Blocks destructive commands like rm -rf, git force-push, kubectl delete on production systems and autonomous agents. Locks file edits to specific directories.
From everything-claude-codenpx claudepluginhub binzetss/mobile-hvgllocalThis skill uses the workspace's default tool permissions.
Generates platform-native social content for X, LinkedIn, TikTok, YouTube, newsletters from source material like articles, demos, docs, or notes. Adapts voice and format per platform.
Caches expensive file processing (PDFs, text extraction, images) using SHA-256 content hashes for path-independent, auto-invalidating JSON storage in Python.
Reorganizes X and LinkedIn networks: review-first pruning of low-value follows, priority-based add/follow recommendations, and drafts warm outreach in user's voice.
Three modes of protection:
Intercepts destructive commands before execution and warns:
Watched patterns:
- rm -rf (especially /, ~, or project root)
- git push --force
- git reset --hard
- git checkout . (discard all changes)
- DROP TABLE / DROP DATABASE
- docker system prune
- kubectl delete
- chmod 777
- sudo rm
- npm publish (accidental publishes)
- Any command with --no-verify
When detected: shows what the command does, asks for confirmation, suggests safer alternative.
Locks file edits to a specific directory tree:
/safety-guard freeze src/components/
Any Write/Edit outside src/components/ is blocked with an explanation. Useful when you want an agent to focus on one area without touching unrelated code.
Both protections active. Maximum safety for autonomous agents.
/safety-guard guard --dir src/api/ --allow-read-all
Agents can read anything but only write to src/api/. Destructive commands are blocked everywhere.
/safety-guard off
Uses PreToolUse hooks to intercept Bash, Write, Edit, and MultiEdit tool calls. Checks the command/path against the active rules before allowing execution.
codex -a never sessions~/.claude/safety-guard.log