Tell HN: Anthropic is starting to inject ads into Claude Code turns

I was working in the mobile app via remote control when I saw it:

"PostToolUse:Bash says: Tip: Run /ultrareview before you push to catch bugs with a cloud-based multi-agent review — 3 free reviews left."

Haven't decided how I feel about this yet as it wasn't too disruptive, but I can see where it could cause issues in an automation pipeline. But maybe this is something they're only pushing to subscription users in interactive sessions, so I guess it could be considered "reasonably unobtrusive". Regardless though this is a darkening road.

3 points | by skeledrew 1 hour ago

1 comments

  • rvz 1 hour ago
    They have always done that for years. Nothing new here.

    Once again, if you don't like it stop using Claude Code then.

    [-]
    • skeledrew 1 hour ago
      While there have always been ads in the UI itself, I've never seen any in the actual turn message. I'd say this has prompt injection potential, if the session is being managed by another agent.
      [-]