Enabling Consistent AI-Assisted Engineering with GitHub Copilot Plugins

When an engineer or team creates useful agentic artifacts for their daily work (e.g., instructions, skills, and MCP configurations), others naturally want to adopt them when they see how those artifacts could help with their own work. Sharing the files is straightforward, but keeping those consumers supplied with fixes, updated guidance, and compatible tool configurations requires a way to maintain and distribute those artifacts. That challenge shaped our work with a large enterprise customer as we designed and built a migration and modernization toolkit together. Their internal and third-party engineering teams needed a consistent way to apply the customer’s architecture guidance, tools, and delivery practices while modernizing thousands of applications. We packaged and distributed those capabilities through GitHub Copilot plugins, and we’ll walk through the choices we made, the trade-offs behind them, and how you can adapt the approach to your own engineering workflows. This work applied platform engineering practices to AI-assisted engineering workflows. We maintained shared capabilities as a versioned toolkit that teams could…