skills.rest
tgmarinho
tgmarinhoCOMMUNITY
Explore all skills by this author →
Website𝕏@tgmarinhoGitHub

guard

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

Updated May 15, 2026
Search Tags:#claude code#hooks#safety#freeze#edit boundary#destructive commands#guard mode
One-click install
npx skills add https://github.com/tgmarinho/canetaco --skill guard-tgmarinho
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/tgmarinho/canetaco/tree/main/.claude/skills/guard
Command: npx skills add https://github.com/tgmarinho/canetaco --skill guard-tgmarinho

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? When working on production systems or debugging live environments, a single destructive command (rm -rf, DROP TABLE, force-push) or an edit to the wrong file can cause serious damage. Guard mode activates two layers of protection at once so risky operations are caught before they execute. ## Core Features & Use Cases - Destructive Command Warnings: Intercepts Bash commands matching dangerous patterns (rm -rf, DROP TABLE, force-push) and warns before execution, with the option to override. - Directory-Scoped Edit Boundary: Blocks Edit and Write operations outside a user-specified directory, enforced via PreToolUse hooks. - Combined Activation: Merges the /careful and /freeze skills into a single command for maximum safety in one step. - Use Case: You are hotfixing a bug in a live repository and only want changes inside the app/api/ folder. Activate guard mode, set the boundary to app/api/, and any accidental edit elsewhere is blocked while dangerous shell commands trigger a warning. ## Quick Start Ask the AI to activate guard mode and restrict edits to a specific directory such as src/.

Frequently Asked Questions about guard

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

FAQPage Schema
How do I block edits outside a specific directory in Claude Code?▼

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 any Edit or Write operation targeting files 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 it.

Does guard mode work without the careful and freeze skills installed?▼

No. Guard mode references hook scripts from the sibling careful and freeze skill directories, so both must be installed. They are installed together by the gstack setup script.

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

Run /unfreeze to remove the directory edit boundary while keeping the session active. To deactivate all protections entirely, end the session.

Can I override a destructive command warning in guard mode?▼

Yes. Destructive command warnings are advisory and can be overridden by the user. The edit boundary, however, is a hard block on files outside the frozen directory until /unfreeze is run.

Related Skills

Explore More Software Engineering Skills→
EhsaanArkEhsaanArk

guard

Enable guard mode to warn before destructive commands and restrict edits to a directory.

Community
Advanced
nocnocgroupnocnocgroup

unfreeze

Clear the freeze state file to lift edit restrictions across directories.

Official
Basic
DataKnifeAIDataKnifeAI

security-management

Audit Protect surveillance access controls and user permissions for compliance.

Official
Advanced
alexandervashurinalexandervashurin

guard

Enforce directory-scoped edits and destructive-command warnings during sensitive operations.

Community
Advanced