Devops Monk

Claude’s computer use capability — the ability to see your screen and interact with applications via mouse clicks, keyboard input, and scrolling — is one of the most discussed features in the AI space. It is also one of the most misapplied. The correct mental model is not “Claude can now automate everything on my screen.” It is “Claude now has a flexible fallback layer for tasks that do not have a structured API integration.

If you have been using Claude in a browser tab to help with code, you are leaving most of its capability on the table. Claude Code CLI brings the full power of Claude directly into your terminal — it reads your actual codebase, runs real commands, edits files, commits code, and integrates with every tool in your DevOps stack. This guide covers everything from installation to advanced patterns that most engineers never discover.

The MCP (Model Context Protocol) ecosystem now has over 14,000 servers. Most of them you do not need. Installing too many slows responses, inflates your context window with tool definitions that never get used, and turns debugging into a guessing game across a dozen integrations. This guide applies a simple filter: only install a server if it replaces a daily copy-paste workflow. It is organised by role — developers, QA testers, and DevOps/platform engineers — because the right stack is different for each.

Token usage with Claude Code follows a frustrating pattern: costs are not spread evenly — they cluster around a handful of bad habits. Most developers using Claude Code daily are burning 40–60% more tokens than they need to, simply because of how they phrase prompts, what they put in CLAUDE.md, and which model they reach for by default. This guide covers five concrete changes that make an immediate difference. Why Tokens Are Worth Caring About Every message you send in a Claude Code session includes:

The /loop command in Claude Code lets you schedule a prompt to repeat at a regular interval within an active session. It is one of the less-documented features, and it is also one of the most misunderstood — particularly around what it cannot do. This post explains what /loop actually is, the three scenarios where it genuinely earns its keep, and where cron jobs remain the better choice. What /loop Does /loop 5m check if the Vite dev server is still running and report any new errors This runs the prompt immediately, then repeats it every 5 minutes for the duration of your session.

Every CLAUDE.md file gets loaded into context on every session. Most teams treat it like documentation — a place to describe the project, list the tech stack, explain what the tests do. That is the wrong mental model and it is why most CLAUDE.md files are both too long and too ineffective. CLAUDE.md is behavioral programming. Its job is to change how Claude makes decisions, not to describe facts that Claude can read from the codebase itself.

There is a tendency in the AI tooling space to reach for frameworks — LangChain, AutoGen, CrewAI, OpenClaw — the moment you want an AI that does more than answer one question at a time. Most of the time, that is the wrong move. The framework adds complexity, dependencies, and debugging surface area for problems that a few shell scripts and cron jobs solve perfectly well. Claude Code’s headless mode (-p flag) plus a markdown file for personality plus cron scheduling is a complete AI assistant stack.

If you run a home server — a Raspberry Pi, a NAS, a Kubernetes cluster in your garage — you have probably hit the same annoying wall: your internet provider gives you a different public IP address every few days, and suddenly nobody can reach your server anymore. This post explains how I solved that problem by building ddns.devops-monk.com, a fully self-hosted Dynamic DNS platform. I will walk through the idea from scratch, explain every moving part in plain English, and include full architecture diagrams for those who want the deep technical picture.

When you build custom Helm charts for your organisation, you need somewhere to store and distribute them. Public registries like Artifact Hub are not suitable for internal charts. ChartMuseum is an open-source Helm chart repository server that you can run on your own infrastructure — with support for local storage, AWS S3, GCS, Azure Blob, and more. How It Fits Into Your Workflow flowchart LR Dev[Developer] -->|helm package| Chart[chart.tgz] Chart -->|curl POST| CM[ChartMuseum Server] CM -->|stores in| Storage[Local / S3 / GCS / Azure] CI[CI Pipeline] -->|helm install| CM Cluster[Kubernetes Cluster] -->|pulls chart| CI ChartMuseum exposes a standard Helm repository API — any Helm client can add it as a repository and install charts from it exactly like any public repo.

Helm is the package manager for Kubernetes — the same idea as apt on Ubuntu or npm in Node.js, but for deploying applications to your cluster. Instead of writing and maintaining dozens of raw Kubernetes YAML files per application, you define a chart once, parameterise it with values, and deploy it consistently across every environment. Note: Helm 4 was released in 2025 with breaking changes. This guide covers Helm 3, which remains widely used and supported.