Warn on destructive commands and restrict edits to a specified directory.
npx skills add https://github.com/VertaKhan/cs_gstack --skill guard-vertakhan
Please help me install this Agent Skill. Skill: guard Source: https://github.com/VertaKhan/cs_gstack/tree/main/.claude/skills/gstack/guard Command: npx skills add https://github.com/VertaKhan/cs_gstack --skill guard-vertakhan
Provides a safety surface that warns about destructive commands and enforces directory-scoped edits to prevent accidental or malicious changes in critical environments.
Provide the target directory and run guard mode to enable full safety.
High-intent search queries and answers about installing and using this skill.
Guard mode prevents destructive commands by warning on dangerous operations like rm -rf, DROP TABLE, or force-push, requiring confirmation before execution to protect critical environments during maintenance.
Directory-bound edit enforcement restricts file modifications to a specified target directory, blocking changes outside the boundary to maintain controlled change boundaries and auditability during debugging.
Provide the target directory and enable guard mode to enforce directory-scoped edits, preventing accidental or malicious file modifications outside the specified boundary path.
Yes, the safety workflow leverages Bash, Read, and AskUserQuestion tools, coordinating sibling scripts to perform pre-use checks and integrate command-safety warnings within existing workflows.
Guard mode has no formal dependencies but coordinates lightweight sibling scripts for pre-use checks, utilizing Bash, Read, and AskUserQuestion tools to enforce edit boundaries and destructive-command warnings.
catlog22Configure directory-level write boundaries for workflow guard enforcement.
caozx1110Standardize analysis of research units with evidence-bound prepare-fill-verify workflows.
ekrishguptaWarn before destructive commands and restrict edits to a directory scope.
huichenWarn on destructive commands and restrict edits to a specified directory.
