guard

Enforce runtime safety guardrails for destructive commands and directory-scoped edits.

Updated Dec 13, 2017
One-click install
npx skills add https://github.com/dogeared/tnra --skill guard-dogeared
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/dogeared/tnra/tree/main/.claude/skills/gstack/guard
Command: npx skills add https://github.com/dogeared/tnra --skill guard-dogeared

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Reduces the risk of accidental damage in development and production by enforcing safety guardrails around destructive commands and edits.

Core Features & Use Cases

  • Destructive command warnings: warns before executing dangerous commands like rm -rf, DROP TABLE, or force-push.
  • Edit boundary enforcement: restricts edits to a user-selected directory to prevent drift in production environments.
  • Pre-activation safety checks: validates readiness and dependencies before enabling guard mode to avoid misconfigurations.

Quick Start

Run the guard command to activate full safety mode in the current project.

Frequently Asked Questions about guard

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

FAQPage Schema
How do I prevent accidental destructive commands like rm -rf or DROP TABLE in production?

Runtime safety guardrails intercept destructive commands like rm -rf, DROP TABLE, or force-push, warning you before execution to prevent accidental damage in development and production environments.

What is edit boundary enforcement and how does it protect shared environments?

Edit boundary enforcement restricts file modifications to a user-selected directory, preventing drift and unmanaged edits in production or shared environments by blocking changes outside the specified boundary.

How do I activate guard mode for safety checks in my current project?

Run the guard command in your current project to activate full safety mode. Pre-activation safety checks validate readiness and dependencies beforehand to prevent misconfigurations.

Does this safety mode work with other DevOps risk mitigation tools?

Yes, this safety mode integrates with sibling tools /careful and /freeze to provide layered risk mitigation. It validates constraints with these tools before activation to ensure comprehensive production protection.

When should I not use automated production protection guardrails?

Avoid automated production protection guardrails when your workflow requires unrestricted execution of destructive commands without warnings, or when directory-scoped edit boundaries would block necessary cross-directory modifications.