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.; node9-proxy: Node9 is an execution security layer for AI agents that intercepts dangerous shell commands and tool calls in real-time. It features a multi-channel approval system (native popup, browser, Slack, terminal), a flight recorder for live monitoring, and an AI negotiation loop to guide safer behavior. It also includes DLP content scanning and shadow git snapshots for undo.
Generate MVP agent harness blueprints for any business domain (CRM, ops, finance, healthcare)
Protect AI agents from executing dangerous commands during development