Learn how I built a custom Claude Code command to automatically detect unused Drupal modules by comparing Composer dependencies with enabled modules. This practical example demonstrates how AI-powered automation can streamline routine development tasks and keep your Drupal projects lean and maintainable. See the complete implementation and real-world output from my production site.

After upgrading to Docker 29.0, my entire Traefik setup suddenly stopped working, even the latest Traefik version failed to connect. The root cause turned out to be a breaking API change: Docker 29 now requires API 1.44+, while Traefik still uses 1.24. Until Traefik updates its Docker client, the only fix is to downgrade to Docker 28.5.2 and hold updates.

As developers, we often bounce between "just ship it" mode and "I should probably plan this," especially now when vibe coding is everywhere. Backlog.md bridges that gap elegantly. It's a markdown-native task manager that lives right in your git repo, bringing just enough structure without killing the flow.

I've been experimenting with Claude Code and other AI coding assistants for months now, and while they're incredibly helpful, I kept running into the same frustration. They know everything about Drupal and React hooks and Python decorators, but nothing about the specific commands and scripts in my projects. I finally decided to try MCP (Model Context Protocol) to see if I could fix this problem, and it worked better than I expected.

Claude Code subagents are specialized AI assistants designed for task-specific workflows. Each subagent has its own context window, system prompt, and tool permissions, allowing Claude Code to delegate tasks without cluttering the main conversation. This setup enables focused expertise, better context management, and reusable configurations for consistent and efficient development workflows.