Anthropic sets Claude Code's auto mode as the standard option

Anthropic is making auto mode the default setting for Claude Code users on Pro, Max, and Team plans starting August 14, according to a company announcement. This move means that the coding tool will no longer pause for human approval at every step, unless an action is considered irreversible, destructive, or aimed outside the user's environment.

The feature was first tested in March as a balance between speed and control. In a study involving 1,053 paid testers, auto mode caught 89% of harmful actions, while human review caught only 13.6%. Anthropic suggested that manual review often becomes routine, with users approving 97% of permission prompts.

Boris Cherny, head of Claude Code, said on X that he and his team have used auto mode exclusively for months and couldn't imagine returning to permission prompts. The company has also introduced safety enhancements, including prompt injection screening and customizable hard deny rules, aimed at preventing data exfiltration.

Source: TechCrunch