Quality Breakdown
97/ 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
- Autonomous agent system with multi-agent spawning capability (agents/agents.ts, agents/runtime.ts) that operates without explicit human approval gates
- Command execution capability (exec-tool.ts, command-executor.ts) allowing arbitrary shell/bash command execution
- External code execution via MCP (Model Context Protocol) integration (mcp-integration/skill.ts) enabling third-party tool execution
- Persistent configuration and memory modification with CLAUDE.md file indicating persistent context storage
- Workflow authoring and autonomous workflow execution (workflow-authoring/skill.ts, workflow-run-ops/skill.ts) without apparent human approval checkpoints
- Gmail and calendar synchronization with external service access (sync_gmail.ts, sync_calendar.ts) suggesting credential handling and data extraction