Claude Code Dispatch Fixes Permission Gap: Remote Coding Tasks Finally Support Optional Permission Mode

According to 1M AI News monitoring, the Anthropic AI programming tool Claude Code has added a permission mode setting to its Dispatch feature. Dispatch allows users to remotely assign coding tasks to the local desktop instance of Claude Code via their mobile phones. Previously, the options for permission control on coding tasks were limited, but now users can choose a specific permission mode when initiating a task.

Claude Code Product Manager Noah Zweben posted about this update on X. He recommended using the Auto mode, calling it the "safest and smoothest Dispatch experience." The Auto mode leverages an AI classifier to dynamically assess the risk level of each operation, automatically allowing safe operations and blocking high-risk ones, with options between step-by-step confirmation and fully skipping permissions. Users can also choose other pre-approved permission modes. Opting for Bypass Permissions will require manual approval at session initiation.