Quality Breakdown
85/ 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
- Multi-agent spawning capability: Repository contains .agents directory with multiple skill definitions (anthropic-sdk-upgrader, launch) suggesting autonomous agent orchestration
- Autonomous command execution: README explicitly states agents 'autonomously planning work, editing files, running commands, and self-correcting' without explicit human approval gates per operation
- Terminal/shell access patterns: References to 'running terminal commands' and task automation indicate shell execution capabilities
- Complex automation workflows: GitHub Actions workflows (.github/workflows/) and devcontainer configurations suggest automated execution pipelines
- Official Microsoft repository: Significantly mitigates risk - this is a legitimate vendor tool (Microsoft/GitHub Copilot) with expected autonomous capabilities as core product feature