run-locally

Launch the agent locally and test API endpoints via curl.

Updated Mar 17, 2026
One-click install
npx skills add https://github.com/AshDax/sec_scrapper_agent --skill run-locally-ashdax
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: run-locally
Source: https://github.com/AshDax/sec_scrapper_agent/tree/main/agent-openai-agents-sdk/.claude/skills/run-locally
Command: npx skills add https://github.com/AshDax/sec_scrapper_agent --skill run-locally-ashdax

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Run and test the agent locally, enabling fast iteration and verification.

Core Features & Use Cases

  • Start the server locally with the recommended commands to run the agent at http://localhost:8000.
  • Test the agent's API endpoints using curl and perform lightweight evaluation workflows.
  • Troubleshoot issues by adjusting server options, port, or worker settings for development.

Quick Start

Start the server locally by running uv run start-app to launch the agent.

Frequently Asked Questions about run-locally

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run and test my agent locally for rapid iteration?▼

You can test API endpoints locally using curl commands against the running server to perform lightweight evaluation and verify your agent's responses during development.

Can I configure the port and worker settings for local server startup?▼

Local agent testing integrates with MLflow for experiment tracking, allowing you to log evaluation parameters, metrics, and artifacts to monitor and compare model performance across iterations.

What do I need to set up my environment before running the agent locally?▼

You need to enforce proper environment setup and execute the uv run start-app command to launch the agent server locally, enabling validation workflows across development scenarios.

Why is my local agent server not working during troubleshooting?▼

Local agent server issues during troubleshooting can often be resolved by adjusting server options, changing the configurable port, or modifying worker settings to match your development environment constraints.