Our verdict
Being tested. An editor is using Claude Code hands-on; the verdict and score appear here once they sign it off.
What it does
Claude Code is Anthropic’s coding agent. You describe a task in plain English, and it reads your code, plans the work, edits files, runs tests and can open pull requests, asking you when a decision needs your input.
It works in the terminal, in VS Code and JetBrains editors, in the Claude desktop and mobile apps and on the web. It is made for developers, and it shares its usage allowance with your Claude plan.
Why use it
- It can take a task from plan to tested change from one instruction.
- It works in the terminal, VS Code, JetBrains IDEs, the Claude apps and the web.
- You can start tasks from your phone or from Slack and check on them later.
- It comes with paid Claude plans, sharing one usage allowance with Claude chat.
How it works
- Subscribe to a paid Claude plan, or set up a pay-as-you-go API account.
- Install it in your terminal or editor, or open claude.ai/code in your browser.
- Sign in and open the project you want to work on.
- Describe the task in plain English and answer any questions it asks.
- Review and test its changes before you keep them.
How hard is it to use?
Advanced Made for people at home with technical tools, or ready to learn them.
Made for developers: you need to read and judge code to use it safely, which is why we rate it Advanced.
What it costs
Included with paid Claude plans. The free Claude plan doesn’t include it. Pro and Max plans do, with Max allowing much more use; Team and Enterprise plans include it for organisations, and you can also pay as you go through an API account.
Prices change often, so check Claude Code’s own site before you pay.
Watch out for
- Review its changes carefully: it can misread a task or introduce subtle bugs.
- Long tasks use up your plan’s allowance quickly, and extra usage is charged at API rates.
- Give it access only to the files, commands and accounts it needs, especially on work machines.
Your data
On Pro and Max plans, you choose in Claude’s privacy settings whether your coding sessions can help train Anthropic’s models; if you allow it, data is kept for up to five years rather than 30 days. Team, Enterprise and API use isn’t used for training unless the organisation opts in.
We haven’t confirmed that Claude Code can keep your data in the UK, so check where it keeps your data before you share anything private or about other people.