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 code-lawyer/Legal-Agent-Skills --skill contract-reviewgit clone --depth 1 https://github.com/code-lawyer/Legal-Agent-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/code-lawyer/legal-agent-skills/contract-review)<a href="https://agentmods.dev/skills/code-lawyer/legal-agent-skills/contract-review"><img src="https://agentmods.dev/badge/skills/code-lawyer/legal-agent-skills/contract-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/code-lawyer/legal-agent-skills/contract-review"><img src="https://agentmods.dev/badge/skills/code-lawyer/legal-agent-skills/contract-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 | $0.00086 | $0.00836 |
| Opus 5 | $0.00043 | $0.00418 |
| Sonnet 5 | $0.00017 | $0.00167 |
| Haiku 4.5 | $0.00009 | $0.00084 |
Grade A, and why
contract-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 11d 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.
What it actually says
合同审查（中美双法域）
文件定位（先读）
本 skill 由多个文件组成。下文所有 references/…、rules/… 路径均相对于本 SKILL.md 所在目录。开始前先确定该目录（你被指向或读取本文件时所在的位置），之后所有读取都基于它解析，不要用当前工作目录去找。
何时使用
- 用户要求审查、审阅、markup、检查一份合同或其中条款。
- 用户问某条款在中国法或美国法下是否有效/有风险/如何修改。
- 上游技能路由到合同审查。
- 或当被明确要求用本 skill 审查合同、或被指向本
SKILL.md时。
任务边界
本技能只做合同审查 + 可选 Word 红线稿。不做合同起草、企业核验、续约提醒、版本对比、流程图、实务画像。
需要按案卷/知识库填充一份模板/文书 → 使用 document-fill。
执行顺序（按阶段按需读取，不要一次读全）
- 读
references/00-workflow.md，按四阶段推进。 - 阶段2 判定法域时，列出
references/rules/下每个子目录、各读其中的_pack.md清单（极小），不读规则正文。 - 阶段3 深审时，读
references/02-methodology.md+ 判定法域包的_general.md+ 命中业务领域那一个卡；跨境才读第二法域包。 - 出问题清单读
references/06-output-and-severity.md；涉精确法条调references/07-verification.md；要红线稿才读references/08-redline.md。
按需读取索引
references/00-workflow.md— 四阶段主流程references/01-jurisdiction-routing.md— 法域判定与跨境references/02-methodology.md— 法域中立审查骨架 + 失败模式 + 大输入纪律references/rules/<法域>/— 可插拔规则包（_pack.md 清单 / _general.md 通用 / 领域卡）references/06-output-and-severity.md— 双轴评级 + 问题卡 + 来源标签 + 备忘录references/07-verification.md— MCP 验证接口 + 三轮检索 + 注入防御references/08-redline.md— Word 红线七步 QA
输出底线
- 不跳过用户材料；读取失败必须说明。
- 不用模型记忆替代法律核验；引用法规/案例必须带来源标签之一（见 06）并注明核验状态。
- 材料不足提示缺口，不静默脑补。
- 检查表是底线不是上限：超出审查卡的法律问题照常作答并说明；学理问题直接答，不硬塞进文件审查流程。
- 正式审查交付附免责声明（不构成最终法律意见、需主办律师复核）；格式见
references/06-output-and-severity.md。
What ships with it
38 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.
- .gitignore 19 B
- README.md 3.9 KB
- references/_templates/domain-card-template.md 949 B
- references/_templates/pack-template.md 927 B
- references/00-workflow.md 2.3 KB
- references/01-jurisdiction-routing.md 2.5 KB
- references/02-methodology.md 2.8 KB
- references/06-output-and-severity.md 4.6 KB
- references/07-verification.md 1.8 KB
- references/08-redline.md 3.1 KB
- references/clause-library/_index.md 6.2 KB
- references/clause-library/confidentiality.md 8.3 KB
- references/clause-library/dispute-resolution.md 4.9 KB
- references/clause-library/ip.md 7.0 KB
- references/clause-library/liability.md 7.3 KB
- references/clause-library/notice.md 5.1 KB
- references/clause-library/payment.md 7.6 KB
- references/clause-library/quality.md 8.4 KB
- references/clause-library/subject.md 4.8 KB
- references/clause-library/term.md 5.0 KB
- references/clause-library/termination.md 8.6 KB
- references/rules/cn/_general.md 2.0 KB
- references/rules/cn/_pack.md 1.3 KB
- references/rules/cn/labor.md 3.9 KB
- references/rules/cn/loan-financing.md 3.2 KB
- references/rules/cn/nda.md 1.7 KB
- references/rules/cn/sale-of-goods.md 2.1 KB
- references/rules/cn/services-saas.md 2.1 KB
- references/rules/us/_general.md 1.9 KB
- references/rules/us/_pack.md 1.3 KB
- references/rules/us/nda.md 1.7 KB
- references/rules/us/sale-of-goods.md 2.0 KB
- references/rules/us/services-saas.md 1.8 KB
- scripts/redline_docx.py 23 KB runs code
- scripts/requirements.txt 19 B
- scripts/sample_redline_plan.json 1.5 KB
- scripts/test_redline_docx.py 10 KB runs code
- validate.py 5.5 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.
- 11d ago First seen · 42 lines · 86 tokens per session scan A e4315b7907c7
contract-review is a skill published in the GitHub repository code-lawyer/Legal-Agent-Skills (2 stars, last pushed 19d ago), licensed MIT. It adds 86 tokens to every session and 836 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 2026-08-31.
Other skills, from other repositories
contract-guardian
A contract-review workflow that checks agreements for risks, links important findings to relevant laws, and produces a written review. It covers common agreements such as sales, leases, loans, services, contracting, and intellectual property.
法律周报
A legal-news briefing workflow that finds recent court and legal-practice articles, scores them against selected criteria, and archives chosen items in a local Obsidian notes folder. Obsidian is a local note-taking application.
legal-research
A Chinese-language legal research workflow for finding laws, regulations, court cases, compensation standards, and legal grounds.
legal-citation-comprehensive
A Chinese and foreign legal-citation tool for checking, completing, explaining, and formatting footnotes under the second edition of a legal citation manual. It handles laws, cases, legal documents, and academic sources when the relevant source material is provided.
legal-fact-checker
A Chinese-language fact-checking guide for legal documents such as contracts, case analyses, legal opinions, and legal assignments. It checks provided drafts against factual and legal support without inventing laws, cases, or facts.
workflow-overview
A workflow guide for handling complex legal matters through assessment, issue identification, source research, reasoning, fact checking, and document output.