guard

Warn on destructive commands and restrict edits to a directory boundary.

Updated Apr 1, 2026
One-click install
npx skills add https://github.com/bajajvinamr/little-wins --skill guard-bajajvinamr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/bajajvinamr/little-wins/tree/main/.claude/skills/gstack/guard
Command: npx skills add https://github.com/bajajvinamr/little-wins --skill guard-bajajvinamr

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Combines two protective measures to prevent unintentional damage during maintenance or debugging by warning on destructive commands and locking edits outside an allowed path.

Core Features & Use Cases

  • Destructive-command warnings: prompts before or blocks dangerous operations like rm -rf, DROP TABLE, or force-push.
  • Edit boundary enforcement: sets a directory boundary so edits outside that path are blocked until unfreeze.
  • Use Case: IT teams performing live-prod debugging can enable guard mode to reduce risk and ensure auditable edits.

Quick Start

Enable guard mode and set the freeze boundary to a directory to restrict edits and warn on destructive commands.

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 force-push during production debugging?

To prevent destructive commands during production debugging, you can enable guard mode to activate warnings that prompt or block dangerous operations like rm -rf, DROP TABLE, or force-push before they execute.

How do I set directory edit boundaries to restrict file modifications to a specific path?

You can set directory edit boundaries by enabling guard mode and setting a freeze boundary to a specific directory, which blocks any file edits attempted outside that allowed path until the restriction is unfrozen.

Can I use edit boundary enforcement and destructive command warnings at the same time?

Yes, you can use edit boundary enforcement and destructive command warnings simultaneously by activating guard mode, which combines both protective measures to lock edits outside an allowed path and warn on dangerous operations.

What do I need to set up before enabling guard mode for live-prod debugging?

Before enabling guard mode for live-prod debugging, you need to define the target directory path for the edit freeze boundary and ensure any helper scripts from sibling skills like /careful and /freeze are available for integration.

Why should IT teams use a combined guard mode instead of separate safety measures for prod maintenance?

IT teams should use combined guard mode for prod maintenance because it integrates destructive command warnings with directory-scoped edit restrictions, providing unified risk reduction and ensuring auditable edits across systems and files.