Thomas Thornton Blog

I have been building and using agent skills across Claude Code, Codex and GitHub Copilot, alongside plugins such as Ponytail and Superpowers. I am using Microsoft Agent Package Manager (APM) to manage that collection through a shared manifest. My agent-setup repository holds the configuration and a copy of the global lockfile. The manifest declares what I want installed…

I wanted to send GitHub Copilot CLI telemetry to Azure Application Insights so I could query model requests, token usage and tool executions, including which skills were being used, with KQL. I used an OpenTelemetry Collector running on Azure Container Apps to receive telemetry from the CLI and forward it to Application Insights. The Collector provides an authenticated OTLP e...

If you’re looking for your Azure Log Analytics workspace keys in the portal and can’t find them, you can retrieve it directly with Azure CLI. I’d use with a query for the key I need and to return it without JSON quotes. Run the following command, replacing and with your resource group and workspace names: The argument selects the primary key from the response.

Every AI code review tool I have used or built reaches the same problem on a busy repository. The individual comments can certainly be useful, but after a few pushes the review becomes harder to use. The same finding returns, old comments remain beside newer ones, and some findings report a problem without giving the reviewer enough evidence to verify it. Better model output ...