Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ThomasMoreAI/legal-skills-opennpx agentmods add skills/thomasmoreai/legal-skills-open/contract-genWrote 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/thomasmoreai/legal-skills-open/contract-gen)<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/contract-gen"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/contract-gen/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/thomasmoreai/legal-skills-open/contract-gen"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/contract-gen.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 | $0.00135 | $0.02253 |
| Opus 5 | $0.00068 | $0.01126 |
| Sonnet 5 | $0.00027 | $0.00451 |
| Haiku 4.5 | $0.00014 | $0.00225 |
Grade A, and why
contract-gen 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- contract-gen — 88% identical, 11 lines differ
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
合同生成
以资深法律专家身份,根据用户提供的信息生成完整、严谨的合同。三阶段工作流:信息收集 → 合同生成 → 质量校验与输出。
工作流程
用户输入
│
▼
[阶段一] 信息收集与完整性检查
│ 检查 6 项输入 → 关键信息缺失则补全
│
▼
[阶段二] 合同生成
│ 加载框架 → 应用立场 → 类型适配 → 生成合同
│
▼
[阶段三] 质量校验与输出
│ 自检 → 输出 .md → 可选 .docx
阶段一:信息收集与完整性检查
收集以下 6 项输入信息:
| 序号 | 信息项 | 是否必填 | 说明 |
|---|---|---|---|
| 1 | 合同类型 | 必填 | 如:销售合同、服务合同、租赁合同、劳动合同、建设工程合同、合伙协议、借款合同、股权转让协议等 |
| 2 | 合同立场 | 必填 | 如:买受方/出卖方、甲方/乙方、出租方/承租方、用人单位/劳动者 |
| 3 | 合同背景 | 必填 | 合同签订的背景、目的、缘由 |
| 4 | 主体信息 | 必填 | 各方当事人的名称/姓名、证件号码、联系方式、地址等 |
| 5 | 业务模式 | 必填 | 核心业务条款:标的物/服务内容、价款、付款方式、交付方式、期限等 |
| 6 | 其他要求 | 选填 | 特殊条款要求、行业惯例、参考模板等 |
执行规则:
- 自适应模式:如用户已在初始消息中提供了全部关键信息,直接进入阶段二,不做多余确认
- 关键信息缺失时:直接向用户提问以补全缺失的关键信息。关键信息指法律上必需的要素(如主体身份、标的物、价款、履行方式等),而非表达是否专业
- 无单独优化步骤:不对用户输入做单独的优化确认。无论用户使用专业法律术语还是日常自然语言,只要关键内容表达清楚,在阶段二生成合同时自动融入专业化表述
- 信息推断:对于用户未明确但可合理推断的信息(如国内合同适用中国法律),可直接推断填入;对于无法推断的具体数据(如金额、日期),使用
[____]占位符
阶段二:合同生成
按以下步骤生成合同:
2.1 加载合同框架
读取 references/00-合同框架.md,获取合同框架(含 6 个结构元素 + 17 类实质条款)及起草要点。
2.2 应用立场策略
读取 references/01-立场策略.md,根据用户选择的立场,对价款、违约、风险转移、争议管辖等关键条款进行倾斜设计。
立场应用原则:
- 倾斜必须在法律允许范围内,不违反强制性规定
- 倾斜应当合理,过度倾斜可能导致条款被认定无效
- 对方利益也应有基本保障,避免显失公平
2.3 合同类型适配
读取 references/02-合同类型适配.md,根据合同类型:
- 增加该类型的必备条款
- 删除不适用的条款
- 应用该类型的特殊规则
回退策略: 如用户要求的合同类型未在适配规则中列出(如保密协议、特许经营合同、保险合同等),则仅使用通用合同框架,结合该类型的行业惯例和法律要求自行判断条款增删。
2.4 生成合同正文
以资深法律专家身份,综合以上信息生成完整的 Markdown 格式合同。
生成原则:
- 立场明确但合法:立场倾斜不得违反法律强制性规定
- 智能增删条款:根据合同类型和业务模式增删条款,不生成无关条款
- 术语准确:使用准确的法律术语,避免"合理时间""适当方式"等模糊表述
- 占位符规范:用户未提供的具体数字使用
[____]占位符 - 仅输出合同正文:不输出说明性前后缀、致谢、提示语
- 附免责声明:合同末尾附免责声明,与合同正文以分隔线隔开
Markdown 格式要求:
- 合同标题使用一级标题(
#) - 章节标题使用二级标题(
##) - 条款使用有序列表或层级编号
- 金额、日期等关键信息使用加粗
- 不使用代码块标记包裹合同正文
免责声明模板:
---
**免责声明:** 本合同由 AI 辅助生成,仅供参考,不构成正式法律意见。建议在签署前由专业律师审核。具体条款应根据实际情况和当地法律法规进行调整。
阶段三:质量校验与输出
3.1 质量自检
按 references/03-质量标准.md 对生成的合同进行自检,覆盖五个维度:
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 · 190 lines · 135 tokens per session scan A d9f173c7ec25
contract-gen is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (72 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 135 tokens to every session and 2,253 once invoked, about $0.0007 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
corporate-docs
La parte densa. Y la que más se arma mal, porque se mezclan tres cosas distintas.
doc-review
Casi ninguna empresa parte de cero. Parte de una plantilla que alguien copió y nadie volvió a mirar.
jahresbericht-1863-bgb
Jahresbericht des Betreuers an das Betreuungsgericht nach § 1863 BGB (Reform 2023). Pflichtinhalt: Bericht über persönliche Verhältnisse der betreuten Person, Vermögensentwicklung, geplante Maßnahmen. Pflichtbestandteile, Vorlagefrist, Abgrenzung zur Rechnungslegung § 1865 BGB. Use when ein beruflicher Betreuer den…
software-copyright
A workflow for preparing Chinese software-copyright registration materials from a real software project. It produces drafts and formal Word or text documents for the application.
pia-generator
Generate structured privacy impact assessments so Claude can organize project privacy risks, controls, and decision points into a review-ready report.
audit-scope-checklist
Generate a scoped IT audit program with controls mapped to roles and compliance frameworks. Use this skill for audit planning, control checklist generation, and auditprogram.json creation.