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-l3-fusa-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-l3-fusa-sotif)<a href="https://agentmods.dev/skills/pangzhenying2025/hermes-automotive-skills/china-l3-fusa-sotif"><img src="https://agentmods.dev/badge/skills/pangzhenying2025/hermes-automotive-skills/china-l3-fusa-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-l3-fusa-sotif"><img src="https://agentmods.dev/badge/skills/pangzhenying2025/hermes-automotive-skills/china-l3-fusa-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 | $0.00037 | $0.01898 |
| Opus 5.5 | $0.00015 | $0.00759 |
| Sonnet 5.5 | $0.00007 | $0.00380 |
| Haiku 4.5 | $0.00004 | $0.00190 |
Grade A, and why
china-l3-fusa-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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
L3 Fusa Sotif — China Standard
L3 有条件自动驾驶系统 功能安全和预期功能安全技术要求
标准信息
| 属性 | 值 |
|---|---|
| 标准编号 | 待定（GB/T） |
| 名称 | 智能网联汽车 有条件自动驾驶系统 功能安全和预期功能安全技术要求 |
| 状态 | 工作组草案（2025.01.18 正式版） |
| 推荐等级 | P2-推荐入选 |
| 特殊价值 | 中国独有标准，全球首个将FuSa+SOTIF联合要求系统化的标准 |
| 总页数 | 132页 |
标准定位
L3 FuSa+SOTIF联合标准的独特性
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
国际标准现状:
ISO 26262 (FuSa) ← 独立标准
ISO 21448 (SOTIF) ← 独立标准
→ 两者如何在L3系统中协同？缺少指导
中国创新:
本标准首次将FuSa+SOTIF联合要求系统化
├── 统一的安全目标体系
├── 联合的风险分析方法
├── 集成的V模型开发流程
└── 综合的安全论证框架
引用基础标准:
GB/T 34590-2022 (功能安全)
GB/T 43267-2023 (预期功能安全)
GB/T 40429-2021 (驾驶自动化分级)
GB/T 44721-2024 (自动驾驶系统通用技术要求)
ISO PAS 8800 (AI安全)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
标准结构（9章+6附录，132页）
标准目录结构
├── 第1章 范围
├── 第2章 规范性引用文件
├── 第3章 术语和定义
│ ├── 安全度量指标 (Safety Metric)
│ ├── SOFIL (Safety of Functionality Integrity Level)
│ ├── 主控权 (Override)
│ ├── 影子模式 (Shadow Mode)
│ └── 回退策略 (Regression Strategy)
├── 第4章 通用要求
│ ├── 4.1 概述
│ ├── 4.2 L3功能安全和SOTIF集成要求
│ ├── 4.3 分布式开发管理
│ └── V模型集成框架
├── 第5章 系统规范定义
│ ├── 5.1 功能规范
│ ├── 5.2 运行设计条件 (ODC)
│ ├── 5.3 系统架构
│ ├── 5.4 外部交互
│ └── 5.5 安全策略
├── 第6章 安全目标与接受准则
│ ├── 6.1 车辆级危害清单（11项，含ASIL等级）
│ ├── 6.2 残余风险接受准则
│ └── 6.3 SOFIL等级要求
├── 第7章 风险场景与安全要求
│ ├── 7.1 高速/快速路危险场景（10类）
│ ├── 7.2 城市道路危险场景（10类）
│ ├── 7.3 误用预防
│ ├── 7.4 驾驶员可控性
│ ├── 7.5 功能安全分析要求
│ └── 7.6 MRM安全要求
├── 第8章 测试验证要求
├── 第9章 运行与维护
└── 附录A-F
核心技术内容
车辆级危害清单与ASIL等级
Table 2: L3系统车辆级危害清单（摘要）
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
危害编号 描述 ASIL
H-01 非预期横向运动 ASIL D
H-02 丧失减速能力 ASIL D
H-03 非预期加速 ASIL D
H-04 非预期减速 ASIL C
H-05 非预期激活 ASIL B
H-06 丧失MRM能力 ASIL B
H-07 视野丧失 ASIL A
H-08 误报接管请求 ASIL A
H-09 驾驶员状态误判 ASIL B
H-10 通信安全失效 ASIL B
H-11 数据记录失效 ASIL A
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
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 · 189 lines · 37 tokens per session scan A a39ff3a7764b
china-l3-fusa-sotif is a skill published in the GitHub repository pangzhenying2025/hermes-automotive-skills (10 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 1,898 once invoked, about $0.0001 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…