models-config

Edit and validate multi-provider models.json for Anthropic and OpenAI endpoints.

18|3|Updated Jan 8, 2026
One-click install
npx skills add https://github.com/Dwsy/agent --skill models-config
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: models-config
Source: https://github.com/Dwsy/agent/tree/main/skills/models-config
Command: npx skills add https://github.com/Dwsy/agent --skill models-config

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates configuring and validating multi-provider models.json to simplify model deployment, pricing alignment, and testing.

Core Features & Use Cases

  • Edit and manage ~/.pi/agent/models.json across providers (Anthropic, OpenAI) with built-in protocol support
  • Auto-fetch and apply model pricing from models.dev to keep costs accurate
  • Validate JSON structure and test endpoints using multi-protocol curl commands

Quick Start

Edit ~/.pi/agent/models.json to add providers and models, then run the price updater to refresh costs.

Frequently Asked Questions about models-config

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

FAQPage Schema
How do I sync model pricing from models.dev into my local configuration?

You can sync model pricing by running the price updater to automatically fetch and apply current per-model costs from the remote models.dev API directly into your local configuration file, ensuring accurate deployment costs.

What is the best way to validate a multi-provider models.json file?

Validating a multi-provider models.json file is best handled by running built-in JSON schema checks to verify structural integrity and ensure provider endpoint configurations are correctly formatted.

Can I test OpenAI and Anthropic endpoints using curl variations?

Yes, you can test OpenAI and Anthropic endpoints by executing multi-protocol curl commands generated by the configuration tool to verify connectivity and response behavior across different providers.

How do I edit and manage model endpoints for multiple providers?

You edit and manage model endpoints for multiple providers by modifying the central models.json file, which supports built-in protocol configurations for Anthropic and OpenAI to streamline deployment.

Does this approach support deterministic scripting for local cost mutation?

Yes, the approach supports safe, deterministic scripting for local cost mutation, allowing you to programmatically update per-model pricing and configuration values without risking inconsistent state.