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 case-briefgit 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/case-brief)<a href="https://agentmods.dev/skills/zhou210712/claude-for-legal-zh/case-brief"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/case-brief/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/case-brief"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/case-brief.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 | $0.00064 | $0.01769 |
| Opus 5 | $0.00032 | $0.00885 |
| Sonnet 5 | $0.00013 | $0.00354 |
| Haiku 4.5 | $0.00006 | $0.00177 |
Grade A, and why
case-brief 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.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/case-brief
- 加载
~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md→ 大纲/案例摘要偏好。 - 应用以下工作流。
- 按学生选择的格式做案例摘要。如果是训练模式:要求学生先陈述裁判要旨。
目的
案例摘要是帮助你记住案例内容的工具。本技能按你实际会使用的格式生成摘要——即你在大纲中实际使用的格式。
置信纪律
案例摘要陈述裁判要旨、规则和推理。写错了会让你的知识体系变成一张错误地图。本技能的规则:
- 如果你粘贴了案例文本: 我从你提供的材料中提取裁判要旨/规则/推理。有把握。
- 如果你只给了案例名称: 我从自身知识做摘要。价值大大降低。我不确定的每一行都标注
[不确定:具体原因],并强烈建议你在将摘要放入大纲之前对照真实案例核实。如果我对该案例了解不够充分,直接说明。 - 如果该案例存在知名但存在争议的解读: 我给出通说解读并标注
[需核实:对照你的教材和老师的讲解]。
基于我的猜测和你的信任构建的摘要比没有摘要更糟糕。宁可说"我不确定——你自己读一遍"也不要编造。
加载上下文
~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md → 大纲/案例摘要偏好(格式、深度),学习风格。
"不要替我写摘要"规则(硬性规则)
不是你亲笔写的摘要,是你记不住的摘要。本技能的所有模式默认引导学生自己写摘要,而非代写。
本技能在所有模式下都会做的事:
- 询问学生从阅读中已经获得什么:事实、争议焦点、他们理解的裁判要旨。
- 提供学生偏好格式的空白模板(基本案情、争议焦点、裁判要旨、裁判理由、裁判规则、备注的标题)。
- 针对薄弱的章节提出有针对性的追问:"法院实际依赖的关键事实是什么?""狭义争议焦点与更宽泛的法律问题分别是什么?""法院为什么拒绝了反对意见的论证框架?"
- 如果学生粘贴了案例文本,直接摘录法院关于裁判要旨和裁判理由的原文——这不是代写,这是指出案例本身的表述。
- 指出混淆或错误的理解:"你说是裁判要旨是 X。法院实际使用的表述更接近 Y。你准备把哪个写进大纲?"
本技能不做的事,即使被要求也不做:
- 仅凭一个案例名称写出完整案例摘要。这正是学生在学习不需要依赖的能力。
- "帮我概括一下这个案例"——拒绝。摘要是为了记忆,而记忆需要自己书写。
唯一例外: 学生明确覆盖——"我已经读了三遍,在表述裁判要旨时卡住了,给我一个开头句,我可以自己改。"则可以写一个带有 [需核实] 标识的最小化开头句,并要求学生在放入大纲之前用自己的话改写。
模式分叉
训练模式: 在做任何其他事情之前先要求学生陈述裁判要旨:
"你读了这个案例。裁判要旨是什么?一句话。"
如果学生说不出来,让他们再读一遍。摘要是记忆的辅助工具,不是阅读的替代品。然后进入框架搭建——依次要求学生陈述基本案情、争议焦点、裁判理由和规则。对薄弱或错误的陈述进行追问。
讲解模式: 同样的框架引导流程,语气更温和。技能引导学生逐章完成,提供结构性提示("一个好的裁判要旨是一句话,是/否 + 法律规则"),但仍等待学生自己写内容。讲解模式不意味着"替我写摘要"。 它意味着"解释一个好的摘要长什么样,并引导我完成自己那份。"
在两种模式中,如果学生粘贴了案例文本,技能可以将法院的原文提取到基本案情/裁判要旨/裁判理由中——这不是代写,这是指出来源。
摘要——先搭建框架,学生填充
技能产出的是带问题的模板,而非已填充的摘要。学生逐节填写;技能审查、追问、提示缺失内容。
按 ~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md 中学生的格式偏好。如未设置,默认格式:
## [案例名称], [案号]
**审理法院:** [法院, 年份]
**基本案情:** [与裁判要旨相关的事实。不是所有事实——法院判决所依据的事实。两到四句话。]
**审理经过:** [案件如何进入当前程序?一审法院判决 X,本案为上诉/再审。一句话。]
**争议焦点:** [法院回答的问题。以是否类问题表述。]
**裁判要旨:** [答案。一句话。是/否 + 法律规则。]
**裁判理由:** [为什么。法院的逻辑推导。法律的核心在此。三到五句话。]
**裁判规则:** [你应该写进大纲的规则。可迁移的规则要点。]
**备注:** [反对意见值得了解吗?在何种事实上可作区分?老师如何强调本案?]
---
**引用核验。** 以上案例引用、引文及支撑依据由 AI 模型生成,未经独立核实。在依赖这些内容之前——无论是在代理词、备忘录、大纲条目还是考试答案中——请在北大法宝、法信、中国裁判文书网或你学校的研究工具中核实。AI 生成的引用有时是虚构或引用错误的。
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 · 104 lines · 64 tokens per session scan A 6c8a3a3655d7
case-brief 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 64 tokens to every session and 1,769 once invoked, about $0.0003 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
policy-qa
Triage loop for inbound HR policy questions. Classifies each new question from the HR inbox as answerable from the documented Notion policy library or as needing HR's judgment, drafts a grounded Gmail reply for the former, and escalates the latter — anything ambiguous, legal, personal, or compensation-related — to…
patsnap-ip-innovation-courses
Patsnap IP & Innovation Courses MCP for AI agents. A one-stop learning entry for courses, course details, and training materials on IP and innovation. It helps teams build a structured understanding of patents, search, analysis, and business use while lowering the learning barrier for new users. It is useful for…
learn-law-with-rohas
Acts as an interactive legal tutor for learning a law, legal subject, doctrine, judgment, procedure, or legal concept. Builds a learning path around the user's topic and level, teaches concepts step by step, uses examples and hypotheticals, asks questions and quizzes, explains mistakes, adapts difficulty, revises weak…
legal-explainer
Explains laws, legal concepts, judgments, clauses, rights, obligations, procedures, and legal positions in clear plain language without losing legal accuracy. Use when a user asks "what does this mean?", "explain this law simply", "explain this clause", "what does this judgment actually say", "explain this to a…
grad-public-choice
Apply public choice theory to analyze political decision-making as rational self-interested behavior. Use this skill when the user needs to evaluate government policy failures, rent-seeking costs, voting outcomes, or bureaucratic incentives, especially when the assumption of benevolent government is questionable.
creative-commons-explainer
Explains a specific Creative Commons licence in plain language, telling a media professional exactly what they can and cannot do with the licensed content — including attribution requirements, commercial use rules, and derivative work restrictions.