From core
Assesses blast radius of potentially dangerous operations, requiring explicit user approval before executing destructive actions like deleting data, force-push, or modifying infrastructure.
How this skill is triggered — by the user, by Claude, or both
Slash command
/core:dangerous-actionsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
<dangerous_actions>
<dangerous_actions>
Examples (not limited):
Exceptions (only after blast radius):
</dangerous_actions>
npx claudepluginhub p/griddynamics-core-instructions-r2-coreWarns before destructive commands like rm -rf, DROP TABLE, force-push. Activates when user requests careful mode or safety mode. Useful for prod or shared environments.
Safety guardrails that warn before destructive commands like rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete. Active per session, user can override.
Screens all bash commands for destructive patterns (rm -rf, git push --force, DROP TABLE, etc.) and blocks them with an explanation. Useful in sensitive production environments.