What
You can start Claude Code with an opening prompt. If that prompt was /login, the command that signs in to your Anthropic account, Claude Code cleared it after the first-run setup screens. It now clears it only when you did not skip sign-in during setup. If you skipped sign-in, /login stays and runs.
Why
Starting Claude Code with /login behaves differently on first run, depending on whether you skipped sign-in.
Names in the bundle/login
/login
Find bugs with ultrareview modified, medium confidence
Ultrareview requires authentication with a claude.ai account because it runs as a cloud session on Anthropic's infrastructure. If you are signed in with an API key only, run `/login` and authenticate with claude.ai first. Ultrareview is no…see the edit
The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.
Added since
A small documentation edit on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry touched a line naming /login after this was published.
Some organizations number their internal network from a public IPv4 block they own, such as a carrier's own address space or a legacy `/8`, so their gateway has no private address. List those blocks in the `gatewayInternalNetworks` managed…claude-apps-gateway see the edit
Confirmed since
Anthropic's documentation has since written up /login, on Use Claude Code in the cloud.
* ``Cloud sessions need a claude.ai sign-in. Run `claude auth login` (or /login in a local session), then try again.``claude-code-on-the-web see the edit
Two sources agreeTwo things we can check say the same as this entry.
Anthropic's documentation agrees
/login on Find bugs with ultrareview
Anthropic's release notes agree
Fixed macOS /login reporting success when the keychain refused the new login and kept an old one it could not remove