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.

skills.sh installs: 164
GitHub stars: 2.9K
last updated: Jun 8, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Safe Mode

Three levels of protection against destructive operations during AI coding sessions.

Note: These hooks are skill-scoped — they only activate when you invoke /safe-mode. The global permission-request.js hook in hooks.json provides always-on alerting for dangerous commands. Safe-mode adds opt-in blocking and directory restrictions on top of that.

Modes

Cautious Mode

/safe-mode cautious

Intercepts Bash commands before execution. Warns on dangerous patterns but does not block — the user decides.

Flagged patterns:

Pattern	Risk
`rm -rf` / `rm -r`	Recursive deletion
`DROP TABLE` / `DROP DATABASE`	SQL data loss
`TRUNCATE`	SQL data destruction
`git push --force` / `git push -f`	Remote history rewrite
`git reset --hard`	Local history loss
`git clean -f`	Untracked file deletion
`git checkout .` / `git restore .`	Discard all changes
`chmod 777`	World-writable permissions
`curl` or `wget` piped to a shell	Piped remote execution
`> /dev/sda` / `dd if=`	Disk-level operations
`:(){ :\|:& };:`	Fork bombs
`sudo rm`	Elevated deletion