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 vendor-ai-reviewgit 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/vendor-ai-review)<a href="https://agentmods.dev/skills/zhou210712/claude-for-legal-zh/vendor-ai-review"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/vendor-ai-review/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/vendor-ai-review"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/vendor-ai-review.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 | $0.00078 | $0.02835 |
| Opus 5 | $0.00039 | $0.01418 |
| Sonnet 5 | $0.00016 | $0.00567 |
| Haiku 4.5 | $0.00008 | $0.00283 |
Grade A, and why
vendor-ai-review 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.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/vendor-ai-review
- 读取
~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md→ 合同审查立场、可接受风险阈值、红线条款。 - 运行以下工作流。
- 逐项核查AI特定风险——训练数据→责任→模型变更→合规传导。
- 输出：风险总结 + 红线标记 + 谈判立场（经核准/附条件/阻止）。
/ai-governance-legal:vendor-ai-review
[paste the vendor AI terms]
AI供应商合同审查
事务上下文
事务上下文。 检查实践级 CLAUDE.md 中的 ## 事务工作区。如果 已启用 为 ✗，跳过本段其余部分。如果已启用且无活跃事务，询问事务归属。加载活跃事务的 matter.md。除非 跨事务上下文 为 开，否则绝不读取其他事务的文件。
目的
AI供应商合同引入了传统技术合同没有的风险维度——供应商是否使用你的数据训练模型、模型变更时你会不会得到通知、如果AI产生了侵权内容谁承担风险、供应商是否完成了法定的算法备案和安全评估（《生成式人工智能服务管理办法》第17条 [法条原文]）。此技能系统性地审查这些风险。
加载当前状态
读取 ~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md：
## 合同审查配置— 公司立场、风险偏好、红线## 监管注册表— 适用的法规框架## 已批准的供应商— 既有关系和已通过审查的条款
审查框架
第1步：服务定性
首先明确供应商提供的是什么：
| 模型提供方式 | 说明 | 关键风险 |
|---|---|---|
| API接口 | 通过云端API调用模型 | 数据传输安全、数据是否被记录用于训练 |
| 本地部署 | 模型部署在自有服务器 | 安全可控性高，但更新和升级依赖供应商 |
| SaaS产品 | 使用供应商的AI功能产品 | 使用条款可能不清晰，数据用途条款需特别关注 |
| 模型授权/定制 | 授权基础模型进行微调 | 知识产权归属、模型更新的兼容性 |
第2步：训练数据检查
这是AI合同审查中最重要的部分。
核心问题链
- 供应商是否使用客户数据训练模型？
- 如果是，客户是否知情并同意？
- 训练数据中是否包含个人信息或敏感个人信息？
- 客户数据流出后是否可以追回（"遗忘权"的实操可行性）？
审查清单
| 检查项 | 理想状态 | 风险标记 |
|---|---|---|
| 训练数据条款 | 明确约定不将客户数据用于模型训练，或经客户明确书面同意 | 🔴 合同沉默、或条款笼统声称供应商可"使用数据进行服务改进" |
| 个人信息训练 | 不将包含个人信息的数据用于训练，或已取得个人单独同意（《个人信息保护法》第23条 [法条原文]） |
🔴 未区分数据类型，一刀切授权 |
| 训练数据合法性保证 | 供应商保证其训练数据来源合法，不侵犯第三方知识产权（《生成式人工智能服务管理办法》第7条 [法条原文]） |
🟠 供应商仅提供"尽力"保证或不提供保证 |
| 数据删除 | 合同终止后供应商删除客户数据并销毁包含客户数据的模型副本 | 🟠 仅承诺"停止使用"而不承诺删除 |
| 知识产权归属 | 明确约定微调模型的权属（客户拥有/供应商拥有/共享） | 🟠 合同沉默 |
训练数据条款的红线
- 供应商单方面保留"为改进服务目的"使用客户全部数据的权利，且不可协商
- 供应商拒绝就训练数据的合法来源提供任何保证
- 涉及个人信息且供应商拒绝签署数据处理协议（参照《个人信息保护法》第21条
[法条原文]）
第3步：责任分配
AI产出的特殊性使得传统的责任条款可能无法直接适用。需要特别关注：
| 责任场景 | 供应商理想立场 | 风险 |
|---|---|---|
| AI产出侵权（知识产权） | 供应商承担因其训练数据或模型本身导致的侵权责任 | 🔴 供应商将全部侵权风险转嫁客户 |
| AI产出违法/不良内容 | 供应商基于《生成式人工智能服务管理办法》承担内容安全责任 | 🔴 供应商声称仅为"技术中立工具" |
| AI产出错误导致商业损失 | 责任分配合理，特殊或间接损失合理排除 | 🟠 供应商完全免责且客户承担全部损失 |
| 模型停机/服务中断 | SLA明确，有可用性承诺和服务积分/赔偿机制 | 🟡 SLA模糊或缺失 |
| 模型性能退化 | 供应商保证模型输出质量不实质性下降 | 🟠 供应商保留单方修改模型的权利且无通知义务 |
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 · 209 lines · 78 tokens per session scan A 6ff4bc77202b
vendor-ai-review 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 78 tokens to every session and 2,835 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…