careful

Intercept bash commands and warn on destructive patterns before execution.

Updated Apr 5, 2026
One-click install
npx skills add https://github.com/rahmanayon/beehive --skill careful-rahmanayon
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/rahmanayon/beehive/tree/main/.claude/skills/gstack/careful
Command: npx skills add https://github.com/rahmanayon/beehive --skill careful-rahmanayon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Prevents accidental data loss by warning before destructive commands such as rm -rf, git reset --hard, kubectl delete, and similar operations. Users can override warnings when necessary, making it suitable for prod debugging and shared environments.

Core Features & Use Cases

  • Pre-execution guardrails detect destructive patterns in bash commands and prompt for confirmation.
  • Safe exceptions allow certain operations (like removing build artifacts) to proceed without warning.
  • Usage analytics are logged locally to help auditing and improvement of guard rules.
  • Applicable to development, deployment, and maintenance workflows where risky actions could impact systems.

Quick Start

Run a potentially destructive command to trigger a warning and choose whether to proceed or cancel.

Frequently Asked Questions about careful

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

FAQPage Schema
How do I prevent accidental data loss from destructive bash commands like rm -rf?

To prevent accidental data loss from destructive bash commands, you can use guardrails that intercept commands like rm -rf or git reset --hard and prompt for confirmation before execution.

Can I override safety warnings when running destructive commands in production?

You can override safety warnings for destructive commands using a configurable override, allowing necessary operations to proceed in production debugging or shared environments when needed.

How do bash command guardrails detect destructive patterns before execution?

Bash command guardrails detect destructive patterns using pre-execution pattern-based checks that scan commands for risky actions, blocking or warning the user before any execution occurs.

Can I exclude specific operations like removing build artifacts from safety prompts?

You can exclude specific operations like removing build artifacts from safety prompts by configuring safe exceptions, allowing those operations to proceed without triggering a warning.

Is local usage logging available for auditing destructive command warnings?

Local usage logging is available for auditing destructive command warnings, recording usage analytics locally to help you audit activity and improve guard rules over time.

Do these safety guardrails work for deployment and maintenance workflows?

These safety guardrails work for deployment and maintenance workflows, protecting systems where risky actions such as mass deletions or history rewrites could impact operations.