Quality Breakdown
117/ 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
high
Broad system access required. Carefully review permissions before installing.
Active
Updated within the last 90 days. Actively maintained.
Risk Assessment
- Persistent AI agent configuration in .claude/ directory with multiple agents (planner, researcher) and custom commands (execute, commit, create-pr) that can modify repository state
- GitHub Actions workflows including claude.yml that could execute autonomous agent operations during CI/CD
- Multi-agent spawning capability evidenced by .claude/agents/ directory structure with defined agents that can be orchestrated
- Custom command definitions (.claude/commands/execute.md) suggesting shell/bash execution capabilities without clear approval gates
- CLAUDE.md and SELF-HOSTING.md files indicate this is an AI agent framework itself, creating nested AI automation risk
- DevContainer and Docker configurations (.devcontainer/setup.sh, Dockerfile) providing bootstrap automation