https://www.whizme.ai/tags/hooks/Recent content in Hooks on WhizMe.ai Tech BlogHugoen-usTue, 07 Apr 2026 00:00:00 +0000https://www.whizme.ai/blogs/locking-down-claude-code/Tue, 07 Apr 2026 00:00:00 +0000https://www.whizme.ai/blogs/locking-down-claude-code/<p>Claude Code can be made much safer, but only if you understand what each control is actually doing.</p> <p>A lot of teams get confused because the names sound similar:</p> <ul> <li><code>CLAUDE.md</code></li> <li>permissions</li> <li>sandboxing</li> <li>hooks</li> <li>managed settings</li> </ul> <p>They are <strong>not</strong> the same thing.</p> <p>A simple way to think about them is this:</p> <ul> <li><strong><code>CLAUDE.md</code></strong> tells Claude what you want it to do</li> <li><strong>permissions</strong> decide which tools Claude is allowed to use</li> <li><strong>sandboxing</strong> limits what Bash can actually do on the machine</li> <li><strong>hooks</strong> inspect actions at runtime and can allow, deny, or modify them</li> <li><strong>managed settings</strong> stop users from weakening policy in an enterprise setup</li> </ul> <p>If you only remember one thing from this article, remember this:</p>