skills.rest
raghavbadhwar
raghavbadhwarCOMMUNITY
Explore all skills by this author →
GitHub

guard

Activates destructive command warnings and directory-scoped edit restrictions for safer sessions.

Updated Aug 9, 2026
Search Tags:#hooks#safety#guardrails#freeze#destructive commands#edit restrictions#production debugging
One-click install
npx skills add https://github.com/raghavbadhwar/rstack --skill guard-raghavbadhwar
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/raghavbadhwar/rstack/tree/main/guard
Command: npx skills add https://github.com/raghavbadhwar/rstack --skill guard-raghavbadhwar

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? When working on production systems or debugging live environments, a single accidental command like rm -rf or an edit to the wrong file can cause serious damage. This Skill combines two safety layers so destructive commands trigger warnings and file edits are confined to a directory you choose. ## Core Features & Use Cases - Destructive Command Warnings: Intercepts dangerous Bash commands such as rm -rf, DROP TABLE, and force-push, warning you before execution with the option to override. - Directory-Scoped Edit Boundary: Blocks Edit and Write operations outside a user-specified directory, enforced through PreToolUse hooks. - Use Case: You are hotfixing a bug in a live deployment's config directory. Activate guard mode, restrict edits to that config path, and any accidental edit attempt elsewhere is blocked while risky shell commands prompt for confirmation. ## Quick Start Ask the AI to activate guard mode and restrict edits to a specific directory such as your project's src folder.

Frequently Asked Questions about guard

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

FAQPage Schema
How do I restrict file edits to a specific directory in a coding session?▼

Activate guard mode and provide a directory path when prompted. The skill resolves it to an absolute path, saves it to a freeze state file, and PreToolUse hooks then block Edit and Write operations outside that boundary.

How do I get warnings before running destructive commands like rm -rf?▼

Guard mode registers a PreToolUse hook on Bash that checks commands against destructive patterns such as rm -rf, DROP TABLE, and force-push. Matching commands trigger a warning before execution, and you can choose to override.

Does guard mode require other skills to be installed?▼

Yes. Guard depends on hook scripts from the sibling careful and freeze skill directories. Both are installed together by the gstack setup script, so a standard installation satisfies this dependency.

How do I turn off the edit boundary after activating guard mode?▼

Run the /unfreeze command to remove the directory edit boundary. Destructive command warnings remain active for the session; ending the session deactivates everything.

When should I not use guard mode?▼

Avoid guard mode for routine local development where edits span many directories, since the boundary blocks legitimate changes outside the chosen path. It is intended for high-risk contexts like production or live system work.

Related Skills

Explore More Software Engineering Skills→
aicodeproaicodepro

guard

Combines destructive command warnings with directory-scoped edit restrictions for safer sessions.

Official
Intermediate
VertaKhanVertaKhan

unfreeze

Clears the freeze boundary state file to allow edits in all directories again.

Community
Basic
cogine-aicogine-ai
3

peer-review

Review changed files for logic, security, and error handling issues using Codex CLI.

Official
Advanced
yabafreyabafre
2

aped-ship

Verify integration completeness and run pre-push quality gates for sprint umbrella pull requests.

Community
Advanced