Warn before destructive commands and restrict file edits to a specified directory.
npx skills add https://github.com/Jia-Hong-Peng/jolike.com --skill guard-jia-hong-peng
Please help me install this Agent Skill. Skill: guard Source: https://github.com/Jia-Hong-Peng/jolike.com/tree/main/.claude/skills/gstack/guard Command: npx skills add https://github.com/Jia-Hong-Peng/jolike.com --skill guard-jia-hong-peng
When working on production systems, critical codebases, or live debugging environments, accidental execution of destructive commands (like rm -rf, DROP TABLE, or force-push) or unintended edits to files outside your target directory can cause irreversible data loss, system outages, or costly hard-to-reverse mistakes.
Ask the AI to activate guard mode and provide the directory you want to restrict edits to, and it will enable both destructive command warnings and block all edits outside that specified path.
High-intent search queries and answers about installing and using this skill.
Preventing destructive command execution in production requires a safety guardrail that intercepts high-risk patterns like rm -rf or DROP TABLE and triggers a pre-execution warning. This allows you to verify or override the action if intentional.
Directory-scoped edit restriction is a safety mechanism that blocks all file write and edit operations outside a user-specified directory path. This limits the operational blast radius to only your intended target area during critical codebase modifications.
You can restrict file write operations during live debugging by activating guard mode and providing a target directory path. This enforces directory-scoped restrictions, automatically blocking any unintended edits to files outside that specific scope.
Yes, command safety guardrails for production system maintenance issue pre-execution warnings for high-risk commands rather than hard blocks. You receive an alert and retain the option to intentionally override the warning to proceed with the action.
You need operational blast radius limits for live environment debugging when working on sensitive code or critical modules to ensure no unintended changes are made. This prevents irreversible data loss by isolating write operations to a specific directory.
alexandervashurinEnforce directory-scoped edits and destructive-command warnings during sensitive operations.
mattothomasEnforces edit boundaries and warns against destructive commands during maintenance and debugging workflows.
oxiePromote validated staging deployments to production with version bump and git release tagging.
OpenCovenManage file system access with explicit read and write permissions within a root directory.
