---
title: "Comment by Vic Moreno on \"Claude Code auto mode blocked 89% of dangerous commands in a controlled test. Humans blocked 13.6%\" | Hashnode"
description: "13.6% is the number that stings: a human clicking through approval prompts is a weaker gate than a classifier that never gets tired. Of the three, a Stop hook t"
url: "https://hashnode.com/posts/claude-code-best-practices-auto-mode-hooks-ci/6af6b357bafc7a7b0687b08e/comment/6af6f1085893e6480a9f64bd"
---

[Discussion](https://hashnode.com/posts/claude-code-best-practices-auto-mode-hooks-ci/6af6b357bafc7a7b0687b08e)

Comment [Claude Code auto mode blocked 89% of dangerous commands in a controlled test. Humans blocked 13.6%](https://hashnode.com/posts/claude-code-best-practices-auto-mode-hooks-ci/6af6b357bafc7a7b0687b08e)

[Vic Moreno](https://hashnode.com/@itsvicmoreno)

[4h ago](https://hashnode.com/posts/claude-code-best-practices-auto-mode-hooks-ci/6af6b357bafc7a7b0687b08e/comment/6af6f1085893e6480a9f64bd)

13.6% is the number that stings: a human clicking through approval prompts is a weaker gate than a classifier that never gets tired. Of the three, a Stop hook that runs the tests before the session may end is the cheapest to add. Did the test say how much of the missed 11% was actually destructive?