careful

Validate destructive Bash, SQL, Git, Kubernetes, and Docker commands before execution.

4|Updated Mar 21, 2026
One-click install
npx skills add https://github.com/Kit4Some/Oh-my-ClaudeClaw --skill careful-kit4some
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/Kit4Some/Oh-my-ClaudeClaw/tree/main/skills/careful
Command: npx skills add https://github.com/Kit4Some/Oh-my-ClaudeClaw --skill careful-kit4some

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, and similar actions, helping prevent data loss.

Core Features & Use Cases

  • Trigger warnings for risky commands in Bash, SQL, Git, Kubernetes, and Docker.
  • Allow user confirmation or cancellation before proceeding, with a clear memory log for auditability.
  • Integrate with OpenClaw-CC workflow to stop accidental destructive operations in production environments.

Quick Start

Activate safety mode and prompt before executing any destructive command.

Frequently Asked Questions about careful

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I prevent accidental destructive commands like rm -rf or DROP TABLE in bash and SQL?

To prevent accidental destructive commands, you need a pre-run check that validates dangerous patterns like rm -rf or DROP TABLE. A warning step triggers before execution, allowing you to confirm or cancel the operation and prevent data loss.

Can I get a warning before force-push or destructive git commands are executed?

Yes, you can get a warning before destructive git commands like force-push are executed. By applying pre-execution validation, the system detects risky Git patterns and prompts for confirmation before allowing the operation to proceed.

Does this safety guardrail work with Kubernetes and Docker operations?

Yes, this safety guardrail works with Kubernetes and Docker operations. It validates destructive patterns across Bash, SQL, Git, Kubernetes, and Docker, triggering a warning step before proceeding to stop accidental destructive operations.

What is the best way to audit destructive commands before they run in production?

The best way to audit destructive commands is to use a safety mode that enforces a pre-run check via a hook and includes memory logging. This creates a clear memory log for auditability, ensuring you can review destructive actions.

How do I set up a PreToolUse hook to validate dangerous bash commands?

To set up a PreToolUse hook to validate dangerous bash commands, you enforce a pre-run check using a validation script. The hook intercepts commands, matches destructive patterns, and triggers a warning step before proceeding.