Anthropic Launches Auto Mode for Claude Code, Adding Smart Permission Controls Between Safe and Risky Operations
Summary
Anthropic launches 'auto mode' for Claude Code, a smart permissions system that automatically allows safe operations while blocking dangerous ones like mass file deletion or data exfiltration, rolling out now for Team plan users with Enterprise and API access coming soon.
Key Points
- Anthropic is launching auto mode for Claude Code, a new permissions system that acts as a middle ground between conservative default permissions and the risky --dangerously-skip-permissions flag.
- A built-in classifier reviews each tool call before execution, automatically allowing safe actions while blocking potentially destructive ones such as mass file deletion, sensitive data exfiltration, or malicious code execution.
- Auto mode is rolling out now as a research preview for Team plan users, with Enterprise and API access coming in the next few days, and is compatible with both Claude Sonnet 4.6 and Opus 4.6.