agents-best-practices: A provider-neutral Agent Skill library for designing, auditing, and refactoring agentic harnesses compatible with Codex and Claude Code. It covers the full control plane of an agent runtime: typed tool design, permission checks, context management, memory, and observability. Targeted at developers building production-ready agent systems across any domain or AI provider.; unraid-mcp: This MCP server translates tool calls into Unraid GraphQL queries and mutations over HTTP and WebSocket. It provides a comprehensive set of actions for system inspection, health checks, array management, Docker, VM, notifications, and more. Destructive operations require explicit confirmation to prevent accidents.
Generate MVP agent harness blueprints for any business domain (CRM, ops, finance, healthcare)
System inspection and monitoring