automotive-hpc

automotive-hpc is a skill for Claude Code, Codex from pangzhenying2025/hermes-automotive-skills. It costs 40 tokens per session (26,911 once invoked), scanned A, original, MIT.

Guidance for high-performance vehicle computers that run many software services, covering the AUTOSAR Adaptive Platform, containers, virtual machines, safety certification, and vehicle computing platforms. AUTOSAR is a set of common standards for automotive software.

In plain words
What is it for?
Use it when designing C++14 applications and services for software-defined vehicles, including communication, process control, logging, diagnostics, updates, and system states.
Why use it?
It helps developers understand how complex vehicle computers are structured and how their services communicate, run, and update.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is - ./data/rosbag:/data:ro.

Good fit Use it when designing C++14 applications and services for software-defined vehicles, including communication, process control, logging, diagnostics, updates, and system states.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/pangzhenying2025/hermes-automotive-skills
agentmods
npx agentmods add skills/pangzhenying2025/hermes-automotive-skills/automotive-hpc

Made for: Claude Code, Codex.

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 automotive-hpc

README.md
[![agentmods](https://agentmods.dev/badge/skills/pangzhenying2025/hermes-automotive-skills/automotive-hpc/github.svg)](https://agentmods.dev/skills/pangzhenying2025/hermes-automotive-skills/automotive-hpc)
Your own site
<a href="https://agentmods.dev/skills/pangzhenying2025/hermes-automotive-skills/automotive-hpc"><img src="https://agentmods.dev/badge/skills/pangzhenying2025/hermes-automotive-skills/automotive-hpc/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 automotive-hpc

Your own site · 80×15
<a href="https://agentmods.dev/skills/pangzhenying2025/hermes-automotive-skills/automotive-hpc"><img src="https://agentmods.dev/badge/skills/pangzhenying2025/hermes-automotive-skills/automotive-hpc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 26,911 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. ✓ AI security review Sonnet 5 · 7 Sept 2026 📄 Read the review
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 $0.00040 $0.26911
Opus 5 $0.00020 $0.13456
Sonnet 5 $0.00008 $0.05382
Haiku 4.5 $0.00004 $0.02691

Measured 12d ago against content hash a843929ddd62, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

automotive-hpc 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 12d 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.

skills/automotive-hpc/SKILL.md · 3,681 lines

How it starts

The opening of the file, as written. The whole thing — 3,681 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Automotive Hpc

Autosar Adaptive

AUTOSAR Adaptive Platform for HPC

Category: automotive-hpc Version: 1.0.0 Maturity: production Complexity: advanced

Overview

Comprehensive guide to AUTOSAR Adaptive Platform (AP) for high-performance computing in Software-Defined Vehicles. Covers service-oriented architecture, ara::com communication, execution management, state management, and C++14 framework development.

Core Competencies

1. AUTOSAR Adaptive Architecture

AUTOSAR Adaptive Platform Stack:

┌─────────────────────────────────────────────────┐
│         Adaptive Applications (C++14)           │
├─────────────────────────────────────────────────┤
│  ara::com  │  ara::exec │  ara::log │  ara::per│
│  ara::diag │  ara::sm   │  ara::ucm │  ara::phm│
├─────────────────────────────────────────────────┤
│          Adaptive Platform Foundation           │
│  - Communication Management (SOME/IP)           │
│  - Execution Management (Process Control)       │
│  - State Management (Function Groups)           │
│  - Update & Config Management                   │
├─────────────────────────────────────────────────┤
│       Operating System (POSIX PSE51)            │
│  - Linux with PREEMPT_RT patch                  │
│  - QNX 7.1 (Safety-certified option)            │
└─────────────────────────────────────────────────┘

2. Service-Oriented Communication (ara::com)

Service Interface Definition (ARXML):

<?xml version="1.0" encoding="UTF-8"?>
<AUTOSAR xmlns="http://autosar.org/schema/r4.0">
    <AR-PACKAGES>
        <AR-PACKAGE>
            <SHORT-NAME>RadarServices</SHORT-NAME>
            <ELEMENTS>
                <!-- Service Interface Definition -->
                <SERVICE-INTERFACE>
                    <SHORT-NAME>RadarFusion</SHORT-NAME>
                    <MAJOR-VERSION>1</MAJOR-VERSION>
                    <MINOR-VERSION>0</MINOR-VERSION>

                    <!-- Events (pub/sub) -->
                    <EVENTS>
                        <VARIABLE-DATA-PROTOTYPE>
                            <SHORT-NAME>ObjectList</SHORT-NAME>
                            <TYPE-TREF DEST="IMPLEMENTATION-DATA-TYPE">/DataTypes/ObjectListType</TYPE-TREF>
                        </VARIABLE-DATA-PROTOTYPE>
                        <VARIABLE-DATA-PROTOTYPE>
                            <SHORT-NAME>FreeSpaceMap</SHORT-NAME>
                            <TYPE-TREF DEST="IMPLEMENTATION-DATA-TYPE">/DataTypes/FreeSpaceMapType</TYPE-TREF>
                        </VARIABLE-DATA-PROTOTYPE>
                    </EVENTS>

                    <!-- Methods (client/server) -->
                    <METHODS>
                        <CLIENT-SERVER-OPERATION>
                            <SHORT-NAME>SetRadarMode</SHORT-NAME>
                            <ARGUMENTS>
                                <ARGUMENT-DATA-PROTOTYPE>
                                    <SHORT-NAME>mode</SHORT-NAME>
                                    <TYPE-TREF DEST="IMPLEMENTATION-DATA-TYPE">/DataTypes/RadarModeType</TYPE-TREF>
                                    <DIRECTION>IN</DIRECTION>
                                </ARGUMENT-DATA-PROTOTYPE>
                                <ARGUMENT-DATA-PROTOTYPE>
                                    <SHORT-NAME>success</SHORT-NAME>
                                    <TYPE-TREF DEST="IMPLEMENTATION-DATA-TYPE">/DataTypes/BooleanType</TYPE-TREF>
                                    <DIRECTION>OUT</DIRECTION>
                                </ARGUMENT-DATA-PROTOTYPE>
                            </ARGUMENTS>
                            <POSSIBLE-ERROR-REFS>
                                <POSSIBLE-ERROR-REF DEST="APPLICATION-ERROR">/Errors/InvalidModeError</POSSIBLE-ERROR-REF>
                            </POSSIBLE-ERROR-REFS>
                        </CLIENT-SERVER-OPERATION>
                    </METHODS>

                    <!-- Fields (getter/setter) -->
                    <FIELDS>
                        <FIELD>
                            <SHORT-NAME>RadarStatus</SHORT-NAME>
                            <TYPE-TREF DEST="IMPLEMENTATION-DATA-TYPE">/DataTypes/RadarStatusType</TYPE-TREF>
                            <HAS-GETTER>true</HAS-GETTER>
                            <HAS-SETTER>false</HAS-SETTER>
                            <HAS-NOTIFIER>true</HAS-NOTIFIER>
                        </FIELD>
                    </FIELDS>
                </SERVICE-INTERFACE>

                <!-- Service Instance Deployment -->
                <SOMEIP-SERVICE-INSTANCE-TO-MACHINE-MAPPING>
                    <SHORT-NAME>RadarFusionInstance</SHORT-NAME>
                    <COMMUNICATION-CONNECTOR-REF DEST="ETHERNET-COMMUNICATION-CONNECTOR">
                        /Network/EthernetConnector
                    </COMMUNICATION-CONNECTOR-REF>
                    <SERVICE-INTERFACE-DEPLOYMENT-REF DEST="SOMEIP-SERVICE-INTERFACE-DEPLOYMENT">
                        /Deployments/RadarFusionDeployment
                    </SERVICE-INTERFACE-DEPLOYMENT-REF>
                    <SOMEIP-SERVICE-INSTANCE-CONFIG>
                        <SERVICE-ID>0x1234</SERVICE-ID>
                        <INSTANCE-ID>0x0001</INSTANCE-ID>
                        <MAJOR-VERSION>1</MAJOR-VERSION>
                        <MINOR-VERSION>0</MINOR-VERSION>
                        <UDP-PORT>30490</UDP-PORT>
                        <TCP-PORT>30491</TCP-PORT>
                    </SOMEIP-SERVICE-INSTANCE-CONFIG>
                </SOMEIP-SERVICE-INSTANCE-TO-MACHINE-MAPPING>
            </ELEMENTS>
        </AR-PACKAGE>
    </AR-PACKAGES>
</AUTOSAR>

Read the full file on GitHub · 3,681 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. 12d ago First seen · 3,681 lines · 40 tokens per session scan E a843929ddd62

Subscribe to this mod's changes

automotive-hpc is a skill published in the GitHub repository pangzhenying2025/hermes-automotive-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 26,911 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

iso26262

ISO 26262 functional-safety expert that operates in two modes: (1) HARA / ASIL determination — enumerate hazardous events from item malfunctions × driving situations, rate Severity (S0–S3), Exposure (E0–E4), Controllability (C0–C3), look up ASIL from ISO 26262-3:2018 Table 4, and produce a HARA report with Safety…

ptsilivis/autonomousguy · 197 tokens

automotive-syseng

When the user wants to analyze automotive requirements, check INCOSE/EARS compliance, review MISRA-C code, assess ADAS levels, or verify ISO 26262/AUTOSAR/SOTIF conformance. Also use when the user says 'check requirements', 'EARS check', 'INCOSE analysis', 'MISRA check', 'ASIL assessment', 'V-model check'…

duonghvu/automotive-syseng · 122 tokens

automotive-expert

Expert-level automotive systems, connected vehicles, fleet management, telematics, ADAS, and automotive software. Use when the user mentions connected car, fleet, telematics, ADAS, or vehicle, or when the task involves Automotive Systems, Technologies, Standards and Protocols, or Fleet Management.

personamanagmentlayer/pcl · 64 tokens

codebase-analysis

First-run skill that walks the entire repository, auto-detects Classic vs Adaptive AUTOSAR, and maps it accordingly. For Classic (default): identifies features and SWCs and documents referenced requirement IDs (SW-REQ-, REQ-, FSR-, SYS-REQ-), port interfaces (S/R, C/S, Mode Switch, Parameter), dependencies on other…

ptsilivis/autonomousguy · 225 tokens

autosar-bsw

AUTOSAR BSW expert. Defaults to Classic AUTOSAR (BSW/MCAL/RTE, static config, C, AUTOSAR OS) and operates in six modes: (1) BSW configuration — Com, NvM, Dem, Dcm, Os, MemIf with dependency chain and EB Tresos / DaVinci container paths; (2) ARXML debugging — classify, locate, and fix consistency errors with a…

ptsilivis/autonomousguy · 285 tokens

autosar-swc

AUTOSAR SWC expert. Defaults to Classic AUTOSAR (SWCs, RTE, ARXML, C) and operates in five modes: (1) Component design — decompose a feature into SWC types, define port interfaces, specify runnables and ExclusiveAreas, produce a plain-text composition diagram; (2) Interface definition — SenderReceiver / ClientServer /…

ptsilivis/autonomousguy · 240 tokens