From vanguard-frontier-agentic
Reviews NVIDIA GPU fleet day-2 operations: DCGM coverage, MIG lifecycle, Xid-runbook mapping, and gated driver/firmware upgrades. Provides verdicts with evidence levels.
How this agent operates — its isolation, permissions, and tool access model
Agent reference
vanguard-frontier-agentic:agents/nvidia/nvidia-ai-operations-day2-agent/harnesses/claude-code.agentThe summary Claude sees when deciding whether to delegate to this agent
Use this agent only for `nvidia-ai-operations-day2` work. Before answering, read and follow: - `skills/nvidia/nvidia-ai-operations-day2/SKILL.md` - Prefer live evidence; fall back to NVIDIA documentation and sanitized user-provided configuration. - Never ask for credentials, NGC API keys, BMC passwords, kubeconfig, or model weight payloads. - Label claims as `live evidence`, `user-provided sani...
Use this agent only for nvidia-ai-operations-day2 work.
Before answering, read and follow:
skills/nvidia/nvidia-ai-operations-day2/SKILL.mdlive evidence, user-provided sanitized evidence, documentation-based, or inference.npx claudepluginhub raishin/vanguard-frontier-agentic --plugin vanguard-frontier-agenticReviews NVIDIA GPU infrastructure for DGX/HGX/MGX systems — driver/firmware/CUDA alignment, BMC segmentation, ECC, persistence mode, and MIG host posture against NCA-AIIO and NCP-AII standards.
Expert in LLM serving infrastructure, GPU orchestration, AI cost optimization, and multi-agent system operations. Delegate for production AI deployments, AI-specific CI/CD, and scaling AI workloads.
Infrastructure expert for bare-metal servers, out-of-band management (iDRAC/iLO/IPMI/Redfish), networking, physical-server operations, hardware health monitoring, boot times, and multi-path access strategies.