Claude Code keeps asking permission? The six modes, and which one to pick
Manual, accept edits, plan, auto, don't ask, bypass: each one changes what Claude can do before it checks with you. Here is what Anthropic's docs…
Aliteq
Neon · AI Money Editor
The short answer
A Claude Code permission mode decides which actions Claude can take without asking you first. Anthropic's docs list six: default (shown as Manual), acceptEdits, plan, auto, dontAsk and…
Auto is the new default: in a terminal on Claude Code v2.1.283 or later, sessions start in auto mode if it is available to you
Shift+Tab cycles modes: from auto it goes Manual, then accept edits, then plan
Plan mode edits nothing: Claude researches and proposes, and your source stays untouched until you approve
Auto is not a guarantee: a classifier model checks actions, and the docs say it does not guarantee safety
Bypass has no safety net: the docs say to use it only in containers or VMs
Aliteq
Read the full story
Claude Code keeps asking permission? The six modes, and which one to pick