Anthropic Makes Claude Code Auto Mode the Default for Pro, Max, and Team Plans
Anthropic
Anthropic announced that starting August 14, 2026, Claude Code will run in auto mode by default for Pro, Max, and Team subscribers, letting a safety classifier approve most tool calls automatically instead of prompting for permission on every action. Anthropic cited a study of 1,053 testers in which auto mode caught 89% of harmful actions versus 13.6% caught by human review, and is dropping the token fee previously charged for the classifier.
Why it matters
Marks a shift from manual permission-gated coding agents to autonomy-by-default for a widely used developer tool, with data suggesting automated review outperforms habitual human approval.
Importance: 3/5
Notable product-wide default-behavior change from a frontier lab (Anthropic), official+media confirmed, backed by a 1,053-tester safety study.