// Context Engineering

In this episode, we recap the latest GitHub changelog updates including Copilot coding agent availability for pro users and the new Playwright MCP browser capability. We update Copilot custom instructions and setup steps for a GitHub Action project, use the Playwright MCP server to build interactive UI features on a trend radar app, and leverage Copilot coding agent to identify and fix technical debt.

GitHub Copilot for Xcode now supports agent mode alongside the existing ask mode, with full Model Context Protocol (MCP) support for extending Copilot with additional tools. This video walks through toggling between ask and agent modes in the Xcode chat pane, configuring the GitHub MCP server via the Xcode MCP settings tab, and using agent mode to look up and prioritize repository issues. A hands-on demo shows Copilot diagnosing and fixing a premature form validation problem in an iOS app, verified in the simulator.

Getting the best results from the GitHub Copilot coding agent requires deliberate setup across four areas. This video covers writing well-scoped GitHub Issues with clear acceptance criteria and file pointers, crafting Copilot custom instructions to enforce team conventions and development flow, configuring a consistent development environment using Copilot setup steps, and extending Copilot's toolset with Model Context Protocol (MCP) servers configured from repository settings.

In this stream, Chris builds a GitHub CLI extension (gh-demo) in Go from scratch using a spec-driven development approach with Copilot Agent Mode. Topics include bootstrapping a VS Code workspace with Copilot, test-driven development for a hydrate subcommand, and setting up GitHub Actions CI.

Chris continues exploring Copilot Agent Mode and custom instructions by building a memory sequence game for the GitHub CLI extension project in Go. The changelog segment covers GitHub CLI accessibility improvements, Copilot Code Review expanding to all languages, Copilot Autofix updates, and the introduction of Copilot premium requests.

This episode dives deep into Copilot custom instructions — what they are, how to write them, and why they matter for guiding AI-assisted development. Chris reviews the GitHub Changelog including the credential revocation API, CodeQL improvements, and the GitHub Models playground's new prompt improvement feature, then live codes a higher/lower game for a Go-based GitHub CLI extension using Agent Mode with detailed custom instructions.

Chris explains what Model Context Protocol (MCP) is and demos the new GitHub MCP server alongside Copilot Agent Mode in VS Code. The stream covers creating repos and issues through MCP tools, then builds a strategy visualization app from a screenshot using agent mode, vision, and the Playwright and sequential thinking MCP servers.

Chris live-codes a GitHub-themed brick breaker walkthrough using Copilot agent mode, demonstrating how prompt framing, context, and custom instructions shape AI-generated output.

Chris introduces OctoSnap, a GitHub-themed memory card game built with Next.js, and dives deep into designing a scoring model with Copilot covering difficulty multipliers, time bonuses, and penalty mechanics.

This is a companion walkthrough for the hero Game of Life video that was published on the GitHub YouTube channel.