name); // "Jane Doe"
+```
+
+### Strict Tool Use
+
+```typescript
+const response = await client.messages.create({
+  model: "claude-opus-4-6",
+  max_tokens: 1024,
+  messages: [
+    {
+      role: "user",
+      content: "Book a flight to Tokyo for 2 passengers on March 15",
+    },
+  ],
+  tools: [
+    {
+      name: "book_flight",
+      description: "Book a flight to a destination",
+      strict: true,
+      input_schema: {
+        type: "object",
+        properties: {
+          destination: { type: "string" },
+          date: { type: "string", format: "date" },
+          passengers: {
+            type: "integer",
+            enum: [1, 2, 3, 4, 5, 6, 7, 8],
+          },
+        },
+        required: ["destination", "date", "passengers"],
+        additionalProperties: false,
+      },
+    },
+  ],
+});
+```

package/templates/.agent/skills/claude-win11-speckit-update-skill/SKILL.md

@@ -0,0 +1,23 @@
+---
+name: claude-win11-speckit-update-skill
+description: "Windows 11 system management"
+risk: safe
+source: "https://github.com/NotMyself/claude-win11-speckit-update-skill"
+date_added: "2026-02-27"
+---
+
+# Claude Win11 Speckit Update Skill
+
+## Overview
+
+Windows 11 system management
+
+## When to Use This Skill
+
+Use this skill when you need to work with windows 11 system management.
+
+## Instructions
+
+This skill provides guidance and patterns for windows 11 system management.
+
+For more information, see the [source repository](https://github.com/NotMyself/claude-win11-speckit-update-skill).

package/templates/.agent/skills/clerk-auth/SKILL.md

@@ -0,0 +1,58 @@
+---
+name: clerk-auth
+description: "Expert patterns for Clerk auth implementation, middleware, organizations, webhooks, and user sync Use when: adding authentication, clerk auth, user authentication, sign in, sign up."
+risk: unknown
+source: "vibeship-spawner-skills (Apache 2.0)"
+date_added: "2026-02-27"
+---
+
+# Clerk Authentication
+
+## Patterns
+
+### Next.js App Router Setup
+
+Complete Clerk setup for Next.js 14/15 App Router.
+
+Includes ClerkProvider, environment variables, and basic
+sign-in/sign-up components.
+
+Key components:
+- ClerkProvider: Wraps app for auth context
+- <SignIn />, <SignUp />: Pre-built auth forms
+- <UserButton />: User menu with session management
+
+### Middleware Route Protection
+
+Protect routes using clerkMiddleware and createRouteMatcher.
+
+Best practices:
+- Single middleware.ts file at project root
+- Use createRouteMatcher for route groups
+- auth.protect() for explicit protection
+- Centralize all auth logic in middleware
+
+### Server Component Authentication
+
+Access auth state in Server Components using auth() and currentUser().
+
+Key functions:
+- auth(): Returns userId, sessionId, orgId, claims
+- currentUser(): Returns full User object
+- Both require clerkMiddleware to be configured
+
+## ⚠️ Sharp Edges
+
+| Issue | Severity | Solution |
+|-------|----------|----------|
+| Issue | critical | See docs |
+| Issue | high | See docs |
+| Issue | high | See docs |
+| Issue | high | See docs |
+| Issue | medium | See docs |
+| Issue | medium | See docs |
+| Issue | medium | See docs |
+| Issue | medium | See docs |
+
+## When to Use
+This skill is applicable to execute the workflow or actions described in the overview.

package/templates/.agent/skills/cloud-architect/SKILL.md

@@ -0,0 +1,131 @@
+---
+name: cloud-architect
+description: Expert cloud architect specializing in AWS/Azure/GCP multi-cloud infrastructure design, advanced IaC (Terraform/OpenTofu/CDK), FinOps cost optimization, and modern architectural patterns.
+risk: unknown
+source: community
+date_added: '2026-02-27'
+---
+
+## Use this skill when
+
+- Working on cloud architect tasks or workflows
+- Needing guidance, best practices, or checklists for cloud architect
+
+## Do not use this skill when
+
+- The task is unrelated to cloud architect
+- You need a different domain or tool outside this scope
+
+## Instructions
+
+- Clarify goals, constraints, and required inputs.
+- Apply relevant best practices and validate outcomes.
+- Provide actionable steps and verification.
+- If detailed examples are required, open `resources/implementation-playbook.md`.
+
+You are a cloud architect specializing in scalable, cost-effective, and secure multi-cloud infrastructure design.
+
+## Purpose
+Expert cloud architect with deep knowledge of AWS, Azure, GCP, and emerging cloud technologies. Masters Infrastructure as Code, FinOps practices, and modern architectural patterns including serverless, microservices, and event-driven architectures. Specializes in cost optimization, security best practices, and building resilient, scalable systems.
+
+## Capabilities
+
+### Cloud Platform Expertise
+- **AWS**: EC2, Lambda, EKS, RDS, S3, VPC, IAM, CloudFormation, CDK, Well-Architected Framework
+- **Azure**: Virtual Machines, Functions, AKS, SQL Database, Blob Storage, Virtual Network, ARM templates, Bicep
+- **Google Cloud**: Compute Engine, Cloud Functions, GKE, Cloud SQL, Cloud Storage, VPC, Cloud Deployment Manager
+- **Multi-cloud strategies**: Cross-cloud networking, data replication, disaster recovery, vendor lock-in mitigation
+- **Edge computing**: CloudFlare, AWS CloudFront, Azure CDN, edge functions, IoT architectures
+
+### Infrastructure as Code Mastery
+- **Terraform/OpenTofu**: Advanced module design, state management, workspaces, provider configurations
+- **Native IaC**: CloudFormation (AWS), ARM/Bicep (Azure), Cloud Deployment Manager (GCP)
+- **Modern IaC**: AWS CDK, Azure CDK, Pulumi with TypeScript/Python/Go
+- **GitOps**: Infrastructure automation with ArgoCD, Flux, GitHub Actions, GitLab CI/CD
+- **Policy as Code**: Open Policy Agent (OPA), AWS Config, Azure Policy, GCP Organization Policy
+
+### Cost Optimization & FinOps
+- **Cost monitoring**: CloudWatch, Azure Cost Management, GCP Cost Management, third-party tools (CloudHealth, Cloudability)
+- **Resource optimization**: Right-sizing recommendations, reserved instances, spot instances, committed use discounts
+- **Cost allocation**: Tagging strategies, chargeback models, showback reporting
+- **FinOps practices**: Cost anomaly detection, budget alerts, optimization automation
+- **Multi-cloud cost analysis**: Cross-provider cost comparison, TCO modeling
+
+### Architecture Patterns
+- **Microservices**: Service mesh (Istio, Linkerd), API gateways, service discovery
+- **Serverless**: Function composition, event-driven architectures, cold start optimization
+- **Event-driven**: Message queues, event streaming (Kafka, Kinesis, Event Hubs), CQRS/Event Sourcing
+- **Data architectures**: Data lakes, data warehouses, ETL/ELT pipelines, real-time analytics
+- **AI/ML platforms**: Model serving, MLOps, data pipelines, GPU optimization
+
+### Security & Compliance
+- **Zero-trust architecture**: Identity-based access, network segmentation, encryption everywhere
+- **IAM best practices**: Role-based access, service accounts, cross-account access patterns
+- **Compliance frameworks**: SOC2, HIPAA, PCI-DSS, GDPR, FedRAMP compliance architectures
+- **Security automation**: SAST/DAST integration, infrastructure security scanning
+- **Secrets management**: HashiCorp Vault, cloud-native secret stores, rotation strategies
+
+### Scalability & Performance
+- **Auto-scaling**: Horizontal/vertical scaling, predictive scaling, custom metrics
+- **Load balancing**: Application load balancers, network load balancers, global load balancing
+- **Caching strategies**: CDN, Redis, Memcached, application-level caching
+- **Database scaling**: Read replicas, sharding, connection pooling, database migration
+- **Performance monitoring**: APM tools, synthetic monitoring, real user monitoring
+
+### Disaster Recovery & Business Continuity
+- **Multi-region strategies**: Active-active, active-passive, cross-region replication
+- **Backup strategies**: Point-in-time recovery, cross-region backups, backup automation
+- **RPO/RTO planning**: Recovery time objectives, recovery point objectives, DR testing
+- **Chaos engineering**: Fault injection, resilience testing, failure scenario planning
+
+### Modern DevOps Integration
+- **CI/CD pipelines**: GitHub Actions, GitLab CI, Azure DevOps, AWS CodePipeline
+- **Container orchestration**: EKS, AKS, GKE, self-managed Kubernetes
+- **Observability**: Prometheus, Grafana, DataDog, New Relic, OpenTelemetry
+- **Infrastructure testing**: Terratest, InSpec, Checkov, Terrascan
+
+### Emerging Technologies
+- **Cloud-native technologies**: CNCF landscape, service mesh, Kubernetes operators
+- **Edge computing**: Edge functions, IoT gateways, 5G integration
+- **Quantum computing**: Cloud quantum services, hybrid quantum-classical architectures
+- **Sustainability**: Carbon footprint optimization, green cloud practices
+
+## Behavioral Traits
+- Emphasizes cost-conscious design without sacrificing performance or security
+- Advocates for automation and Infrastructure as Code for all infrastructure changes
+- Designs for failure with multi-AZ/region resilience and graceful degradation
+- Implements security by default with least privilege access and defense in depth
+- Prioritizes observability and monitoring for proactive issue detection
+- Considers vendor lock-in implications and designs for portability when beneficial
+- Stays current with cloud provider updates and emerging architectural patterns
+- Values simplicity and maintainability over complexity
+
+## Knowledge Base
+- AWS, Azure, GCP service catalogs and pricing models
+- Cloud provider security best practices and compliance standards
+- Infrastructure as Code tools and best practices
+- FinOps methodologies and cost optimization strategies
+- Modern architectural patterns and design principles
+- DevOps and CI/CD best practices
+- Observability and monitoring strategies
+- Disaster recovery and business continuity planning
+
+## Response Approach
+1. **Analyze requirements** for scalability, cost, security, and compliance needs
+2. **Recommend appropriate cloud services** based on workload characteristics
+3. **Design resilient architectures** with proper failure handling and recovery
+4. **Provide Infrastructure as Code** implementations with best practices
+5. **Include cost estimates** with optimization recommendations
+6. **Consider security implications** and implement appropriate controls
+7. **Plan for monitoring and observability** from day one
+8. **Document architectural decisions** with trade-offs and alternatives
+
+## Example Interactions
+- "Design a multi-region, auto-scaling web application architecture on AWS with estimated monthly costs"
+- "Create a hybrid cloud strategy connecting on-premises data center with Azure"
+- "Optimize our GCP infrastructure costs while maintaining performance and availability"
+- "Design a serverless event-driven architecture for real-time data processing"
+- "Plan a migration from monolithic application to microservices on Kubernetes"
+- "Implement a disaster recovery solution with 4-hour RTO across multiple cloud providers"
+- "Design a compliant architecture for healthcare data processing meeting HIPAA requirements"
+- "Create a FinOps strategy with automated cost optimization and chargeback reporting"