guard

Enforce directory-boundary edits and warn before destructive commands.

3|3|Updated Mar 26, 2026
One-click install
npx skills add https://github.com/tsensei/ReelMistri --skill guard-tsensei
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/tsensei/ReelMistri/tree/main/.claude/skills/gstack/guard
Command: npx skills add https://github.com/tsensei/ReelMistri --skill guard-tsensei

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Guard mode mitigates the risk of destructive actions by enforcing a directory-boundary and warning before irreversible commands, helping teams protect prod and critical data.

Core Features & Use Cases

  • Destructive command warnings are always active, preventing accidental deletes, drops, or overwrites.
  • Directory edit boundary enforces safe work areas by restricting edits to a user-specified path.
  • Seamless integration with companion skills /careful and /freeze to provide end-to-end safety during debugging and maintenance.

Quick Start

Enable guard mode to restrict edits to a directory and enable destructive-command warnings during workflow.

Frequently Asked Questions about guard

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

FAQPage Schema
How do I prevent destructive commands from executing in production directories?

You can prevent destructive commands by enabling a directory-boundary guard that restricts edits to safe paths and requires explicit confirmation before irreversible actions like deletes or overwrites are executed.

What is directory edit boundary enforcement for workflow security?

Directory edit boundary enforcement is a workflow-security mechanism that restricts file modifications to a user-specified safe path, preventing accidental edits or destructive commands from impacting critical production data outside the boundary.

How do I restrict file edits to a specific directory during maintenance tasks?

You can restrict file edits to a specific directory by enabling guard mode, which enforces a strict directory boundary and triggers warnings before any destructive or irreversible commands are executed outside the safe path.

Can I use guard mode with existing DevOps safety hooks like careful and freeze?

Yes, guard mode seamlessly integrates with the careful and freeze hooks to provide end-to-end safety during debugging and maintenance, requiring no special code execution to activate real-time protections.

Do I need special dependencies to enable destructive command warnings?

No special dependencies are required to enable destructive command warnings, as the guard mode operates without in-skill code execution and integrates directly with existing workflow hooks for real-time protection.

When should I use a freeze boundary for irreversible actions?

You should use a freeze boundary during development and production maintenance tasks where edits must be constrained to a safe path, ensuring that destructive commands require explicit confirmation before execution.