Skip to content

phuryn/product-engineering / app-stack/skills/embedded-agents-agent-sdk

embedded-agents-agent-sdk

Verified

Only when the Agent SDK is asked for, an agent needs Claude Code's own tools, or the app already runs it: embed Claude agents in a Next.js app with the Agent SDK.

examples/research-agent.live.test.ts

View on GitHub
import { describe, test, expect, vi } from 'vitest';

vi.mock('server-only', () => ({}));
import { askAgent } from '@/lib/agent';

// The example research-agent's own behaviour, against the real model (outside the gate).
// Needs PERPLEXITY_API_KEY; the second test calls Perplexity and spends its credits.

async function ask(prompt: string): Promise<{ text: string; done: boolean }> {
  let text = '';
  let done = false;
  for await (const ev of askAgent({ agent: 'research-agent', prompt })) {
    if (ev.type === 'text') text += ev.text;
    if (ev.type === 'done') done = true;
  }
  return { text, done };
}

describe('research-agent', () => {
  test('its AGENTS.md is in force: the sign-off', async () => {
    const { text } = await ask('Say hello in one short sentence. Do not call any tools.');
    expect(text).toContain('Best, Research Agent');
  });

  test('researches with Perplexity and cites a source', async () => {
    const { text, done } = await ask('What is the latest stable version of Node.js? One line, with a source URL.');
    expect(done).toBe(true);
    expect(text).toMatch(/https?:\/\//);
  });
});
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall