careful

Warn before executing destructive Bash commands in development and production environments.

Updated Mar 28, 2026
One-click install
npx skills add https://github.com/zaeem-rafiq/tatheer-swift-sdk --skill careful-zaeem-rafiq
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/zaeem-rafiq/tatheer-swift-sdk/tree/main/.claude/skills/gstack/careful
Command: npx skills add https://github.com/zaeem-rafiq/tatheer-swift-sdk --skill careful-zaeem-rafiq

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Safety guardrails for destructive commands warn before execution and allow overrides to prevent accidental data loss in development, staging, or production environments.

Core Features & Use Cases

  • Preemptive warnings for destructive operations such as rm -rf, DROP TABLE, git reset --hard, kubectl delete, and similar risky actions.
  • Override capability to proceed after a warning, with explicit user confirmation.
  • Suitable for use in prod, staging, or local environments to reduce accidental damage during maintenance or debugging tasks.

Quick Start

Enable careful mode before executing destructive commands.

Frequently Asked Questions about careful

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

FAQPage Schema
How do I add safety guardrails to prevent accidental destructive bash commands in production?

Safety guardrails for destructive bash commands intercept risky patterns like rm -rf or git reset --hard and prompt for explicit user confirmation before execution to prevent accidental system changes.

Can I override a destructive command warning if I need to proceed with the operation?

Yes, you can override the destructive command warning by providing explicit user confirmation, allowing you to proceed with the operation after acknowledging the safety prompt.

Does this safety hook work with CI/CD workflows and local staging environments?

Yes, the safety hook integrates into CI/CD workflows, local development, and production debugging sessions, identifying destructive patterns across developer environments to prevent accidental data loss.

What destructive command patterns are caught by these bash safety warnings?

The safety warnings catch destructive command patterns including rm -rf, DROP TABLE, git reset --hard, and kubectl delete, triggering a pre-use hook script to warn before execution.

How do I enable careful mode before executing potentially risky shell commands?

You enable careful mode via a pre-use hook script that checks Bash commands against destructive patterns, requiring YAML frontmatter configuration with name and description plus optional directories.

What are the limitations of relying on pre-use hooks for bash command safety?

The safety hook relies on pattern matching for known destructive commands, meaning novel or obfuscated risky syntax might bypass the warnings and not trigger the confirmation prompt.