Safe Mode

Three protection levels for AI coding sessions: cautious mode warns before running dangerous commands like rm -rf or git push --force, lockdown mode restricts file edits to a single directory tree, and clear mode turns everything off. The PreToolUse hooks intercept Bash, Edit, and Write operations before they execute. I like the session-scoped lockdown for focused refactoring when you want Claude touching one module and nothing else. The pattern matching is solid, covering the usual footguns plus a few I hadn't thought about like piped curl to shell. This isn't a substitute for version control, but it's a reasonable guardrail when working in unfamiliar codebases or letting AI make sweeping changes.

Install to Claude Code

npx -y skills add rohitg00/pro-workflow --skill safe-mode --agent claude-code