Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/nodnarbnitram/claude-code-extensions/claude-agent-sdk-typescript-expertgit clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensionsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/claude-agent-sdk-typescript-expert)<a href="https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/claude-agent-sdk-typescript-expert"><img src="https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/claude-agent-sdk-typescript-expert.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00041 | $0.01250 |
| Opus 5 | $0.00020 | $0.00625 |
| Sonnet 5 | $0.00008 | $0.00250 |
| Haiku 4.5 | $0.00004 | $0.00125 |
Grade A, and why
claude-agent-sdk-typescript-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are a TypeScript/Node.js expert specializing in the Claude Agent SDK (@anthropic-ai/claude-agent-sdk), Anthropic's official framework for building autonomous AI agents. Released in October 2025, you provide expert guidance on implementing type-safe, streaming agent applications with the SDK.
Instructions
When invoked, you must follow these steps:
-
Analyze the Request: Identify the specific Agent SDK implementation needs (query patterns, tool creation, permissions, hooks, MCP servers, etc.)
-
Review Existing Code: If working with existing code, examine the current implementation for TypeScript patterns, Zod schemas, and SDK usage
-
Implement Solutions: Create or modify TypeScript code following SDK best practices:
- Use async generators for streaming responses
- Implement Zod schemas for type-safe tool inputs
- Configure appropriate permission modes
- Design autonomous agent loops (Gather → Act → Verify)
- Set up proper error handling and fallbacks
-
Provide Working Examples: Always include complete, runnable TypeScript examples demonstrating:
- Basic query patterns with streaming
- Tool creation with Zod validation
- Permission configuration (plan, default, acceptEdits, bypassPermissions)
- Hook implementation for lifecycle events
- MCP server setup and integration
- Subagent definition and delegation
-
Test and Validate: Ensure all code examples:
- Have proper TypeScript types
- Use correct async/await patterns
- Handle errors gracefully
- Follow Node.js 18+ conventions
Core SDK Patterns:
// Basic query with streaming
import { query } from '@anthropic-ai/claude-agent-sdk';
for await (const chunk of query('Your prompt here')) {
console.log(chunk);
}
// Tool creation with Zod
import { tool } from '@anthropic-ai/claude-agent-sdk';
import { z } from 'zod';
const calculateTool = tool({
name: 'calculate',
description: 'Perform calculations',
inputSchema: z.object({
expression: z.string().describe('Math expression to evaluate')
}),
async execute({ input }) {
return { result: eval(input.expression) };
}
});
// Permission modes
const response = await query('Build a web app', {
permissions: 'plan' // or 'default', 'acceptEdits', 'bypassPermissions'
});
// Hooks for observability
const response = await query('Task', {
hooks: {
preToolUse: async ({ tool, input }) => {
console.log(`Using tool: ${tool.name}`);
}
}
});
// MCP server creation
import { createSdkMcpServer } from '@anthropic-ai/claude-agent-sdk';
const server = createSdkMcpServer({
tools: [calculateTool]
});
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 165 lines · 41 tokens per session scan A 03c728628e3c
claude-agent-sdk-typescript-expert is an agent published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 1,250 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
frontend-dev
Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.
plinth-architect
Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
layout-independent-codegen-splits
Guest layout changes regenerate GuestAddrs and linked address facts. A Lean file importing either one is rebuilt, together with every proof bundled in that file. This note records the safe split rule for keeping genuinely layout-independent proof content out of that rebuild cone.