Basic agent runner

Skill kjuhwa/skills-hub/skills/agents/basic-agent-runner

Define an Agent and run it synchronously or asynchronously with Runner.From its SKILL.md

Install

npx -y skills add kjuhwa/skills-hub --skill basic-agent-runner

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.7 KB, 295 tokens by cl100k_base, as published. Nobody here has run it

basic-agent-runner

Create a minimal Agent with instructions and run it with Runner. Use Runner.run() for async, Runner.run_sync() for synchronous, or Runner.run_streamed() for streaming.

When to apply

Starting point for any agent integration using the OpenAI Agents SDK. Use when you need the simplest single-agent turn with a text reply.

Core snippet

import asyncio
from agents import Agent, Runner

agent = Agent(
    name="Assistant",
    instructions="You only respond in haikus.",
)

async def main():
    result = await Runner.run(agent, "Tell me about recursion in programming.")
    print(result.final_output)

asyncio.run(main())

Variants

# Synchronous (blocks)
result = Runner.run_sync(agent, "Hello!")
print(result.final_output)

# Streaming
result = Runner.run_streamed(agent, "Tell me 5 jokes.")
async for event in result.stream_events():
    # handle events
    pass

Key properties

Agent(name, instructions) — minimum required fields
result.final_output — the text output of the last agent turn
Default model is gpt-4o; override with model="gpt-4o-mini" on the Agent
Runner.run() wraps a loop: model call → tool calls → model call until final output

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.