The Problem # After months of building Claude Code extensions (agents, skills, commands, hooks, MCP servers) I had a growing collection of powerful tools with no coherent entry point. Want to pull all repos? Run a shell script. Want to check infrastructure health? Ask Claude and hope it knows which command to use. Want to automate a browser task? Figure out whether to use the MCP plugin or write a script.
The Challenge # I’ve been running a homelab for years, constantly deploying new services, debugging issues, and learning from mistakes. Every time I solve a particularly gnarly problem or build something interesting, I think, “I should write this up.” And then I don’t.
The friction is real. By the time I finish a project—maybe deploying Wazuh XDR or migrating from Watchtower to WUD—I’m mentally done. The last thing I want to do is sit down and reconstruct what I did, sanitize my internal network details for public consumption, and format everything into a proper blog post. The motivation is there when I’m in the middle of solving a problem, but it evaporates the moment I’m done.
The Problem # Watchtower had been my go-to for automatic Docker container updates across 8+ services. It worked… mostly. But I kept running into issues:
Opt-out model is dangerous - Watchtower watches ALL containers by default. I had to remember to add com.centurylinklabs.watchtower.enable=false to containers I didn’t want updated. Forgetting meant surprise updates.
No visibility - Updates happened silently at 4 AM. I only knew something updated when it broke. No dashboard, no easy way to see pending updates.
Overview # This site uses a hybrid content structure that combines the best of wikis and blogs. Instead of choosing between “everything chronological” or “everything by topic,” we get both:
Wiki sections for evergreen reference content (organized by topic) Blog posts for journey updates and lessons learned (organized by date) Tutorials for step-by-step guides (standalone, searchable) Series for multi-part deep dives (linked learning paths) Content Architecture #
AI-augmented homelab operations — from multi-agent orchestration to automated content pipelines. This wiki documents how Claude Code and agentic patterns accelerate infrastructure work.
4-Layer Agentic Architecture # A framework for organizing AI-assisted automation into composable layers:
4-Layer Agentic Architecture — Justfile → Commands → Skills → Agents: how each layer has a single responsibility Skill Development # Building custom Claude Code skills for repeatable workflows:
