Skill of Skills
📄 skillActivePromisinghigh

ClawKeeper

by SafeAI-Lab-X

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers (aka The Norton for OpenClaw)

Supported Platforms

🤖 Claude Code🧠 Codex

Stars

1.0k

Skill Type

⚙️ Infrastructure Operations

Quality Score

104/200

License

Unknown

Forks

55

Last Updated

Jun 11, 2026

Discovered

May 10, 2026

Validation

Passed

github.com/SafeAI-Lab-X/ClawKeeper

Quality Breakdown

104/ 200

Content Signals

○Gotchas/Edge Cases+40
✓Progressive Disclosure+30
○Trigger Description+20
○Verification/Safety+20
✓Code Examples+15
✓Composability+15

Repo Health

✓Recent Activity+15
✓Scripts/Automation+10
✓Real Usage (Issues)+10
✓Single Responsibility+10
✓Config/Persistence+10
✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

high

Broad system access required. Carefully review permissions before installing.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Multiple install scripts present (install.sh, install.ps1) that execute without explicit user approval gates
  • Bash/shell execution capabilities explicitly defined in tool-schemas (bash.json)
  • Plugin-based runtime interception system that modifies agent behavior at execution level
  • File write capabilities (write_file.json) combined with execution gates
  • Multi-agent spawning architecture documented in .agents directory with autonomous skills
  • Watcher system designed for 'real-time execution intervention' and 'halting high-risk actions'