Devops Monk

A Claude Code session is your working context — conversation history, file state, permissions, and memory. Understanding how sessions work and how to manage them unlocks the ability to parallelize work, switch contexts without losing state, and recover from mistakes instantly. This guide covers session fundamentals, parallel work patterns, and five developer habits that compound over time. What Is a Session? A session is: Directory-scoped, not branch-scoped — tied to a folder location, not a git branch Persistent across context limits — survives /compact and /clear Shareable — /rename and /resume to switch between named sessions Isolated — each session has its own context window, permissions, memory Critical distinction: Sessions follow your directory, not your branch.

A sub-agent is a specialized Claude instance that runs in an isolated context window with its own allowed tools, memory, and instructions. While your main Claude session handles the conversation, a sub-agent spins up to handle a specific task — investigation, code review, security audit, testing — in parallel with your work. Sub-agents excel at tasks that require: Reading many files without cluttering main context Specialized expertise in one domain Fresh perspective (the agent isn’t biased by earlier conversation) Parallel execution (multiple agents working simultaneously) Sub-Agents vs Skills vs Hooks Before diving into sub-agents, understand the distinctions:

A Skill in Claude Code is a specialized workflow that Claude can invoke automatically or you can trigger manually with a slash command. Unlike CLAUDE.md rules (which advise on every decision) or Hooks (which enforce deterministic actions), Skills are progressive disclosure — deep knowledge that loads only when relevant, keeping your base context lean while providing specialized expertise when needed. This guide covers how Skills work, when to use them, and how to build real Skills that serve developers, testers, and DevOps engineers.

I was tired of bouncing between a dozen different sites just to format JSON or decode a JWT. One tab for a JSON formatter. Another for a Base64 decoder. Another for a DNS lookup. Another for an SPF validator. Browser full of bookmarks, half of them plastered with ads, most requiring an account to do anything useful. So I built MonkKit — a single place for all of them. 106 free developer tools across 10 categories.

Skills, agents, and hooks you add to .claude/ are powerful — but they are locked to one project. Every time you start a new repo you copy the same files, maintain them in multiple places, and drift out of sync. Claude Code plugins solve this: a plugin is a shareable, versioned package that carries all your customisations and can be installed in any project with one command. This post covers what plugins are, when to use them, and how to build a real one from scratch — a DevOps helper that ships a deployment skill, a pre-deploy safety hook, and an MCP server connection to your Kubernetes cluster.

Building an e-commerce site is one of those projects that sounds simple until you actually start. Payments, authentication, inventory, personalisation, image handling, email notifications, admin tools, live chat — each piece is its own rabbit hole. I built PersonalisedGifts, a full UK-market personalised gifts store from scratch, wiring all of these together into a single cohesive product. The site lets customers browse gifts by category (Mugs, Jewellery, Canvas Prints, Home Décor) or occasion (Birthday, Wedding, Christmas, New Baby), personalise their chosen item with custom text, images, fonts, or colours, and pay via Stripe (cards, Apple Pay, Google Pay, Klarna) or directly from their bank account via Tink’s open banking integration.

Claude Code can read and write files, execute shell commands, and search your codebase. But here’s the problem: it lives in isolation. It can’t talk to your database. It can’t query your Jira board. It can’t inspect network requests in your running app. It can’t access your AWS infrastructure. Without MCP, Claude Code is smart but limited. With MCP (Model Context Protocol), Claude Code becomes a full participant in your development ecosystem—talking to databases, APIs, monitoring systems, and custom tools in real-time.

By default, Claude generates its response token by token without any deliberate planning step. For most tasks — answering a question, writing a function, explaining a concept — this is fine. The response comes quickly and it is good. For some tasks, it is not enough. Complex multi-step reasoning problems, ambiguous architecture decisions, intricate security analyses — these benefit from Claude thinking through the problem before committing to an answer. That is what extended thinking and adaptive thinking provide.

Building an AI agent that runs autonomously — browses the web, executes code, reads and writes files, persists memory across sessions — requires infrastructure. You need a sandbox, a process that can run for hours without your web server timing out, and a way to resume from where you left off after a network hiccup. Claude Managed Agents, launched in public beta in April 2026, offloads all of that to Anthropic.

Picking the wrong Claude model is expensive. Opus on every task costs 5x more than Sonnet for comparable results on most work. Haiku on a complex reasoning task produces worse output than just asking Sonnet. And if you are still using models from early 2025, some of them are deprecated — or will be soon. This guide covers every current Claude model, what each is good at, how much they cost, and a concrete decision framework for choosing the right one.