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.; shellguard: ShellGuard is an MCP server that provides LLM agents with controlled, read-only bash access to remote servers over SSH. It parses and validates every command against an allowlist, blocking destructive operations with helpful suggestions. The LLM can connect, run diagnostics, inspect logs, query databases, and download files without manual context-switching.
Generate MVP agent harness blueprints for any business domain (CRM, ops, finance, healthcare)
Remote server diagnostics and troubleshooting without manual SSH sessions