.

Found 3 possible duplicate issues:

1. https://github.com/anthropics/claude-code/issues/12100
2. https://github.com/anthropics/claude-code/issues/11519
3. https://github.com/anthropics/claude-code/issues/14833

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

This is a painful one — hooks silently blocked with no error is really hard to debug. We've added a doctor check + auto-fix for this in Cozempic v0.9.0 (context health tool for Claude Code):

pip install -U cozempic
cozempic doctor       # detects missing hasTrustDialogHooksAccepted
cozempic doctor --fix # sets it to true for all trusted workspaces

The check scans .claude.json for project entries where hasTrustDialogAccepted=true but hasTrustDialogHooksAccepted is absent or false, and patches them in one shot. Hopefully useful until the upstream fix lands.

Very clear

Regards,
Junaid Ali Qureshi

On Mon, 9 Mar 2026 at 4:24 PM seiseisette @.***> wrote:

seiseisette left a comment (anthropics/claude-code#32424) <https://github.com/anthropics/claude-code/issues/32424#issuecomment-4023382464> Thanks for sharing — glad to see more tooling around this. One design note: cozempic doctor --fix patches all workspaces where hasTrustDialogAccepted=true in one shot, bypassing the per-directory consent model entirely. That's the same gap flagged in the Secondary Risk section above — silent bulk-patching is exactly what this bug enables. claudetruster takes the opposite approach: - interactive prompt per directory, explicit confirmation before any write - zero silent patching, zero install (pip or otherwise) — single light shell script - full passthrough: env vars and flags work exactly as with claude directly (MY_VAR=1 claudetruster -c "...", claudetruster /remote-control, etc.) - acts as a proper trust dialog wrapper, not a bulk config editor Different tradeoffs — just worth being explicit about them, especially on a security-labeled issue. — Reply to this email directly, view it on GitHub <https://github.com/anthropics/claude-code/issues/32424#issuecomment-4023382464>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AFVALNOPVQPXIAOFRQD2V5L4P2ZWPAVCNFSM6AAAAACWLXMODSVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHM2DAMRTGM4DENBWGQ> . You are receiving this because you commented.Message ID: @.***>

This issue has been automatically locked since it was closed and has not had any activity for 7 days. If you're experiencing a similar issue, please file a new issue and reference this one if it's relevant.