Summary
In Claude Code v2.1.200 (released July 3, 2026), Anthropic changed the default permission mode from auto-continuation to Manual across the CLI, VS Code extension, and JetBrains plugin, so the coding agent now asks for explicit human approval before every file write, shell command, or external API call. Auto mode remains available but must be opted into.
What changed
Claude Code's default permission mode became Manual, requiring explicit approval for each sensitive action (file modification, shell execution, external API call) instead of auto-continuing; the change ships by default on install or update across CLI and IDE integrations.
Why it matters
Flipping the default to human-in-the-loop resets the safety baseline for one of the most widely used coding agents, trading some autonomy for auditability and guardrails—an implicit acknowledgment that unattended agent actions are an enterprise risk as coding agents move deeper into production workflows.
Evidence excerpt
Anthropic changed Claude Code's default permission mode from Auto to Manual across every surface where the tool runs—the CLI, the VS Code extension, the JetBrains plugin. Claude Code should ask for permission before every write action by default.