[FEATURE] Auto Permission Mode

Resolved 💬 2 comments Opened May 19, 2026 by thomasnagashima-droid Closed May 19, 2026

Preflight Checklist

  • [x] I have searched existing requests and this feature hasn't been requested yet
  • [x] This is a single feature request (not multiple features)

Problem Statement

My biggest complaint about working with Claude Code is having to grant permissions to tool usage. But I can't just blindly YOLO it because it loves to chain things and do thirty safe commands with "&& delete your hard drive" tacked on at the end. So I loved the auto mode until I found out it was also forcing Claude to not asking me actual questions (even ones surfaced explicitly via prompts/skills). That is NOT what I want. I need that intelligent permission check without your biased prompt injection.

Proposed Solution

You have auto mode, you have a Proactive style (which is don't ask me questions but bug me with every permission check possible, IMO the worst of all worlds) but you don't have the inverse, safe permission auto checks but don't try to answer my questions for me. Please add that as an option.

Alternative Solutions

_No response_

Priority

High - Significant impact on productivity

Feature Category

Interactive mode (TUI)

Use Case Example

Literally everything I do. Every single session I'm bugged no joke 100+ times a day with useless permission checks that I can't just auto allow because I never know if the 3-4 line bash script has something snuck in there.

Additional Context

_No response_

View original on GitHub ↗

This issue has 2 comments on GitHub. Read the full discussion on GitHub ↗