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.

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.

If you are calling the Claude API repeatedly with a large system prompt, a big document, or a long codebase context — and you are not using prompt caching — you are paying full price every time for content that has not changed. Prompt caching stores a prefix of your prompt server-side and charges 90% less to read it back on every subsequent request. For applications that repeatedly process the same context, this is the single highest-impact API optimisation available.

Most AI assistants are chatbots. You ask, they answer, the interaction ends. The interesting shift happening right now is treating AI as an autonomous worker — something that runs on a schedule, produces real artifacts, and delivers results without you being in the loop. This post walks through building that kind of assistant: a background agent that runs weekly, researches a set of topics relevant to your work, and delivers a structured briefing via Telegram or email.

Tools like ESLint, Semgrep, and Bandit catch what they are programmed to find: known patterns, common injection strings, deprecated API calls. They are fast, reliable, and deterministic. They are also blind to anything that requires understanding what your code is supposed to do. Claude Code operates differently. It reads code the way a human security researcher would — tracing data flows across files, understanding business logic, and reasoning about what could go wrong given the specific context of your application.

Most teams use Claude Code reactively — they type a prompt, Claude responds, they type another. That is fine, but it leaves significant value on the table. Claude Code has four automation layers that let you turn it from a reactive assistant into an active workflow participant: Layer What it does When to reach for it Hooks Shell or HTTP calls that fire on lifecycle events “This must happen every time, without exception” Custom Commands Reusable slash commands for repeatable prompts “I type the same prompt repeatedly” Skills Context-aware instructions Claude loads automatically “Claude should always do X when working on Y” Subagents Separate Claude instances for isolated, parallel work “This task is noisy and the main session only needs a summary” This post covers how to create each one and when to use them.

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.