ToolsAugust 8, 2026via The Decoder
Anthropic sets Claude Code to Auto Mode by default to protect developers from bad approvals
Why it matters
Claude Code's shift to automatic approval by default changes developer workflows at scale—practitioners need to understand the safety tradeoff and how to manage autonomous code execution in production environments.
Key signals
- Auto Mode becomes default for Pro, Max, Team plans starting August 14, 2026
- Safety classifier catches 89% of dangerous commands vs 13.6% by human reviewers
- Shifts developer role from code authorship to AI output monitoring
- Applies to Claude Code, Anthropic's primary AI coding product
The hook
89% vs 13.6%: Anthropic's safety classifier now auto-approves code execution by default. Developers move from writing to monitoring.
Starting August 14, Anthropic will make Auto Mode in Claude Code the default for Pro, Max, and Team plans. The company says it's safer. In tests, the classifier caught 89 percent of dangerous commands, while human reviewers caught only 13.6 percent. For the most widely used AI coding tool, this mean…