GitHub Copilot Links
Lyle’s curated collection of GitHub Copilot links and resources
Agents
-
AGENTS.md The generic general guide to creating agents.
-
YouTube: Multi-agent workflows in VS Code (VS Code Channel) Demo on how you launch and run multiple agents in the background
-
YouTube: Agent Skills in VS Code (James Montemagno) How to build your own agent skill and use it in VS Code
-
YouTube: The complete guide to Agent Skills (Burke Holland) A comprehensive walkthrough of creating and using agent skills
-
YouTube: After This Video, You’ll Actually Understand Agent Orchestration (Burke Holland)
-
Enabling 3rd Party Agents in VS Code How can you enable 3rd party agents like Claude Code in VS Code
-
AGENTS.md outperforms skills in our agent evals - Vercel (Jan 2026) They got different results when putting data in AGENTS.md vs putting in just skills…?
Agentic Workflow
Boards
Azure DevOps
- Azure DevOps Remote MCP Server (public preview) - Azure DevOps Blog (March 17, 2026)
Jira
- GitHub Copilot coding agent for Jira is now in public preview - GitHub Changelog
- Integrate Jira with GitHub | Atlassian Support — Note: To make this work, you have to pay $ for: Atlassian Rovo
Cheat Sheets
What feature should I use?
Code Indexes
- Indexing repositories for GitHub Copilot - GitHub Docs
- How Copilot understands your workspace (VS Code Site - Copilot section) — Talks about the code index and local vs remote index and GH vs AzDO indexing
Copilot CLI
-
Install it: https://github.com/features/copilot/cli
-
YouTube: You need to try the GitHub Copilot CLI right now! (Burke Holland)
-
YouTube: Getting Started with GitHub Copilot CLI and Work IQ (John Savill - March 2026)
Copilot SDK
-
YouTube: The GitHub Copilot SDK is out!
-
YouTube: GitHub Copilot SDK Tutorial: Build AI Apps with Live Coding
-
YouTube: GitHub Copilot SDK demo: Creating “Flight School” Chris Reddington demonstrates “Flight School,” a custom Next.js application built to personalize his learning journey using the GitHub Copilot SDK. See how he leverages agentic workflows to generate daily coding challenges based on his GitHub profile, evaluate solutions against test cases, and automatically export projects to new repositories.
General Repos
Learning Paths
Models
- AI model comparison - GitHub Docs
- Hosting of models for GitHub Copilot Chat - GitHub Docs (where hosted, no training, no retention, etc.)
- Enterprise bring your own key (BYOK) for GitHub Copilot is now in public preview - GitHub Changelog (Nov 20, 2025)
Model Usage
Suggestions for Model Usage (a proposal - not final!)
This is not official in any way, just guidance based on my experience and the resources above. No need to argue with me or tell me I’m wrong, just try it out and see if it works for you. Your mileage may vary, and the best way to find out is to experiment with different models for different tasks and languages and see what works best for you.
| SDLC Phase | Recommended Model | Rationale |
|---|---|---|
| Planning/Requirements | GPT-5.4 (High) | Multi-step problem solving and architecture-level code analysis |
| Architecture | GPT-5.4 (High) | Complex reasoning, system design trade-offs |
| UI/UX Design | Claude Opus 4.6 | Best for CSS, visual design, layout, frontend work |
| Development | GPT-5.3-Codex (High) | Code-specialized model, best for implementation |
| Code Review | Claude Opus 4.6 or Sonnet | Good for review without heavy compute |
| Testing | GPT-5.3-Codex (High) | Code-aware model great for test generation |
| Documentation | Claude Haiku or GPT-5.4 Mini | Fast, reliable answers to lightweight coding questions |
| Deployment/DevOps | GPT-5.3-Codex (High) | Agentic tasks, IaC, pipeline YAML, scripting |