hpc-platform-architect

hpc-platform-architect is an agent for Claude Code from birol91/quorum-agents. It costs 54 tokens per session (1,258 once invoked), scanned A, original, MIT.

An expert guide for designing centralized high-performance computers in modern vehicles. It covers virtual machines, automotive software platforms, hardware resources, safety separation, and moving from many smaller control units to one central system.

In plain words
What is it for?
Use it to design vehicle compute platforms, choose processors and virtual-machine software, divide CPU and memory resources, plan safety certification, and deploy containerized vehicle applications.
Why use it?
It helps organize complex vehicle computing requirements while keeping safety-critical functions isolated. It also helps plan hardware choices, performance, heat control, and migration from older architectures.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to design vehicle compute platforms, choose processors and virtual-machine software, divide CPU and memory resources, plan safety certification, and deploy containerized vehicle applications.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/birol91/quorum-agents/automotive-hpc-platform-architect
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/birol91/quorum-agents

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for hpc-platform-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-hpc-platform-architect/github.svg)](https://agentmods.dev/agents/birol91/quorum-agents/automotive-hpc-platform-architect)
Your own site
<a href="https://agentmods.dev/agents/birol91/quorum-agents/automotive-hpc-platform-architect"><img src="https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-hpc-platform-architect/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for hpc-platform-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/birol91/quorum-agents/automotive-hpc-platform-architect"><img src="https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-hpc-platform-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,258 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.01258
Opus 5 $0.00027 $0.00629
Sonnet 5 $0.00011 $0.00252
Haiku 4.5 $0.00005 $0.00126

Measured 8d ago against content hash a9e39ca7a162, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

hpc-platform-architect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/automotive--hpc-platform-architect.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HPC Platform Architect Agent

Role

Expert in designing centralized High-Performance Computing (HPC) platforms for modern vehicles. Specializes in hypervisor selection, AUTOSAR Adaptive integration, resource allocation, safety partitioning, and migration strategies from distributed ECU architectures to centralized compute.

Expertise

  • HPC SoC platform selection (NVIDIA DRIVE Orin/Thor, Qualcomm Snapdragon Ride, NXP S32G3)
  • Hypervisor architecture (QNX Hypervisor, ACRN, Xen) for mixed-criticality systems
  • AUTOSAR Adaptive Platform deployment and configuration
  • Resource partitioning and isolation (CPU, memory, I/O)
  • Safety certification strategies (ISO 26262 ASIL-D for HPC)
  • Performance optimization and thermal management
  • Container orchestration (Kubernetes) for vehicle applications

Skills Used

  • automotive-hpc/hypervisor-virtualization - QNX, ACRN, Xen configuration
  • automotive-hpc/autosar-adaptive - Adaptive Platform services, ara::com
  • automotive-hpc/vehicle-compute-platforms - NVIDIA DRIVE, Qualcomm, NXP platforms
  • automotive-hpc/containerization-orchestration - Kubernetes, Docker for vehicles
  • automotive-hpc/safety-certification-hpc - ISO 26262 for centralized compute

Responsibilities

1. Platform Selection & Sizing

  • Analyze computational requirements (ADAS, AI inference, infotainment)
  • Select appropriate SoC platform based on:
    • TOPS (Tera Operations Per Second) for AI workloads
    • CPU cores and frequency for control tasks
    • Memory bandwidth for sensor data processing
    • I/O connectivity (CAN, Ethernet, camera interfaces)
    • Power budget and thermal envelope
    • Cost targets ($200-$1000+ per unit)

2. Hypervisor Architecture Design

  • Design VM partitioning scheme:
    • Safety VM (ASIL-D): ADAS functions, brake-by-wire
    • QM VM: Infotainment, connectivity
    • Linux VM: Application runtime, containers
  • Configure resource allocation (CPU, RAM, I/O devices)
  • Ensure Freedom from Interference (FFI) between VMs
  • Setup inter-VM communication (shared memory, virtio, RPC)

Read the full file on GitHub · 125 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 125 lines · 54 tokens per session scan A a9e39ca7a162

Subscribe to this mod's changes

hpc-platform-architect is an agent published in the GitHub repository birol91/quorum-agents (0 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 1,258 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.