Warn before executing destructive Bash commands via a PreToolUse hook.
npx skills add https://github.com/legotec73/gstack --skill careful-legotec73
Please help me install this Agent Skill. Skill: careful Source: https://github.com/legotec73/gstack/tree/main/careful Command: npx skills add https://github.com/legotec73/gstack --skill careful-legotec73
Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful mode".
Describe the destructive command you are about to run and let careful warn you with an option to proceed or cancel.
High-intent search queries and answers about installing and using this skill.
Guarding destructive commands like rm -rf requires a PreToolUse hook that analyzes commands before execution. This Skill intercepts dangerous bash operations in interactive shells or scripts, returning a permission decision to ask or allow before proceeding.
Yes, safety guardrails for git reset --hard and kubectl delete can be applied across CI pipelines and automated scripts. The mechanism analyzes commands and logs usage for auditing while providing per-command override options to maintain workflow.
Yes, this safety mode tool works with python3 and bash environments. It depends on bash, grep, sed, and python3 to analyze commands and return permission decisions, applying effectively across shared environments and live system debugging.
The best way to warn before executing DROP TABLE statements in automated scripts is using a PreToolUse hook that analyzes commands for destructive operations. This approach returns a permission decision of ask or allow, enabling user overrides while logging usage for auditing.
Overriding a destructive command warning when debugging live systems is handled via per-command override options. When the guardrail intercepts an operation like force-push, it prompts the user, allowing you to proceed with the action or cancel it entirely.
alangebProcess system logs and test outputs with Unix command-line utilities.
sajalsuhaneAnalyze shell commands and warn before destructive operations execute.
iyakiEnforce non-interactive shell execution in CI environments.
npc-chrisScan bash commands for destructive patterns and warn before execution.
