Safety Guard

This is the kind of thing you turn on before letting Claude run in full-auto mode on a production system. It intercepts destructive commands like `rm -rf`, `git push --force`, and `DROP TABLE` before they execute, then warns you and suggests safer alternatives. You can also freeze edits to a specific directory so an autonomous agent can't touch code outside its scope. Three modes: careful (blocks dangerous commands), freeze (locks edits to one path), or guard (both). It hooks into the tool execution layer and catches things at the Bash, Write, and Edit level. Logs everything it blocks to a file so you can review what would have happened.

Install to Claude Code

npx -y skills add affaan-m/ecc --skill safety-guard --agent claude-code