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-sotif-hazard-scenariogit 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-sotif-hazard-scenario)<a href="https://agentmods.dev/skills/pangzhenying2025/hermes-automotive-skills/automotive-sotif-hazard-scenario"><img src="https://agentmods.dev/badge/skills/pangzhenying2025/hermes-automotive-skills/automotive-sotif-hazard-scenario/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-sotif-hazard-scenario"><img src="https://agentmods.dev/badge/skills/pangzhenying2025/hermes-automotive-skills/automotive-sotif-hazard-scenario.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 | $0.00027 | $0.02871 |
| Opus 5 | $0.00014 | $0.01435 |
| Sonnet 5 | $0.00005 | $0.00574 |
| Haiku 4.5 | $0.00003 | $0.00287 |
Grade A, and why
automotive-sotif-hazard-scenario 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automotive Sotif Hazard Scenario
Sotif Hazard Scenario
SOTIF Hazard Scenario Construction — Systematic Identification and Analysis
Overview
Deep methodology for SOTIF (Safety Of The Intended Functionality, ISO 21448) hazard scenario identification, construction, and analysis. This skill goes beyond basic SOTIF overview to provide actionable frameworks for identifying triggering conditions, constructing hazardous scenarios, and systematically reducing the unknown unsafe area.
The Four-Quadrant Framework (Deep Dive)
ISO 21448 Four-Quadrant Model
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Known Unknown
┌─────────────────┬─────────────────┐
│ Area 1 │ Area 3 │
Safe │ Known Safe │ Unknown Safe │
│ 已知安全 │ 未知安全 │
│ │ │
│ ✓ Normal ops │ ? Safe but │
│ ✓ Validated │ undiscovered │
├─────────────────┼─────────────────┤
│ Area 2 │ Area 4 │
Unsafe │ Known Unsafe │ Unknown │
│ 已知不安全 │ Unsafe │
│ │ 未知不安全 │
│ ⚠ Identified │ ✗ Greatest risk │
│ ⚠ Mitigated │ ✗ Must minimize │
└─────────────────┴─────────────────┘
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
SOTIF Goal: Minimize Area 4 (unknown unsafe)
by moving scenarios to Area 2 (known unsafe → mitigated)
or Area 1 (known safe → validated)
Triggering Condition Taxonomy
Systematic Identification Method
# Triggering Condition Identification Framework
triggering_conditions = {
"sensing_limitations": {
"camera": {
"illumination": [
"Direct sunlight / sun glare (太阳眩光)",
"Low sun angle (5°-15° elevation)",
"Tunnel entry/exit (dark-bright transition)",
"Night without street lights",
"LED traffic light flicker (PWM)",
"Headlight reflection on wet road",
],
"weather": [
"Heavy rain (>25mm/h)",
"Fog (visibility <200m)",
"Snow (lens covered / white-out)",
"Haze/smog (PM2.5 >200 in China)",
"Sandstorm (Northern China specific)",
],
"occlusion": [
"Lens contamination (mud, insects, water drops)",
"Partial blockage by adjacent objects",
"Wiper interference during rain",
"Ice/frost on lens",
],
"perception_failures": [
"White vehicle against white sky",
"Black vehicle in shadow",
"Motorcycle/bicycle thin profile",
"Unusual vehicle shapes (overloaded truck)",
"Road debris vs. road texture confusion",
"Lane marking worn/faded/absent",
"Temporary vs. permanent lane markings",
],
},
"radar": {
"interference": [
"Multi-path reflection (guardrails, tunnels)",
"Adjacent vehicle radar interference",
"Metallic bridge overhead reflection",
"Rain clutter (heavy precipitation)",
],
"missed_detection": [
"Stationary objects (bridge pillars, barriers)",
"Low-RCS targets (motorcycle, pedestrian)",
"Crossing targets at extreme angles",
"Speed-ambiguity (relative speed near zero)",
],
"false_detection": [
"Manhole covers (strong radar return)",
"Metal debris on road",
"Overhead signs/structures (elevated targets)",
"Guardrail reflections as ghost targets",
],
},
"lidar": {
"limitations": [
"Black/dark surfaces (low reflectivity)",
"Transparent objects (glass barriers)",
"Rain/fog scattering",
"Direct sunlight saturation",
"Dust/dirt on sensor window",
],
},
"gnss_localization": {
"degradation": [
"Urban canyon (tall buildings)",
"Tunnel (no GNSS signal)",
"Dense tree canopy",
"Multi-path interference (bridges)",
"Jamming/spoofing",
],
},
},
"algorithm_limitations": {
"perception": [
"Out-of-distribution objects (rare objects)",
"Adversarial patterns (adversarial patches)",
"Domain shift (training vs. deployment environment)",
"Class confusion (truck rear vs. wall)",
"Tracking ID switch (occluded targets)",
],
"prediction": [
"Unpredictable human behavior (jaywalker)",
"Unusual vehicle maneuvers (illegal U-turn)",
"Group behavior (crowd crossing)",
"Intention ambiguity (vehicle drifting in lane)",
],
"planning": [
"Conflicting objectives (comfort vs. safety)",
"Rare road geometry (unusual intersection)",
"Construction zone navigation",
"Emergency vehicle response",
],
},
"human_factors": {
"misuse": [
"Overreliance on automation (complacency)",
"Distracted driving during L2",
"Intentional abuse (hands-off driving)",
"Misunderstanding of ODD boundaries",
],
"takeover_failures": [
"Slow response after long automation use",
"Mode confusion (manual vs. automated)",
"Incorrect takeover action (wrong pedal)",
"Physical impairment (drowsy, intoxicated)",
],
},
"infrastructure": [
"Missing/contradictory road signs",
"Temporary construction zone",
"Road surface irregularities (potholes)",
"Non-standard intersection layout",
"Toll station / service area transitions",
],
}
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.
- 9d ago First seen · 361 lines · 27 tokens per session scan A e661180775f0
automotive-sotif-hazard-scenario is a skill published in the GitHub repository pangzhenying2025/hermes-automotive-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 2,871 once invoked, about $0.0001 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.
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…
requirements
Requirements-engineering expert that operates in three modes: (1) Elicitation — extract atomic, testable requirements from briefs, meeting notes, or system specs using EARS notation, with full attribute set (ID, type, priority, ASIL, verification method, source), flagging ambiguities as open questions; (2) Refinement…
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.