---
title: Using Claude Code
---

Claude Code is Anthropic's agentic coding assistant — a tool you talk to in plain language that reads your codebase, edits files across a project, runs commands, and works with your other tools. These pages collect how I actually use it day to day, so the notes are practical rather than exhaustive.

## What it is

You describe a task; Claude gathers context by reading files and running commands, makes the changes, and checks its own work. You stay in the loop the whole time — review its plan, approve edits, redirect it mid-task, or stop it and take over. The mental model that makes it click: it's a conversation, not a one-shot generator. The quality of the result tracks the quality of your steering.

It runs in the terminal, in the VS Code and JetBrains extensions, in a desktop app, and on the web — all driving the same engine, so your configuration and instructions travel with you.

## What I use it for

- **Features and fixes** across several files at once, with the architecture in view rather than one file at a time.
- **Exploring unfamiliar code** — "explain how auth works here" before I touch anything.
- **The tedious stuff**: tests for untested code, lint sweeps, dependency bumps, one-off migration scripts.
- **Anything runnable from a shell**: builds, Docker, deploy scripts, digging through logs.

> *TODO (Chris): add a line or two on what you reach for Claude Code for most.*

## Start here

<PageRef space="notes" slug="claude-code-getting-started" />

<PageRef space="notes" slug="claude-code-workflow" />

<PageRef space="notes" slug="customizing-claude-code" />