skills/safe-mode/SKILL.md
Prevent destructive operations using Claude Code hooks. Three modes — cautious (warn on dangerous commands), lockdown (restrict edits to one directory), and clear (remove restrictions). Uses PreToolUse matchers for Bash, Edit, and Write.
npx skillsauth add rohitg00/pro-workflow safe-modeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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 globalpermission-request.jshook in hooks.json provides always-on alerting for dangerous commands. Safe-mode adds opt-in blocking and directory restrictions on top of that.
/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 |
What happens:
WARNING: Destructive operation detected
Command: rm -rf ./build
Pattern: rm -rf (recursive forced deletion)
Risk: Permanently deletes ./build and all contents
Proceed? The command will execute as-is if you continue.
The warning goes to stderr. Claude sees it and asks for confirmation before proceeding.
/safe-mode lockdown <path>
Restricts Edit and Write operations to a single directory tree. Prevents accidental changes to unrelated code.
How it works:
LOCKDOWN ACTIVE: Edits restricted to src/api/
Blocked: Edit to src/utils/helpers.ts
Reason: File is outside the lockdown path (src/api/)
To edit files outside the lockdown, run: /safe-mode clear
Use cases:
Scope: Session-scoped. Resets when the session ends.
/safe-mode clear
Removes all restrictions for the current session. Both cautious warnings and lockdown restrictions are disabled.
SAFE MODE: All restrictions cleared for this session.
The hook inspects tool_input.command before every Bash execution:
const DANGEROUS_PATTERNS = [
{ pattern: /\brm\s+(-[a-zA-Z]*[rf][a-zA-Z]*\s|--recursive|--force)/, label: "rm with -rf flags" },
{ pattern: /\bDROP\s+(TABLE|DATABASE|INDEX|VIEW)\b/i, label: "DROP SQL statement" },
{ pattern: /\bTRUNCATE\b/i, label: "TRUNCATE SQL statement" },
{ pattern: /\bgit\s+push\s+(-[a-zA-Z]*f|--force)/, label: "git force-push" },
{ pattern: /\bgit\s+reset\s+--hard\b/, label: "git hard reset" },
{ pattern: /\bgit\s+clean\s+-[a-zA-Z]*f/, label: "git clean -f" },
{ pattern: /\bgit\s+(checkout|restore)\s+\./, label: "git discard all changes" },
{ pattern: /\bchmod\s+777\b/, label: "chmod 777" },
{ pattern: /\bcurl\b.*\|\s*(sh|bash)\b/, label: "piped remote execution" },
{ pattern: /\bwget\b.*\|\s*(sh|bash)\b/, label: "piped remote execution" },
{ pattern: /\bsudo\s+rm\b/, label: "elevated deletion" },
];
Match found → emit warning to stderr. No match → pass through silently.
The hook checks tool_input.file_path against the lockdown path:
function isInsideLockdown(filePath, lockdownPath) {
const resolved = fs.realpathSync(path.resolve(filePath));
const allowed = fs.realpathSync(path.resolve(lockdownPath));
const rel = path.relative(allowed, resolved);
return rel === '' || (!rel.startsWith('..') && !path.isAbsolute(rel));
}
Inside lockdown path → pass through. Outside → block with explanation.
Mode state lives in a session-scoped temp file (keyed by session ID to avoid cross-session leaks):
$TMPDIR/pro-workflow/safe-mode-<sessionId>.json
{
"mode": "lockdown",
"lockdownPath": "/Users/dev/project/src/api",
"sessionId": "abc123",
"activatedAt": "2026-03-28T10:00:00Z"
}
Cleared by /safe-mode clear. State persists until explicitly cleared or the temp file is manually removed. Each session has its own state file.
Cautious and lockdown can run simultaneously:
/safe-mode cautious
/safe-mode lockdown src/api/
Now you get:
src/api/ onlyClear removes both.
| Situation | Mode | |-----------|------| | Working on production-adjacent code | Cautious | | Focused refactoring of one module | Lockdown | | Unfamiliar codebase, feeling cautious | Cautious | | Pair programming, limiting AI scope | Lockdown | | Done with restrictions | Clear |
devops
SkillOpt-flavored offline training loop for any SKILL.md. Treats accumulated learn-rule corrections as training trajectories, proposes bounded patches via an optimizer LLM, gates each candidate against a held-out validation set built from the user's own past corrections, and ships only candidates that demonstrably improve the score. Inspired by Microsoft SkillOpt's ReflACT pipeline (rollout → reflect → aggregate → select → update → evaluate) adapted to pro-workflow's SQLite store. Use when a skill has accumulated 8+ learn-rule rows and the user wants the skill itself to get better, not just longer.
development
Complete AI coding workflow system. Orchestration patterns, 18 hook events, 5 agents, cross-agent support, reference guides, and searchable learnings. Works with Claude Code, Cursor, and 32+ agents.
data-ai
Analyze permission denial patterns and generate optimized alwaysAllow and alwaysDeny rules. Use when permission prompts are slowing you down or after sessions with many denials.
tools
Auto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate tooling. Use when onboarding a new codebase.