careful

Warns before executing risky Bash commands via a PreToolUse hook with per-command overrides and usage logging.

Updated Mar 30, 2026
One-click install
npx skills add https://github.com/mulyoved/awesome-agent-ides --skill careful-mulyoved
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/mulyoved/awesome-agent-ides/tree/main/.agents/skills/gstack/careful
Command: npx skills add https://github.com/mulyoved/awesome-agent-ides --skill careful-mulyoved

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. (gstack)

Core Features & Use Cases

  • Provides pre-execution warnings for dangerous commands in Bash sessions.
  • Allows per-command overrides to proceed with explicit confirmation.
  • Useful in production maintenance, debugging shared environments, and CI scripts.

Quick Start

Enable safety checks for destructive Bash commands in your session.

Frequently Asked Questions about careful

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

FAQPage Schema
How do I add a safety warning before running destructive bash commands?

You can add safety warnings for destructive bash commands by implementing a PreToolUse hook that runs a safety script. This intercepts risky operations like rm -rf or git reset --hard, warning you before execution across interactive shells and automated workflows.

Can I override the warning if I need to force push or delete a resource?

Yes, you can override warnings on a per-command basis. The guardrail prompts you with explicit confirmation before executing destructive commands, allowing you to bypass the safety check intentionally when pushing to prod or deleting resources.

Does this command guardrail work in automated CI scripts and shared environments?

Yes, the bash guardrail works across automated workflows and shared environments. It prevents data loss by intercepting destructive operations in CI scripts and interactive shells, logging usage analytics to track when overrides occur during debugging.

What specific destructive operations does the safety guardrail catch?

The safety guardrail catches destructive bash commands including rm -rf, DROP TABLE, force-push, git reset --hard, and kubectl delete. It warns you before these risky operations execute to prevent data loss in production and development environments.

When should I use a bash guardrail for destructive commands?

You should use a bash guardrail when touching production, debugging live systems, or working in a shared environment. It provides pre-execution warnings for dangerous commands, preventing accidental data loss during sensitive maintenance tasks.