Claude Code makes auto mode the default for permissions
By Steven Van ·
Starting 14 August, Pro, Max, and Team users get a risk classifier instead of manual command approval by default.
Starting 14 August, auto mode becomes the default permission setting in Claude Code for Pro, Max, and Team users. Instead of approving each shell command manually, a separate classifier reviews commands and actions for risk. In Anthropic's testing, that classifier caught 89% of dangerous commands, compared with 14% caught under manual approval.
Read the full announcement.
Claude
AI assistant by Anthropic — write, analyze, code, and create with one of the most capable large language models available.
View Claude →