careful

Warns before destructive Bash, Git, Kubernetes, and Docker operations with overridable prompts and audit logging.

5|2|Updated Dec 27, 2025
One-click install
npx skills add https://github.com/agatx/serenada --skill careful-agatx
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/agatx/serenada/tree/main/.claude/skills/gstack/careful
Command: npx skills add https://github.com/agatx/serenada --skill careful-agatx

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. Use when asked to "be careful", "safety mode", "prod mode", or "careful mode".

Core Features & Use Cases

  • Enforces warning prompts before dangerous commands across Bash, Git, Kubernetes, Docker, and other toolchains.
  • Supports per-command override, audit logging, and safe-exception rules to allow avoidance of false positives on common build artifacts.
  • Use case: when administering production systems, debugging shared environments, or performing risky operations where collateral damage must be avoided.

Quick Start

Use the careful skill to automatically warn before potentially destructive commands and log decisions.

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 warn before destructive bash or git commands?

Safety guardrails intercept destructive commands like rm -rf or git reset --hard across Bash, Git, Kubernetes, and Docker, displaying an override prompt to prevent accidental data loss before execution proceeds.

Can I override the warning prompt when running kubectl delete in production environments?

Yes, the warning prompt supports per-command overrides, allowing you to proceed with kubectl delete or similar destructive operations in development, production, or shared environments after acknowledging the warning.

How do I prevent false positive warnings on known build artifacts during development?

You can configure safe-exception rules to bypass warning prompts for specific known build artifacts, preventing false positives while still enforcing safety guardrails on genuinely destructive commands.

Does this destructive command warning system log override decisions for auditing?

Yes, warning events and override decisions are logged to an analytics store, providing an auditing trail to review destructive command approvals and improve safety guardrail configurations over time.

What is the best way to enable safety mode for risky operations in shared environments?

Activating careful mode automatically enforces warning prompts before potentially destructive operations across toolchains, guarding risky shared environment actions with overridable safety guardrails and audit logging.