destructive-op-guard
OfficialIntercept destructive commands with guardrails.
Authorm2ai-portfolio
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Autonomous agents can execute irreversible operations in seconds without human intervention. This skill provides a PreToolUse hook that blocks high‑risk commands and requires explicit authorization before they run, preventing catastrophic outcomes.
Core Features & Use Cases
- Prevents irreversible shell actions (rm -rf, DROP TABLE, kubectl delete, etc.) from executing without approval.
- Configurable block lists, authorization options, and integration as a project-local hook in Claude Code.
- Use cases include safety reviews after incidents, proactive guardrail hardening, and auditing existing hooks for coverage.
Quick Start
Install and configure the PreToolUse hook in your Claude Code project to block high-risk commands and require explicit authorization before execution.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: destructive-op-guard Download link: https://github.com/m2ai-portfolio/m2ai-skills-pack/archive/main.zip#destructive-op-guard Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.