From openclaw-cc
<!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly. Run: node scripts/gen-skill-docs.mjs -->
How this skill is triggered — by the user, by Claude, or both
Slash command
/openclaw-cc:carefulThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
<!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly. Run: node scripts/gen-skill-docs.mjs -->
name: careful description: > Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. Triggers on "careful", "조심", "안전 모드", "prod mode", "safety mode", "프로덕션 모드", "be careful", "careful mode". allowed-tools:
Safety mode is now active. Every bash command will be checked for destructive patterns before running. If a destructive command is detected, you'll be warned and can choose to proceed or cancel.
Before executing this skill:
Load context from memory:
memory_search(query: "{skill-relevant-query}", associative: true, limit: 5)
memory_search(tag: "{skill-name}", limit: 3)
Review returned memories for relevant past context, decisions, and patterns.
Check OMC state for active work:
state_get_status()
If conflicting active tasks exist, warn the user before proceeding.
Detect current branch (for git-related skills):
git rev-parse --abbrev-ref HEAD 2>/dev/null || echo "not-a-git-repo"
Check proactive mode:
state_read("occ-proactive")
If "false": do NOT proactively suggest other OpenClaw-CC skills during this session.
Only run skills the user explicitly invokes.
Log skill activation:
memory_daily_log(type: "note", entry: "Skill activated: /{skill-name}")
| Pattern | Example | Risk |
|---|---|---|
rm -rf / rm -r / rm --recursive | rm -rf /var/data | Recursive delete |
DROP TABLE / DROP DATABASE | DROP TABLE users; | Data loss |
TRUNCATE | TRUNCATE orders; | Data loss |
git push --force / -f | git push -f origin main | History rewrite |
git reset --hard | git reset --hard HEAD~3 | Uncommitted work loss |
git checkout . / git restore . | git checkout . | Uncommitted work loss |
kubectl delete | kubectl delete pod | Production impact |
docker rm -f / docker system prune | docker system prune -a | Container/image loss |
DELETE FROM (without WHERE) | DELETE FROM users | Mass data deletion |
These patterns are allowed without warning:
rm -rf node_modules / .next / dist / __pycache__ / .cache / build / .turbo / coverage / .omcThe hook reads the command from the tool input JSON, checks it against the
patterns above, and returns permissionDecision: "ask" with a warning message
if a match is found. You can always override the warning and proceed.
memory_daily_log(type: "note", entry: "Safety mode activated: /careful")
To deactivate, end the conversation or start a new one. Hooks are session-scoped.
Every skill must end with one of these status codes:
| Code | Meaning | When to Use |
|---|---|---|
| DONE | All steps completed, evidence provided | Root cause found + fix verified, PR created, review finished |
| DONE_WITH_CONCERNS | Completed with warnings or caveats | Tests pass but coverage dropped, fix applied but can't fully verify |
| BLOCKED | Cannot proceed, requires user intervention | 3 failed attempts, missing permissions, external dependency down |
| NEEDS_CONTEXT | Missing information to continue | Unclear requirements, need user clarification |
3-strike rule: After 3 failed attempts at any step, STOP and escalate to user. Do not continue guessing. Present what was tried and ask for direction.
Scope escalation: If fix/change touches 5+ files unexpectedly, pause and confirm with the user before proceeding.
Security uncertainty: If you are unsure about a security implication, STOP and escalate. Never guess on security.
Verification requirement: Never claim DONE without evidence.
═══════════════════════════════════════
Status: {DONE | DONE_WITH_CONCERNS | BLOCKED | NEEDS_CONTEXT}
Summary: {one-line description of outcome}
Evidence: {test output, verification results, or blocking reason}
═══════════════════════════════════════
npx claudepluginhub kit4some/oh-my-claudeclaw --plugin openclaw-ccWarns 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.
Blocks destructive Bash commands like rm -rf, DROP TABLE, git force-push, reset --hard, and restricts file edits to a specific directory. Use for protection on critical systems.
Prevents destructive operations via three modes: cautious (warns on dangerous commands like rm -rf, git push --force, SQL drops), lockdown (restricts edits to one directory), and clear (removes restrictions). Uses PreToolUse hooks for Bash, Edit, and Write.