Brief

The developer tool mcp-probe has released version 1.5.0, introducing a new 'doctor' command. This command performs preflight checks on a repository to ensure it is correctly configured for running MCP readiness checks within a Continuous Integration (CI) environment. It verifies Node.js runtime, the existence and validity of configuration files, sidecar files, and GitHub Actions workflows that invoke mcp-probe, aiming to catch setup errors early. AI

This post introduces a method for testing changes to large language model prompts, treating them as code migrations rather than simple edits. It proposes a 50-line Python script that runs evaluations against two prompt versions, calculates the difference in output scores, and uses bootstrapping to determine statistical significance. This approach aims to prevent subtle prompt changes from degrading model performance without immediate detection, ensuring quality is maintained across different user segments. AI

Anthropic is implementing a separate billing structure for its Claude Agent SDK and programmatic CLI usage, effective June 15th. This change will split the existing unified usage pool into two distinct pools: one for interactive use and another for automation. Users who rely on tools like `claude -p`, GitHub Actions, or the Agent SDK for automated tasks will now draw from this separate automation pool, which has its own monthly credit allocation and potential for extra usage billing. AI

The author details a process for automating blog deployment using GitHub Actions. This automation was implemented after switching from WordPress to the Hugo static site generator, which initially still required manual deployment steps. The new workflow streamlines the process of publishing blog content. AI