Installing Claude Code

FEWD Studio works with any AI agent that writes to disk. Claude Code is the one we use ourselves, and the one most people ask about. This page explains what it is, why it behaves so differently from the AI you may have used inside a page builder, and how to install it.

If you just want the commands, skip to Installation.

What Claude Code is

Claude Code is a command-line tool from Anthropic. You open a terminal, go to a project folder, type claude, and you are in a session with an AI that can see and act on that project.

The important word is act. It is not a chat window that hands you a snippet to copy. Within the directory you started it in, it can:

• read any file, and follow imports across the codebase
• create, edit and delete files
• run shell commands (your build, your dev server, a git diff, a search)
• read the output of those commands and respond to it

So a request like “the mobile nav is broken below 640px, find it and fix it” is something it can genuinely attempt. It searches for the relevant selectors, opens the files, makes the change, and can run your build to check nothing broke.

Why this is a different category to page-builder AI

Most designers and developers meet AI first inside a tool: a prompt box in WordPress, a generate button in a page builder. Claude Code is not a bigger version of that. It is a different shape.

1. It has the whole project, not the current block

A prompt box inside a builder sees the element you are editing. It has no idea what your other components look like, what your token file contains, or what naming convention you have used for the last six months.

An agent in your project root reads all of it, so it can match your existing patterns. If you keep a CLAUDE.md or NOTES.md in the repo describing your conventions, it reads that every session and works to it.

2. Its tools are primitives, not a feature list

Builder AI can only do what the vendor built an action for. Claude Code’s tools are the shell and the file system, so the scope is “anything you could do at a command line”: rename a class across forty files, write a build script, generate components from a CSV.

3. The output is code you own

Files in your repo, in git, in a format any other tool can read. If you stop using the agent tomorrow, you keep everything it made.

A caveat

If you are not working in a codebase and do not want to be, a prompt box inside the tool you already use is the better fit. Claude Code assumes you are comfortable in a terminal and that your work lives in a git repo.

How this fits with FEWD Studio

FEWD Studio and a terminal agent solve different halves of the same job.

Claude Code is strong at reasoning across a whole codebase: refactors, wiring, scripts, anything that touches many files. It is weak at anything visual, because it cannot see your layout.

FEWD Studio is the opposite: the live node tree and round-trip visual editing give you direct manipulation of the thing you are looking at, written straight back to disk as real code.

Because both write to plain files in the same repo, you can move between them freely. Restructure with the agent, then open FEWD and adjust by eye. There is no import step and no sync. It is also why FEWD is not tied to Claude Code: Cursor, Gemini CLI or anything else that writes to disk works the same way.

See also Working with an AI agent.

Before you start

You will need:

• A supported OS. macOS 13+, Windows 10 (1809+), or Ubuntu 20.04+ / Debian 10+ / Alpine 3.19+.
• A terminal. Terminal or iTerm on macOS, PowerShell on Windows.
• A paid Claude account. Claude Code requires a Pro, Max, Team, Enterprise or Anthropic Console account. The free Claude.ai plan does not include it.

You do not need Node.js. The installer downloads a self-contained binary.

Installation

Step 1: Run the installer

macOS, Linux or WSL:

curl -fsSL https://claude.ai/install.sh | bash

Windows PowerShell:

irm https://claude.ai/install.ps1 | iex

macOS via Homebrew (an alternative, if you prefer brew):

brew install --cask claude-code

The native installer keeps itself updated in the background. Homebrew installs do not, so run brew upgrade claude-code yourself from time to time.

Step 2: Fix your PATH if needed

The installer usually finishes with a “Setup notes” warning that ~/.local/bin is not on your PATH. If you skip this, claude comes back as command not found even though the install succeeded.

Run the line that matches your shell. If you are not sure which you use, run echo $SHELL first.

zsh (the macOS default):

echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.zshrc
source ~/.zshrc

bash:

echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bash_profile
source ~/.bash_profile

If you use both shells at different times, add it to both files. It is harmless to have it twice.

Step 3: Verify the install

claude --version

Step 4: Start a session

cd ~/path/to/your-project
claude

The first run opens your browser to authenticate. Log in with the Claude account from the prerequisites, and you are in.

This is easier in FEWD Studio. Open a project, open the terminal, and you are already in your project folder. Type claude and it starts.

Step 5: Try it on something small

A good first test on an existing project:

Read through this project and summarise the structure, the CSS conventions in use,
and anything that looks inconsistent.

It costs a minute, and tells you straight away whether it has understood your codebase.

Useful commands

Command	What it does
claude	Start an interactive session in the current directory
claude --version	Print the installed version
claude doctor	Diagnostics: install health, settings errors, update status
claude update	Apply an update immediately instead of waiting
/help	Inside a session, list the available slash commands

Troubleshooting

claude: command not found right after a successful install. Almost always the PATH issue in step 2. Run the export PATH line, open a new terminal window and try again.

The install command errors out. On Windows, if you see The token '&&' is not a valid statement separator, you are in PowerShell but ran the CMD command. If you see 'irm' is not recognized, you are in CMD but ran the PowerShell one. Your prompt shows PS C:\ in PowerShell.

It runs but will not authenticate. Confirm your Claude plan includes Claude Code. The free tier does not.

Anthropic’s full setup and troubleshooting docs are at code.claude.com/docs/en/setup.

A note on cost

Claude Code uses a lot more tokens than a prompt box does. It reads whole files, holds a large amount of context, and loops through tool calls to check its own work. That is the mechanism by which it is useful.

On a subscription plan, sustained agentic work is absorbed by a flat monthly fee rather than metered per generation. There are still session and weekly usage caps, and heavy use will find them, so it is not unlimited, but the cost of asking it to do something ambitious is predictable.