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.
npx skills add pangzhenying2025/hermes-automotive-skills --skill automotive-agent-definitionsgit clone --depth 1 https://github.com/pangzhenying2025/hermes-automotive-skillsWrote 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.
[](https://agentmods.dev/skills/pangzhenying2025/hermes-automotive-skills/automotive-agent-definitions)<a href="https://agentmods.dev/skills/pangzhenying2025/hermes-automotive-skills/automotive-agent-definitions"><img src="https://agentmods.dev/badge/skills/pangzhenying2025/hermes-automotive-skills/automotive-agent-definitions/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.
<a href="https://agentmods.dev/skills/pangzhenying2025/hermes-automotive-skills/automotive-agent-definitions"><img src="https://agentmods.dev/badge/skills/pangzhenying2025/hermes-automotive-skills/automotive-agent-definitions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.00382 |
| Opus 5 | $0.00020 | $0.00191 |
| Sonnet 5 | $0.00008 | $0.00076 |
| Haiku 4.5 | $0.00004 | $0.00038 |
Grade A, and why
automotive-agent-definitions 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.
What it actually says
Automotive Agent Definitions
221 agent definition files for 214 specialized roles.
Available Agents
- adaptive-orchestrator
- adas-perception-engineer
- ai-safety-validator
- api-gateway-specialist
- app-store-manager
- application-engineer
- ar-hud-engineer
- architect
- asil-decomposition-engineer
- aspice-assessor
- auction-based
- automotive-china-compliance-engineer
- automotive-ethernet-engineer
- automotive-scenario-engineer
- automotive-security-architect
- automotive-sotif-analyst
- autonomous-systems-architect
- autosar-adaptive-developer
- aws-iot-automotive-engineer
- azure-digital-twin-engineer
- battery-recycling-specialist
- bms-algorithm-engineer
- bms-engineer
- body-controller-engineer
- calibration-engineer
- change-propagator
- charging-engineer
- charging-infrastructure-engineer
- chassis-systems-engineer
- climate-test-engineer
- cloud-security-architect
- code-generator
- collaborative-editing
- compiler-specialist
- compliance-auditor
- compliance-auditor-21434
- component-specialist
- consensus-builder
- consulting-engineer
- container-orchestrator
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/adas/adas-perception-engineer.md 7.6 KB
- references/adas/autonomous-systems-architect.md 25 KB
- references/adas/control-engineer.yaml 2.2 KB
- references/adas/perception-engineer.yaml 2.7 KB
- references/adas/planning-engineer.yaml 2.0 KB
- references/ai-ecu/ai-safety-validator.yaml 2.9 KB
- references/ai-ecu/edge-ai-deployer.yaml 2.8 KB
- references/ai-ecu/edge-ai-engineer.md 12 KB
- references/ai-ecu/inference-pipeline-engineer.yaml 2.9 KB
- references/ai-ecu/model-compression-specialist.yaml 3.0 KB
- references/ai-ecu/npu-optimization-engineer.yaml 3.0 KB
- references/ai-ecu/training-data-engineer.yaml 2.9 KB
- references/ai-ecu/vision-ai-specialist.md 17 KB
- references/automotive-workflow/financial-manager.yaml 3.7 KB
- references/automotive-workflow/safe-release-train-engineer.yaml 6.6 KB
- references/automotive-workflow/scrum-master.yaml 6.7 KB
- references/automotive-workflow/v-model-orchestrator.yaml 12 KB
- references/autosar/architect.yaml 5.2 KB
- references/battery/bms-engineer.yaml 2.5 KB
- references/battery/charging-engineer.yaml 2.6 KB
- references/battery/thermal-engineer.yaml 2.2 KB
- references/calibration/calibration-engineer.yaml 5.4 KB
- references/china-compliance/automotive-china-compliance-engineer.md 6.7 KB
- references/cloud/api-gateway-specialist.yaml 2.8 KB
- references/cloud/aws-iot-automotive-engineer.yaml 2.8 KB
- references/cloud/azure-digital-twin-engineer.yaml 2.8 KB
- references/cloud/cloud-security-architect.yaml 3.0 KB
- references/cloud/data-lake-architect.yaml 2.8 KB
- references/cloud/fleet-analytics-engineer.yaml 2.9 KB
- references/cockpit/ar-hud-engineer.yaml 3.0 KB
- references/cockpit/haptics-engineer.yaml 3.2 KB
- references/cockpit/hmi-designer.yaml 2.9 KB
- references/cockpit/interior-sensing-specialist.yaml 3.0 KB
- references/cockpit/spatial-audio-engineer.yaml 3.1 KB
- references/cockpit/voice-assistant-engineer.yaml 3.0 KB
- references/core/llm-council.yaml 5.8 KB
- references/core/skill-router.yaml 9.0 KB
- references/core/tool-adapter.yaml 12 KB
- references/cybersecurity/automotive-security-architect.md 4.1 KB
- references/cybersecurity/compliance-auditor-21434.yaml 3.0 KB
- references/cybersecurity/csms-manager.yaml 2.9 KB
- references/cybersecurity/forensics-investigator.yaml 3.1 KB
- references/cybersecurity/penetration-tester.md 5.5 KB
- references/cybersecurity/soc-analyst-automotive.yaml 3.0 KB
- references/cybersecurity/supply-chain-security-analyst.yaml 3.0 KB
- references/cybersecurity/tara-analyst.yaml 3.0 KB
- references/diagnostics/diagnostic-engineer.yaml 4.7 KB
- references/diagnostics/diagnostic-tester.md 15 KB
- references/diagnostics/flash-specialist.yaml 6.2 KB
- references/ev-systems/battery-recycling-specialist.yaml 2.9 KB
- references/ev-systems/bms-algorithm-engineer.yaml 3.1 KB
- references/ev-systems/charging-infrastructure-engineer.yaml 3.0 KB
- references/ev-systems/range-optimization-engineer.yaml 3.0 KB
- references/ev-systems/thermal-management-engineer.yaml 3.0 KB
- references/ev-systems/v2g-integration-engineer.yaml 2.9 KB
- references/functional-safety/asil-decomposition-engineer.yaml 3.1 KB
- references/functional-safety/dependent-failure-analyst.yaml 3.1 KB
- references/functional-safety/fmea-analyst.yaml 2.9 KB
- references/functional-safety/fta-analyst.yaml 3.1 KB
- references/functional-safety/functional-safety-auditor.yaml 3.0 KB
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.
- 12d ago First seen · 55 lines · 41 tokens per session scan A 4636e4d5efc9
automotive-agent-definitions is a skill published in the GitHub repository pangzhenying2025/hermes-automotive-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 382 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.
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…
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'…
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.
misra
MISRA C:2025 expert that operates in two modes: (1) Review — scan existing C code for violations across all 223 guidelines (22 directives + 201 rules), report findings with rule IDs, corrected code, and deviation justification templates; (2) Develop — generate new C functions, modules, or data structures that are…
diagnose-brake-system-problem
Use when experiencing brake warning signs such as noise, pulsation, pulling, soft pedal, or brake warning light to identify the fault before driving or seeking repair.
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.