How Anthropic built Claude Code auto mode to replace skipped permissions
Original titleHow we built Claude Code auto mode: a safer way to skip permissions
AISummary
Anthropic describes Claude Code auto mode, which delegates approval of agent actions to model-based classifiers instead of manual prompts or skipped permissions.
The classifier reviews tool calls before execution and a separate probe screens tool outputs for prompt injection. Anthropic reports a 0.4% false positive rate on real internal traffic and a 17% false negative rate on real overeager actions.
AIWhy it matters
The post explains the layered classifier design and its measured tradeoffs, showing how autonomous coding agents can cut approval fatigue without fully removing risk.
Source: Anthropic Engineering · anthropic.com