command-guard

SKILLWorkflowcommunity
v0.0.0JKHeadleyMITUpdated 1mo agoSource →

Set up a PreToolUse hook in .claude/settings.json that blocks dangerous commands — rm -rf, force push, database drops, and others — before they execute. Teaches the pattern of safety hooks for any Claude Code project. Trigger words: safety, guard, block dangerous, protect, prevent destructive, safe

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
76Repo stars
1Clients
1Formats
1mo agoLast update
Skill
AuthorJKHeadley
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor—
Copilot—
ChatGPT—
Gemini—
About

Set up a PreToolUse hook in .claude/settings.json that blocks dangerous commands — rm -rf, force push, database drops, and others — before they execute. Teaches the pattern of safety hooks for any Claude Code project. Trigger words: safety, guard, block dangerous, protect, prevent destructive, safe mode, dangerous commands, risky operations.

Keywords
skillclaude

No dependency coverage

This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.