Coding agents

Claude-Code

Claude-Code is a bot operated by Anthropic that pulls documentation and examples while an AI writes code. Claude Code is an AI coding agent by Anthropic that can build, debug, and ship code directly from the terminal, handling tasks like codebase onboarding, multi-file edits,…. Whether it honours robots.txt is undocumented, and a request claiming to be Claude-Code can be checked against a published IP range file.

Claude-Code at a glance

Reference data for the Claude-Code crawler
User agentClaude-Code

Token only. The operator has not published a full user-agent string, so match on the substring rather than an exact header.

OperatorAnthropic
PurposeCoding agents
Respects robots.txtNot documented
Verification methodPublished IP range file

Runs on a developer machine or CI runner, so the source IP is usually the developer, not Anthropic. The published prefix file will not match most of this traffic.

https://claude.com/crawling/bots.json
Crawl patternNot published
Robots.txt tokensClaude-Code
Operator documentationhttps://support.claude.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler

Claude Code is an AI coding agent by Anthropic that can build, debug, and ship code directly from the terminal, handling tasks like codebase onboarding, multi-file edits,…

robots.txt

Allow or block Claude-Code

Paste one of these into the robots.txt file at the root of your domain. Rules are per token, so a block on one crawler leaves every other bot untouched.

Block Claude-Code
User-agent: Claude-Code
Disallow: /

Blocks every path for this crawler only.

Allow Claude-Code
User-agent: Claude-Code
Allow: /

Explicit allow. Useful when a wildcard rule above it would otherwise catch this crawler.

Allow, except the pages you never want quoted
User-agent: Claude-Code
Allow: /
Disallow: /account/
Disallow: /checkout/
Disallow: /search

Edit the Disallow paths to match your own account, checkout and search URLs.

What blocking actually costs you

Blocking Claude-Code mainly affects developers reading your documentation through an AI tool. Most sites want that traffic.

Block every crawler in the directory at once
Verification

Is that really Claude-Code?

A user-agent header is a string the client chooses. Scrapers copy Claude-Code precisely because site owners allow it. Runs on a developer machine or CI runner, so the source IP is usually the developer, not Anthropic. The published prefix file will not match most of this traffic.

Paste the IP address from your access log below. You will see whether it belongs to a hosting provider, a residential proxy pool or a Tor exit, plus the ASN that announces it, which is what tells you whether the claim holds up.

Other crawlers run by Anthropic

Related crawlers

Agentscan

Identify crawlers automatically instead of by hand

Agentscan checks a request against published crawler ranges, reverse DNS and hosting data, then returns a verdict your edge can act on. One call per request, no range files to keep up to date.

FAQ

Claude-Code questions

Claude-Code is a bot operated by Anthropic that pulls documentation and examples while an AI writes code. Claude Code is an AI coding agent by Anthropic that can build, debug, and ship code directly from the terminal, handling tasks like codebase onboarding, multi-file edits,…. Whether it honours robots.txt is undocumented, and a request claiming to be Claude-Code can be checked against a published IP range file.