### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? Sub agents (like `Explore`) aren't much use at the moment, because they keep hitting `Permission to use xxx has been auto-denied in dontAsk mode`. This ha

[BUG] Sub agents can't use tools properly: `Permission to use xxx has been auto-denied in dontAsk mode` even with `--dangerously-skip-permissions`

Status Closed — not planned

Maintainer reply None cached

Activity 10 comments · opened Nov 19, 2025 · closed Feb 12, 2026

Preflight Checklist

[x] I have searched existing issues and this hasn't been reported yet
[x] This is a single bug report (please file separate reports for different bugs)
[x] I am using the latest version of Claude Code

What's Wrong?

Sub agents (like Explore) aren't much use at the moment, because they keep hitting Permission to use xxx has been auto-denied in dontAsk mode. This happens even with --dangerously-skip-permissions. It makes Claude Code much less effective because it can no longer explore codebases, use various commands to read files etc.

What Should Happen?

When --dangerously-skip-permissions is used, sub agents should be able to do whatever they want. No Permission to use xxx has been auto-denied in dontAsk mode error messages.

Error Messages/Logs

Steps to Reproduce

Open Claude Code, go into Plan mode and ask it to do something comprehensive which uses the Explore agent. Explore the codebase + check certain files + go online and do some research. You'll see the sub agent constantly hits the "denied in dontAsk mode" errors.

Claude Model

None

Is this a regression?

I don't know

Last Working Version

_No response_

Claude Code Version

2.0.46

Platform

Anthropic API

Operating System

Windows

Terminal/Shell

Windows Terminal

Additional Information

_No response_

View original on GitHub ↗

10 Comments

github-actions[bot] · 9 months ago

Found 3 possible duplicate issues:

This issue will be automatically closed as a duplicate in 3 days.

If your issue is a duplicate, please close it and 👍 the existing issue instead
To prevent auto-closure, add a comment or 👎 this comment

🤖 Generated with Claude Code

LeonardMH · 9 months ago

Related to #11881, fix allegedly incoming. In the meantime seems like rolling back to 2.0.42 helps some users.

github-actions[bot] · 8 months ago

This issue has been inactive for 30 days. If the issue is still occurring, please comment to let us know. Otherwise, this issue will be automatically closed in 30 days for housekeeping purposes.

gmedlin-p3 · 8 months ago

Still an issue

FBakkensen · 8 months ago

Still experiencing this issue.

Environment:

Claude Code version: 2.0.76
Platform: Windows
Settings: WebFetch(domain:*) configured in .claude/settings.local.json

Symptom:
Subagents (Explore, Plan) hit "Permission to use WebFetch has been auto-denied in dontAsk mode" despite having the wildcard WebFetch(domain:*) in the allow list. Specific domains listed individually (e.g., github.com) work, but the wildcard is not respected.

Workaround found:
Using a PermissionRequest hook bypasses the issue:

{
  "hooks": {
    "PermissionRequest": [
      {
        "matcher": "WebFetch",
        "hooks": [
          {
            "type": "command",
            "command": "exit 0"
          }
        ]
      }
    ]
  }
}

This confirms the permission logic in dontAsk mode doesn't properly evaluate wildcards.

RajuSudhar · 7 months ago

Still an issue.

mieubrisse · 7 months ago

Still hitting this. I didn't enable dontAsk mode.

github-actions[bot] · 6 months ago

This issue has been automatically closed due to 60 days of inactivity. If you're still experiencing this issue, please open a new issue with updated information.

marcindulak · 6 months ago

This issue was closed incorrectly despite recent human comments. This behavior of the bot is reported at https://github.com/anthropics/claude-code/issues/16497. Please upvote that issue, so maybe it gets noticed.