Here are
4 public repositories
matching this topic...
Destructive command guardrails for OpenAI Codex agents and subagents. Blocks rm -rf, dangerous Git operations, pushes, and selected GitHub writes without sacrificing workspace autonomy.
Updated
Jul 12, 2026
PowerShell
A self-contained, toggleable GSD capability that enforces clean open-gsd/gsd-core contributions at the Claude Code harness boundary — 12 fail-closed PreToolUse gates + 2 skills + 5 commands, installed via gsd-core's capability system. Advisory-only on non-Claude runtimes.
Updated
Jun 24, 2026
JavaScript
Pattern-level command filtering for Claude Code. Blocks the dangerous stuff, asks about the risky stuff, lets the normal stuff through.
Updated
Feb 10, 2026
Shell
Give your agents the "Bash" permission but block destructive actions.
Improve this page
Add a description, image, and links to the
pretooluse-hooks
topic page so that developers can more easily learn about it.
Curate this topic
Add this topic to your repo
To associate your repository with the
pretooluse-hooks
topic, visit your repo's landing page and select "manage topics."
Learn more
You can’t perform that action at this time.