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 lawyerllsx-dotcom/Legal-Workflow-Chain --skill contract-guardiangit clone --depth 1 https://github.com/lawyerllsx-dotcom/Legal-Workflow-ChainWrote 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/lawyerllsx-dotcom/legal-workflow-chain/contract-guardian)<a href="https://agentmods.dev/skills/lawyerllsx-dotcom/legal-workflow-chain/contract-guardian"><img src="https://agentmods.dev/badge/skills/lawyerllsx-dotcom/legal-workflow-chain/contract-guardian/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/lawyerllsx-dotcom/legal-workflow-chain/contract-guardian"><img src="https://agentmods.dev/badge/skills/lawyerllsx-dotcom/legal-workflow-chain/contract-guardian.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 | $0.00245 | $0.07918 |
| Opus 5 | $0.00122 | $0.03959 |
| Sonnet 5 | $0.00049 | $0.01584 |
| Haiku 4.5 | $0.00024 | $0.00792 |
Grade A, and why
contract-guardian 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 yesterday.
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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
合同守护者(contract-guardian)
审得对,更要审得不怕担责。一个 skill,走完合同审查全流程。
这个 skill 是什么
一个自包含的合同审查工作流。装这一个 skill,就能完成从"定性"到"交付审查意见书"的完整流程,不需要安装其他配套。与普通"挑毛病"式审查的三个区别:
- 有法条依据——每条底线/重点意见都锚定到《民法典》等具体条文;
- 有防背锅三件套——意见书自带留痕声明、依据标注、免责边界;
- 有完整流程——示范文本对标、红线扫描、按类型专项审查、质量门禁自检,一个不少。
何时用
- 用户发来一份合同要求审查、看有没有坑;
- 用户是合同一方,想知道哪些条款对自己不利;
- 用户需要一份能拿给对方或上级的、有据可查的审查意见。
不适用:合同从零起草、涉外合同(适用外国法)、刑事/行政文书。
总流程(一张图)
「审这份合同」
→ 入口:定立场 + 定方法论(Step 0,含商业模式理解)
→ Step 1 定性:判断合同类型(三特征反推名为X实为Y)
→ Step 2 示范文本对标(有 GF/DB 示范文本则加载为基准)
→ Step 3 结构预检 + 全局红线扫描
→ Step 4 按类型专项审查(买卖/租赁/借款/服务/承揽/知产 → 查对应维度;无匹配 → 冷启动)
→ Step 5 法条锚定(每条底线/重点意见落到法条)
→ Step 6 多 Agent 对抗核验(spawn 独立 Verifier,12 项门禁,P0 必须清零)
→ Step 7 产出批注版意见 + 审查意见书(含防背锅三件套)
→ Step 8 迭代入库(可复用合同→标准模板库,发现的坑→条款坑库)
Step 0 · 启动前检查更新（必做）
每次启动本 Skill 前，先在 Skill 根目录检查 GitHub 上游是否有更新；有更新时先问用户是否要更新，用户确认后再执行更新，然后继续后续流程。
git -C "<SKILL_ROOT>" fetch --quiet
git -C "<SKILL_ROOT>" rev-list --count HEAD..@{u}
如果返回值大于 0，告诉用户检测到上游更新数量，询问是否先执行：
git -C "<SKILL_ROOT>" pull --ff-only
执行规则：
- 不要自动更新。用户拒绝时继续使用当前版本。
- 如果网络不可用、没有 upstream、不是 git 仓库、或 remote 被 404/删除，静默跳过本步，直接进 Step 1，不报错不打断。
- 当前状态：remote 已配置为 https://github.com/5tnb6xgsm5-ops/contract-guardian，Step 0 已生效。
核心原则（不可违反 — 读到第一个字就必须遵守）
| # | 原则 | 禁止行为 |
|---|---|---|
| 1 | 法条锚定：每条底线意见必须落到具体法条 | 不下法条依据就给底线结论 |
| 2 | 委托人权责：只提示法律风险，商业决策由委托人定 | 替委托人做商业判断（签不签、让不让步） |
| 3 | 诚实标注：不确定的内容标 [待核] |
假装确定（比标注不确定更不专业） |
| 4 | 立场先行：不确定立场前不做实质判断 | 假定立场直接审查 |
| 5 | 对抗核验强制：审查初稿必须经独立 Verifier 核验，P0 不清零不交付 | 以"合同简单""赶时间"为由跳过对抗核验 |
| 6 | 入库默认开启：每审一单默认轻量沉淀（坑记一条） | 跳过积累，从零开始重复踩坑 |
入口:审查前必问(Step 0)
收到合同后,先用一段话确认三件事(能从上下文推断的直接声明假设,不必都问):
- 立场:我方是甲方还是乙方?(如"我方是采购方/出租方")——同一条款,立场不同结论相反,不确定立场前不做实质判断;
- 合同类型:买卖/租赁/借款/服务/承揽/知产/其他?
- 底线:有没有绝不能接受的条件?(如"必须在我方所在地管辖")
0.0 能力盘点(首次使用时,可选增强端口)
首次使用时,主动做一次能力盘点——核心审查零依赖,但以下两个可选 MCP 能增强两个环节。用 references/integration.md 的引导话术询问/探测:
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/findings-测试合同-设备买卖.json 3.0 KB
- examples/findings-负向测试.json 3.4 KB
- examples/测试合同-设备买卖合同.md 1.1 KB
- examples/示例-Verifier核验报告.md 2.8 KB
- examples/示例输出-审查意见书.md 10 KB
- README.md 8.7 KB
- references/cold-start.md 3.1 KB
- references/integration.md 4.3 KB
- references/ip-clauses.md 1017 B
- references/legal-rules.md 5.6 KB
- references/pitfalls-library.md 6.8 KB
- references/quality-gate.md 5.3 KB
- references/red-lines.md 2.9 KB
- references/review-playbooks.md 5.7 KB
- scripts/verify_gate.py 15 KB runs code
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.
- yesterday First seen · 357 lines · 245 tokens per session scan A 58dde583dac4
contract-guardian is a skill published in the GitHub repository lawyerllsx-dotcom/Legal-Workflow-Chain (5 stars, last pushed 2d ago), licensed MIT. It adds 245 tokens to every session and 7,918 once invoked, about $0.0012 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 2026-09-11.
Other skills, from other repositories
tw-legal-rag
A tool for finding real Taiwan court judgments and legal interpretations with verifiable citations before answering questions about Taiwan law.
legal-research
A legal research skill for finding and analysing laws and court cases, including similar cases. It requires access to a reliable legal research database before producing a formal report.
document-fill
A document-filling assistant that uses a supplied template and case files to fill in forms, contracts, or legal documents. It also reports where each filled value came from and which details are missing.
contract-review
A contract-review workflow for agreements governed by Chinese law, United States law, or both. It examines clauses one by one and produces a list of legal-risk questions, with an optional marked-up Word document.
legal-kb-builder
A tool for turning legal documents and other source material into a searchable local knowledge base. It supports sources such as PDF, DOCX, images, Markdown, and question-and-answer sets.
kr-patent-consistency-check
A Korean patent-document checker for comparing a patent specification, drawings, and claims—the sections that describe an invention and define its legal protection.