Open
Conversation
Changes the default agent permission mode from interactive to auto. Auto mode uses Claude Code's new --enable-auto-mode flag, which lets Claude make routine permission decisions autonomously while a classifier blocks potentially destructive actions. This is a safer middle ground between interactive (ask for everything) and --dangerously-skip-permissions. Permission modes: - auto (new default): Claude uses --enable-auto-mode, Codex/Gemini run plain - yolo: Claude uses --dangerously-skip-permissions, Codex/Gemini use --yolo - interactive: all agents ask for every permission (old default) New flag: -i/--interactive to override auto mode for a single run. Config: lwt config set agent-mode auto|yolo|interactive
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Changes the default agent permission mode from interactive to auto.
Auto mode uses Claude Code's new
--enable-auto-modeflag (announcement), which lets Claude make routine permission decisions autonomously while a classifier blocks potentially destructive actions. This is a safer middle ground between interactive (ask for everything) and--dangerously-skip-permissions.Permission modes
--enable-auto-mode--dangerously-skip-permissions--yolo-yolo-i/--interactiveChanges
lib/agent.sh—command_stringandlaunchnow acceptauto/yolo/interactiveinstead of a booleanlib/commands.sh— adds-i/--interactiveflag, resolves mode from flag > config > default (auto)lib/config.sh— defaultagent-modechanged frominteractivetoautolib/help.sh— updated help text for all affected commandsREADME.md— updated docsNote
Auto mode is currently available as a research preview on Claude Team plan, rolling out to Enterprise and API soon. For Codex and Gemini, auto mode behaves the same as interactive since they don't have an equivalent feature yet.