careful

Intercept destructive bash commands before execution to prevent data loss.

Updated May 27, 2026
One-click install
npx skills add https://github.com/Shmurdoc/EasyRide-v1 --skill careful-shmurdoc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: careful
Source: https://github.com/Shmurdoc/EasyRide-v1/tree/main/.opencode/skills/gstack-careful
Command: npx skills add https://github.com/Shmurdoc/EasyRide-v1 --skill careful-shmurdoc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Accidentally running destructive commands like rm -rf, DROP TABLE, or git push --force can cause irreversible data loss, system damage, or production outages, especially when working in live environments or shared workspaces.

Core Features & Use Cases

  • Destructive Command Detection: Automatically flags high-risk operations including recursive file deletion, database drops, force pushes, hard git resets, and Kubernetes resource deletions.
  • Safe Exceptions: Allows common non-destructive operations like deleting node_modules or build artifacts without warning.
  • User Override: Lets you bypass any warning with explicit confirmation when you intend to run a destructive command.
  • Use Cases: Ideal for production deployments, live system debugging, and shared development environments where accidental destructive actions pose significant risk.

Quick Start

Use the careful skill to enable safety guardrails that warn you before executing any destructive bash commands.

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 in production?

To prevent accidental data loss from destructive bash commands, you can use safety guardrails that intercept and block high-risk operations like recursive file deletion, database drops, and force pushes before execution. This protects live environments from irreversible damage.

What destructive commands are blocked by git safety and kubectl safety guardrails?

Git safety and kubectl safety guardrails block destructive commands including recursive file deletion, database drops, force pushes, hard git resets, and Kubernetes resource deletions. These command validation rules target operations that cause irreversible data loss or system damage.

Can I bypass command validation warnings when I intentionally need to run a destructive command?

Yes, you can bypass command validation warnings with explicit confirmation when you intentionally need to run a destructive command. Safety guardrails are designed to warn against accidental data loss, but they always permit user override for deliberate destructive operations.

Does command validation flag deleting build artifacts and node_modules as destructive operations?

No, command validation does not flag deleting build artifacts and node_modules as destructive operations. Safety guardrails include safe exceptions that allow common non-destructive file deletions to execute without triggering warnings.

When do I need destructive command interception for shared development workspaces?

You need destructive command interception for shared development workspaces when unintended destructive operations carry high risk. Applying command validation prevents accidental data loss from force pushes, hard resets, or recursive deletions that could disrupt collaborative environments.