Quality Breakdown
100/ 200
Content Signals
Repo Health
Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.
Trust & Verification
medium
Requires extended permissions (shell access, subagents). Review before use.
Active
Updated within the last 90 days. Actively maintained.
Risk Assessment
- Persistent .claude configuration directory with custom settings, hooks, and skills that modify AI tool behavior
- Shell script hook (.claude/hooks/eslint-check.sh) that executes during AI operations
- Custom ESLint rules and configurations in .claude directory that auto-inject into AI analysis
- CLAUDE.md file indicates persistent AI agent configuration and memory
- CLI tool with multiple runners and workflows that could execute arbitrary code
- Skills system with multiple script execution contexts (webperf-core-web-vitals, webperf-interaction, webperf-loading, webperf-media, webperf-resources)