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 china-sotifgit 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/china-sotif)<a href="https://agentmods.dev/skills/pangzhenying2025/hermes-automotive-skills/china-sotif"><img src="https://agentmods.dev/badge/skills/pangzhenying2025/hermes-automotive-skills/china-sotif/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/china-sotif"><img src="https://agentmods.dev/badge/skills/pangzhenying2025/hermes-automotive-skills/china-sotif.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 | $0.03509 |
| Opus 5.5 | $0.00016 | $0.01404 |
| Sonnet 5.5 | $0.00008 | $0.00702 |
| Haiku 4.5 | $0.00004 | $0.00351 |
Grade A, and why
china-sotif 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 1mo 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 — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sotif — China Standard
中国 SOTIF 标准集 — GB/T 43267 + CSAE 316.1/316.2 + CSAE 336
概述
中国 SOTIF(预期功能安全)标准体系,包含一项国标和三项团标,形成从方法论到落地实践的完整框架。
标准集一览
| 标准编号 | 名称 | 状态 | 推荐等级 |
|---|---|---|---|
| GB/T 43267-2023 | 道路车辆 预期功能安全 | 已发布 | P1 |
| T/CSAE 316.1-2023 | 环境感知系统SOTIF 第1部分:触发条件分析与描述方法 | 已发布 | P1 |
| T/CSAE 316.2-2023 | 环境感知系统SOTIF 第2部分:乘用车测试与评价方法 | 已发布 | P1 |
| T/CSAE 336-2023 | 预期功能安全场景要素及管理要求 | 已发布 | P1 |
1. GB/T 43267-2023 道路车辆 预期功能安全
等同采用 ISO 21448:2022,是中国 SOTIF 的纲领性标准。
核心框架
ISO 21448 / GB/T 43267 SOTIF流程
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Clause 5-6: 功能和系统规范 → 功能不足识别
Clause 7: 触发条件识别 → 危害行为分析
Clause 8: 已知危害场景评估 → 风险评价
Clause 9: 功能改进 → 风险降低措施
Clause 10: 已知场景验证(仿真+场地+道路)
Clause 11: 未知场景确认(探索性测试+统计论证)
Clause 12: 运行阶段 → 现场监控+持续改进
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
2. T/CSAE 316.1-2023 触发条件分析与描述方法
标准范围
适用于智能网联汽车环境感知系统(摄像头、毫米波雷达、激光雷达、超声波等)的 SOTIF 触发条件系统化分析。
触发条件分析框架
触发条件分析流程 (CSAE 316.1 Figure 1)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
感知系统定义 → ODD定义
↓
触发源收集 → 触发源属性分析
↓
触发机制识别
↓
触发因素确定
↓
触发后果分析
↓
潜在触发条件 → 危害事件关联
↓
触发条件描述(语义/逻辑/具体)
↓
触发条件评价(发生率O × 敏感度P)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
感知要素五层架构
预期感知要素分层 (CSAE 316.1 Section 5)
├── Layer 1: 道路结构 (Road Structure)
│ ├── 车道信息(标线类型、颜色、位置)
│ ├── 道路边界
│ └── 路面状态
├── Layer 2: 交通设施 (Traffic Infrastructure)
│ ├── 交通信号灯
│ ├── 交通标志
│ └── 护栏/隔离带
├── Layer 3: 临时变更 (Temporary Changes)
│ ├── 施工区域
│ ├── 临时标线
│ └── 交通管制
├── Layer 4: 交通参与者 (Traffic Participants)
│ ├── 机动车(小汽车/卡车/摩托车)
│ ├── 非机动车(自行车/电动自行车)
│ ├── 行人
│ └── 动物
└── Layer 5: 自然环境 (Natural Environment)
├── 降水(雨/雪/冰雹)
├── 空气悬浮物(雾/霾/沙尘)
├── 光照(强光/逆光/暗光/频闪)
└── 其他(温度/电磁干扰)
触发源分类体系
触发源分类 (CSAE 316.1 Table A.1)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
A. 实体要素类触发源
├── 道路结构要素(弯道、坡道、隧道、匝道)
├── 交通设施要素(标志、信号灯、护栏)
├── 临时变更要素(施工区、事故现场)
└── 交通参与者要素(各类车辆、行人)
B. 干扰要素类触发源
├── 自车干扰(振动、发热、电磁)
├── 传感器表面干扰(污损、水滴、冰霜)
├── 悬浮物干扰(昆虫、灰尘、树叶)
├── 遮挡物干扰(前车、建筑物、隧道壁)
└── 高反射微粒干扰(雨滴反光、路面积水)
C. 环境条件类触发源
├── 降水条件(雨/雪/冰雹的强度等级)
├── 空气悬浮物(雾/霾/沙尘的浓度等级)
├── 光照条件(照度、角度、变化率)
└── 其他条件(温度、湿度、电磁场)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
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.
- 1mo ago First seen · 345 lines · 41 tokens per session scan A f6c91cec0bd2
china-sotif is a skill published in the GitHub repository pangzhenying2025/hermes-automotive-skills (10 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 3,509 once invoked, about $0.0002 per session on Opus 5.5. 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'…
policy-creation
Guide for adding new enterprise policies to Chromium. Complete guide for policy definitions, pref mapping, and writing tests.
accessibility-testing
Test for WCAG 2.2 AA compliance with axe-core + Playwright, keyboard navigation audits, screen reader testing, ARIA pattern validation, and legal compliance mapping (ADA, EAA, Section 508). Automated tools catch 30-40% of issues — this skill covers automated and manual testing together. Use when: "accessibility,"…
compliance-testing
Test for regulatory compliance: GDPR/CMP consent verification, Google Consent Mode v2, Global Privacy Control (GPC), CCPA/US state opt-out, EU AI Act Article 50 transparency, Better Ads Standards, and cookie-inventory auditing. Covers automated consent-flow testing, policy-based script blocking before consent, and…
ring:adding-multi-tenancy
Adding database-per-tenant isolation into a Go service end-to-end via an 11-gate cycle: detects the stack, audits compliance, then dispatches backend agents to implement tenantId-from-JWT routing through the lib-commons v5 dispatch layer (config, middleware, repositories, metrics, tests) and runs reviewers. Use when…