What is Claude Code?
Claude Code is Anthropic's agentic coding tool, and you do not need to write code to use it. Here is what it actually does, where it runs, and whether it is for you.
Claude Code is Anthropic's agentic coding tool. It reads your project, edits files and runs commands, and it keeps working through a task instead of answering one question and stopping.
That word "coding" puts people off, and it should not. Most of what it does all day is read files, write files, move things around and run something for you. That is admin, not engineering.
So the useful question is not whether you can code. It is what you would hand to somebody who could sit at your machine and do the boring half of your week.
- What Claude Code actually is, and how it differs from Claude in a browser
- The 6 places it runs, and why that choice matters more than it looks
- What it can reach on your machine, and what it cannot
- Whether you need to be technical to use it
- What it costs, and which plans include it
And I'll show you what it actually is, where it runs, and whether you need to be technical at all.
What is Claude Code?
Claude Code is an agentic coding tool from Anthropic. It reads your codebase, edits files, runs commands and connects to the tools you already use.
The word that matters there is agentic. Claude in a browser answers you. Claude Code does the thing, checks whether it worked, and carries on.
For example, ask a chat window to rename 200 files and it writes you instructions. Ask Claude Code and the files are renamed.
How is it different from Claude in a browser?
It has hands.
Claude in a browser reads what you paste and writes back. It cannot open a file, save one, or run anything.
Claude Code works inside a folder on your machine. It reads what is there, changes it, runs commands, and can reach outside to other services.
So the real difference is not intelligence. It is the same model. It is access.
Where does it run?
In 6 places, and the choice matters more than it first appears.
The terminal, a desktop app, inside VS Code, inside JetBrains, in your browser, and in the Claude app on your phone.
The first 4 run on your machine and share the same configuration, project memory and connected tools, so all 4 read the same files. The web and the phone app run in the cloud by default and check out a repository instead.
But that is a default, not a limit. Run claude remote-control and your phone drives the session on your machine, with @ autocompleting your own file paths from the phone.
That split is worth holding on to. It decides where the folder holding your context has to live, which is the whole subject of an AI OS.
Do you need to be technical?
No, and the name is the only hard part.
You type in plain English. It asks before it changes anything, unless you tell it otherwise, and it can undo its own work.
What you do need is a project, meaning a folder on your machine that holds the thing you are working on. That is it.
What does it cost?
It needs a paid plan: Pro, Max, Team, Enterprise or Console. The free Claude.ai plan does not include Claude Code.
You can also point it at a third-party provider instead, such as Amazon Bedrock, Google Cloud's Agent Platform or Microsoft Foundry, and pay per use there.
No prices are published in the docs themselves, so anyone quoting you a figure is quoting a pricing page that moves.
What to do next
- Decide which of the 6 surfaces you want to start on
- Check your plan includes Claude Code, because the free one does not
- Pick the folder you would point it at first
- Install it, then give it your context, in that order
Claude Code questions
These are the ones people ask before they commit an afternoon to it.
Claude Code is Anthropic's agentic coding tool. It reads your project, edits files, runs commands and connects to other tools.
Agentic means it works through a task rather than answering a question and stopping. Install it here.
Same model, different access. Claude in a browser reads what you paste and writes back.
Claude Code works inside a folder on your machine, so it can open files, change them and run things.
No. You type in plain English, and it asks before changing anything unless you tell it not to.
The name is misleading for what most people use it for, which is reading, writing and moving files.
No. It needs Pro, Max, Team, Enterprise or Console, and the free Claude.ai plan does not include it.
You can also run it against a third-party provider such as Amazon Bedrock and pay per use instead.
In 6 places: the terminal, the desktop app, VS Code, JetBrains, your browser and the Claude mobile app.
The first 4 run on your machine. The web and the phone app run in Anthropic's cloud by default, but they do not have to: Remote Control connects either of them to a session running on your own machine, so your files and the commands stay on your computer. The conversation itself still passes through Anthropic while you are connected.
Only where you point it. It works in a working directory, and you add others deliberately with `/add-dir`.
It also asks before editing, unless you change the permission mode yourself.
Not on its own. Every session starts with an empty context window.
What carries over is what it reads on launch, which is `CLAUDE.md` and its own auto memory. That folder of files is what an AI OS is.
The boring half of a week: renaming and sorting files, pulling data out of documents, drafting from your own notes, running the same job every day.
It reaches other services too, so it can work with your drive, your calendar or your site rather than just the folder in front of it.
It asks first by default, and that default is worth keeping until you trust a given job.
It also checkpoints, so `/rewind` puts the conversation and the code back to an earlier point.
No. The desktop app runs the same engine with a window instead, and there are extensions for VS Code and JetBrains.
The terminal is 1 of 6 surfaces, not the price of entry. The install guide shows which is which.