Skip to content

Test your website now

Free, no card. We read only public pages.

Run free audit →

Vibe coding tools

What is Claude Code?

Claude Code is Anthropic's coding agent for the terminal, IDE, desktop and web. What it does, which plans include it in November 2026, and how to use it safely.

Claude Code is Anthropic's agentic coding tool. It works in your codebase: it reads files, plans changes, edits code across files, runs commands and tests, and handles Git, from the terminal, IDE extensions, a desktop app or the web. It is included in Claude Pro, Max, Team and Enterprise plans, or can be billed through the Claude API.

Published · Last updated

By Michal Měřínský. Audit methodology.

What Claude Code does

  • Understands a repository by reading and searching its files.
  • Plans and makes multi-file changes, then runs tests and fixes failures.
  • Runs commands with your permission, such as installing packages or running migrations locally.
  • Works with Git: branches, commits and pull request descriptions.
  • Connects to external tools and data through MCP servers.
  • Runs in a terminal, in VS Code and JetBrains through extensions, in a desktop app and on the web.

Which plans include it

Anthropic's pricing page on 9 November 2026 lists Claude Code in Pro, at 17 dollars a month billed annually or 20 dollars monthly, Max from 100 dollars a month, Team and Enterprise. It is not included in the free plan. Claude Code shares usage limits with chat on the same plan, and can also be used with pay-as-you-go API billing.

Using it safely

  • Keep the default permission prompts on for commands and file edits until you trust the setup.
  • Commit before large tasks and review the diff before merging.
  • Write a CLAUDE.md file in the repository with commands, conventions and rules, such as never putting secrets in frontend code.
  • Keep .env files and credentials out of what the agent reads, or deny access explicitly.
  • Be careful with MCP servers and external content: instructions hidden in web pages or files can try to steer an agent.

An agent with your terminal has your permissions. Use allowlists for commands and keep production credentials off the machine you develop on.

Who it suits

Developers who want to delegate whole tasks, from features and refactors to debugging and test writing, while staying in control through review. It is also used by non-developers on simpler projects, with the same need to check what ships.

What a scan can and cannot tell you

WebAuditOS checks the deployed site Claude Code helped build: security headers, console errors, duplicate titles, error disclosure and the rest of the technical basics.

It cannot see your repository or Claude Code's changes.

A useful loop: scan the site, give Claude Code the findings with their evidence, let it fix them, then scan again.

Short answers

Is Claude Code free? No. It is included in paid Claude plans or billed through the API.

Is Claude Code the same as Claude? No. Claude is the assistant. Claude Code is the coding agent that works in your codebase.

Does Claude Code work in VS Code? Yes, through an extension, as well as in the terminal and other surfaces.

Can Claude Code deploy my app? It can run your deploy commands with permission. Review before anything reaches production.

In the product

The checks this maps to

Every check named here runs on every scan, on every plan - what a plan changes is how many pages are crawled, how long the history is kept and what you can do with the result. These are the ids the findings carry, so you can match a line in a report to the explanation above.