[BUG] Tool always fail to execute stop hook
Status Fixed / completed
Reported on v2.1.4
Maintainer reply None cached
Activity 8 comments · opened Jan 13, 2026 · closed Feb 2, 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?
When tool finishes its work, it can't execute the stop function. Logs provided. Started to happen right after upgrading.
What Should Happen?
It should stop fluently after work's done.
Error Messages/Logs
● Ran 1 stop hook
⎿ command: "${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" claude-judge-continuation.sh
⎿ Stop hook error: Failed with non-blocking status code: No stderr output
Steps to Reproduce
Ran claude prompt
Claude handles the work
When work's done it should stop but I wait for a few seconds (nearly 1 min) and it doesn't stop, displaying error message.
Claude Model
Opus
Is this a regression?
Yes, this worked in a previous version
Last Working Version
2.1.4
Claude Code Version
2.1.5
Platform
Google Vertex AI
Operating System
Other Linux
Terminal/Shell
Other
Additional Information
Using Cachyos, installed with bun package manager
8 Comments
+1 here
Yes, +1. Even on
2.1.12.Mine error is a little bit different:
Mine error is a little bit different:
⎿ Stop hook error: Failed with non-blocking status code: No stderr output
Same, mark this issue here.
@rzgrozt
The error message shows
run-hook.cmd claude-judge-continuation.sh- do youhave the
double-shot-latteplugin installed?If so, I encountered the same issue. The
run-hook.cmdpolyglot wrapper can'tbe executed directly on Linux/macOS since there's no shebang line.
Uninstall to fix:
``
bash
``claude /plugin uninstall double-shot-latte@superpowers-marketplace
I've submitted a fix: https://github.com/obra/double-shot-latte/pull/11
+1 Experiencing this on v2.1.29 (macOS Darwin 25.3.0, Homebrew Cask install)
Error:
Investigation findings:
{}or{"continue": true})Tested conditions:
The error message "No stderr output" is misleading - stderr should be empty for successful hooks. The issue appears to be in Claude Code's hook result interpretation, not in the hooks themselves.
This was also reported in the now-closed #10463. A comment there claimed it was fixed in "v2.2.12" but that version doesn't exist - latest release is v2.1.29.
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.