skills.rest
tinner-deinno
tinner-deinnoCOMMUNITY
Explore all skills by this author →
GitHub

model-copilot

Sends prompts to GitHub Copilot-capable models with selectable model IDs and token usage logging.

1|Updated May 24, 2026
Search Tags:#code review#api integration#reasoning#model routing#prompting#github copilot#token auth
One-click install
npx skills add https://github.com/tinner-deinno/innova-skills-lib --skill model-copilot
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: model-copilot
Source: https://github.com/tinner-deinno/innova-skills-lib/tree/main/core/model-copilot
Command: npx skills add https://github.com/tinner-deinno/innova-skills-lib --skill model-copilot

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It eliminates the friction of sending prompts from your workflow to GitHub Copilot-capable models, so you can quickly get high-quality responses without manually switching between providers or model endpoints.

Core Features & Use Cases

  • Model routing for GitHub Copilot: Sends your prompt to selectable models (defaulting to gpt-4o) to match the job type (coding, reasoning, summarization).
  • Copilot authentication via token: Uses GITHUB_COPILOT_TOKEN from ~/Jit/.env as a Bearer token for authorized access through the GitHub Models Marketplace API.
  • Operational commands and visibility: Supports listing available models, checking status (token + connection), and returning results with attribution to the chosen model; also logs telemetry to token_log.jsonl.

Example use case: when you need a code review, you can route to claude-3.5-sonnet via Copilot; when you need deeper reasoning about logic or bug-hunting, you can route to o3-mini; when you need a fast summary, you can route to gpt-4o-mini.

Quick Start

Ask for a model-specific response by running: /model-copilot "Explain the architecture of the มนุษย์ Agent system".

Frequently Asked Questions about model-copilot

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

FAQPage Schema
How do I route prompts to GitHub Copilot models for code review and reasoning?▼

To route prompts to GitHub Copilot models, you send your text to selectable models like gpt-4o or claude-3.5-sonnet. This applies to coding assistance, deep reasoning, and fast summarization tasks without manual provider-specific setup.

What token do I need to authenticate with the GitHub Models Marketplace API?▼

You need a valid GITHUB_COPILOT_TOKEN with copilot scope, stored in ~/Jit/.env. This token is used as a Bearer token for authorized access through the GitHub Models Marketplace API.

Can I select specific models like o3-mini or gpt-4o-mini for different tasks?▼

Yes, you can select specific models for different tasks using command flags. Route to claude-3.5-sonnet for code review, o3-mini for deeper reasoning, or gpt-4o-mini for a fast summary.

How do I check connection status and list available GitHub Copilot models?▼

You can check connection status and list available GitHub Copilot models using the built-in list and status operations. These operations verify your token and return the selectable models you can route prompts to.

Does the GitHub Copilot model router log token usage and telemetry data?▼

Yes, the GitHub Copilot model router logs token usage and telemetry data to a token_log.jsonl file. It also returns results with attribution to the chosen model for tracking purposes.

What is the best way to send prompts to GitHub Copilot without manual provider setup?▼

The best way to send prompts to GitHub Copilot without manual provider setup is using an automated model routing skill. It eliminates friction by handling endpoint selection and authentication via the GitHub Models Marketplace API.

Related Skills

Explore More Software Engineering Skills→
DevMHOneDevMHOne

omni-auth

Authenticate NextRoute API sessions with Bearer tokens and session cookies.

Community
Intermediate
tinner-deinnotinner-deinno

model-GPT

Sends prompts to the OpenAI API with automatic model selection and token logging.

Community
Intermediate
CowboyLogicCowboyLogic

copilot-prompt-creator

Create task-specific GitHub Copilot prompts informed by official documentation.

Official
Intermediate
SteveGJonesSteveGJones
3

ollama-image

Generate images locally from prompts using Ollama models.

Community
Advanced