Detect risky shell, Git, Docker, and Kubernetes commands and prompt for confirmation.
npx skills add https://github.com/rkumar261/studio-cast --skill careful-rkumar261
Please help me install this Agent Skill. Skill: careful Source: https://github.com/rkumar261/studio-cast/tree/main/.claude/skills/gstack/careful Command: npx skills add https://github.com/rkumar261/studio-cast --skill careful-rkumar261
Safety mode protects destructive shell operations by warning users before proceeding.
Enable careful mode and attempt a destructive command to see the warning prompt.
High-intent search queries and answers about installing and using this skill.
Guard rules detect risky command patterns like rm -rf or git reset --hard and require explicit user approval before execution proceeds in shell, version-control, or container management workflows.
Yes, the safety guardrails support user overrides, allowing you to bypass the warning prompt and proceed with executing destructive Git or Kubernetes commands when the action is truly needed.
Yes, the destructive command safety guardrails apply to Kubernetes workflows, detecting and warning against risky operations like kubectl delete across both development and production environments.
Custom guard rules for risky bash commands must be explicitly defined to match specific command patterns, enabling the system to intercept and prompt for confirmation before proceeding with those operations.
Yes, the command warning prompt stores audit data locally, logging usage metrics of risky operations to help teams study command patterns without exposing sensitive secrets.
pistosminWarn before executing destructive shell, Git, and Kubernetes commands.
mulyovedWarns before executing risky Bash commands via a PreToolUse hook with per-command overrides and usage logging.
XinheLIUWarn before executing destructive shell commands across Bash, Git, Kubernetes, Docker, and databases.
ComputerConnectionDetects destructive shell commands and prompts for confirmation via a Bash pre-execution hook.
