Claude Code gives developers ‘auto mode,’ a safer alternative to skipping permissions

Anthropic continues to ship in March with a new “auto mode” permissions mode in Claude Code. The company calls it a middle ground between the default configuration and skipping permissions altogether.

Claude Code ‘auto mode’ lets tasks run longer with fewer interruptions

Anthropic says that Claude Code default permissions are intentionally conservative, requiring approval for each file write and bash command.

Prior to “auto mode,” the solution for running longer without interruptions has been to live dangerously and ignore permissions altogether.

The new “auto mode” permissions mode balances convenience and capabilities, which should help developers get more out of Claude Code.

Auto mode is a middle path that lets you run longer tasks with fewer interruptions while introducing less risk than skipping all permissions. Before each tool call runs, a classifier reviews it to check for potentially destructive actions like mass deleting files, sensitive data exfiltration, or malicious code execution. 

Actions that the classifier deems as safe proceed automatically, and risky ones get blocked, redirecting Claude to take a different approach. If Claude insists on taking actions that are continually blocked, it will eventually trigger a permission prompt to the user.

Auto mode reduces risk compared to –dangerously-skip-permissions but doesn’t eliminate it entirely, and we continue to recommend using it in isolated environments.

Claude Teams users can access “auto mode” as a research preview starting today. Enterprise and API customers will gain access “in the coming days.” Users can find more information here.

Separately, Anthropic unveiled the ability for Claude to control your Mac for you yesterday as a different research preview.

FTC: We use income earning auto affiliate links. More.