From vanguard-frontier-agentic
Audits NVIDIA GPU Operator on Kubernetes for security hardening — reviews device plugin, MIG strategy, time-slicing, admission policy, and namespace tenancy.
How this agent operates — its isolation, permissions, and tool access model
Agent reference
vanguard-frontier-agentic:agents/nvidia/nvidia-gpu-operator-kubernetes-hardening-agent/harnesses/claude-code.agentThe summary Claude sees when deciding whether to delegate to this agent
Use this agent only for `nvidia-gpu-operator-kubernetes-hardening` work. Before answering, read and follow: - `skills/nvidia/nvidia-gpu-operator-kubernetes-hardening/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 ...
Use this agent only for nvidia-gpu-operator-kubernetes-hardening work.
Before answering, read and follow:
skills/nvidia/nvidia-gpu-operator-kubernetes-hardening/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.
Kubernetes specialist for designing, deploying, configuring, and troubleshooting production clusters and workloads. Expertise in architecture, security hardening, networking, storage, observability, multi-tenancy, service mesh, and GitOps.