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 zhou210712/claude-for-legal-ZH --skill ai-inventorygit clone --depth 1 https://github.com/zhou210712/claude-for-legal-ZHWrote 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/zhou210712/claude-for-legal-zh/ai-inventory)<a href="https://agentmods.dev/skills/zhou210712/claude-for-legal-zh/ai-inventory"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/ai-inventory/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/zhou210712/claude-for-legal-zh/ai-inventory"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/ai-inventory.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 | $0.00074 | $0.02387 |
| Opus 5 | $0.00037 | $0.01193 |
| Sonnet 5 | $0.00015 | $0.00477 |
| Haiku 4.5 | $0.00007 | $0.00239 |
Grade A, and why
ai-inventory 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 13d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ai-inventory
- 读取
~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md→ 既有AI系统清单(如有)、监管注册表。 - 运行以下工作流。
- 对每个系统:描述功能 → 判定提供者/使用者角色 → 分配风险等级 → 映射监管义务。
- 输出系统级条目 + 汇总表。
/ai-governance-legal:ai-inventory "智能客服系统 v3"
/ai-governance-legal:ai-inventory --full
AI系统清单编制
目的
盘点你正在使用的每一件AI——作为提供者还是使用者,风险层级如何,受哪些法规约束。这是 use-case-triage(评估新事物)和 aia-generation(深度评估单个系统)的基础层。
加载当前状态
读取 ~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md:
## AI系统清单— 既有清单(如有)## 监管注册表— 适用法规及义务## 红线— 禁止的用例类别
单系统录入
当提供系统名称或描述时,运行单系统录入。
工作流
第1步:收集基本信息
如果用户提供的信息不足以填充以下字段,逐项询问:
| 字段 | 说明 |
|---|---|
| 系统名称 | 唯一标识符 |
| 功能描述 | 一段话——系统做什么 |
| AI技术类型 | 机器学习/深度学习/规则系统/大语言模型/计算机视觉/其他 |
| 模型来源 | 自主研发/基于开源模型微调/第三方API/采购的商业产品 |
| 部署方式 | 本地部署/私有云/公有云API/SaaS |
| 数据处理 | 涉及的数据类别——是否包含个人信息、敏感个人信息、商业数据、公开数据 |
| 受影响人群 | 内部员工/商业客户/公众用户/未成年人 |
| 使用场景 | 内部辅助工具/面向客户的功能/面向公众的服务 |
| 决策类型 | 非实质性(推荐、排序)/实质性(影响权利义务)/安全关键 |
第2步:判定角色
| 角色 | 判定标准 |
|---|---|
| 提供者 | 自主研发并向他人(包括公司内部其他部门)提供AI服务 |
| 使用者 | 使用第三方AI服务,不对外提供AI服务本身 |
| 双重 | 基于第三方模型训练/微调后向外部提供服务 |
如果系统仅在公司内部使用且不向外部提供,则通常归为使用者(即使使用了内部数据)。但如果公司开发自己的模型/系统并向外部客户提供该系统的访问权限,则归为提供者。
灰色地带:使用LLM API构建的面向用户的功能——技术上使用了第三方模型,但你构建了应用层并向用户提供服务。此类情况通常归为"双重"角色:对用户来说你是提供者,同时你是底层模型的使用者。
第3步:分配风险等级
| 等级 | 定义 | 触发特征 |
|---|---|---|
| 高风险 | 对权利和利益有实质性影响,或面向弱势群体,或安全关键 | 自动化决策影响信贷/就业/教育/保险;涉及敏感个人信息;面向未成年人;医疗/交通/基础设施安全场景 |
| 中风险 | 面向公众但对权利无实质性影响 | 内容推荐/个性化;使用个人信息但非敏感;生成合成内容 |
| 低风险 | 内部使用,不涉及个人信息,无外部影响 | 内部数据分析;非个人信息处理;生产力和效率工具 |
| 不适用 | 系统中没有AI组件 | 纯确定性的自动化、传统软件 |
第4步:映射监管义务
基于角色和风险等级,确定义务:
| 法规 | 高风险 + 提供者 | 中风险 + 提供者 | 高风险 + 使用者 | 中/低风险 + 使用者 |
|---|---|---|---|---|
生成式AI安全评估(《管理办法》第17条 [法条原文]) |
✅ 必须 | ✅ 必须 | ❌ 不直接 | ❌ 不直接 |
算法备案(《算法推荐管理规定》第24条 [法条原文]) |
✅ 必须(如适用) | ✅ 必须(如适用) | ❌ | ❌ |
科技伦理审查(《伦理审查办法》[法条原文]) |
✅ 必须 | ⚠️ 视具体场景 | ⚠️ 视具体场景 | ❌ |
个人信息保护影响评估(《个保法》第55条 [法条原文]) |
✅ 必须 | ✅ 必须 | ✅ 必须 | ⚠️ 视数据 |
算法推荐透明度(《算法推荐管理规定》第16条 [法条原文]) |
✅ 必须 | ✅ 必须 | ❌ | ❌ |
深度合成标识(《深度合成管理规定》第16条 [法条原文]) |
✅ 必须(如适用) | ✅ 必须(如适用) | ❌ | ❌ |
投诉举报机制(《管理办法》第15条 [法条原文]) |
✅ 必须 | ✅ 必须 | ❌ | ❌ |
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.
- 13d ago First seen · 177 lines · 74 tokens per session scan A 404b16081107
ai-inventory is a skill published in the GitHub repository zhou210712/claude-for-legal-ZH (212 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 74 tokens to every session and 2,387 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
nda-review
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…