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 semester-handoffgit 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/semester-handoff)<a href="https://agentmods.dev/skills/zhou210712/claude-for-legal-zh/semester-handoff"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/semester-handoff/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/semester-handoff"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/semester-handoff.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 | $0.00097 | $0.02741 |
| Opus 5 | $0.00048 | $0.01371 |
| Sonnet 5 | $0.00019 | $0.00548 |
| Haiku 4.5 | $0.00010 | $0.00274 |
Grade A, and why
semester-handoff 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.
This is a copy
92% identical to client-intake — 265 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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.
/semester-handoff
- 加载
~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md→ 诊所画像、学期日期、指导风格。 - 加载
~/.claude/plugins/config/claude-for-legal/legal-clinic/deadlines.yaml和按案件的~/.claude/plugins/config/claude-for-legal/legal-clinic/client-comms/[案件编号]/log.md。 - 使用以下工作流。
- 将活跃案件列表作为输入（如诊所无中心列表则询问）。映射离届 → 新接手人。
- 生成按案件交接备忘录 →
~/.claude/plugins/config/claude-for-legal/legal-clinic/handoffs/[学期]/[案件编号].md。 - 生成群体摘要 →
~/.claude/plugins/config/claude-for-legal/legal-clinic/handoffs/[学期]/_summary.md。 - 按指导模式路由——正式队列 / 可配置标记 / 较轻触。
学期交接
目的
每学期诊所失去其全部劳动力并重建。/ramp 解决了一半问题——它导入新群体。本技能解决另一半：它通过生成交接备忘录协助离届群体，记录新学生需要了解的每个活跃案件的信息。
没有这个，案件知识随学生离开而流失。新学生从案件文件和接待摘要开始，这永远不够。两周被浪费在重新学习案件上，新学生才能做有用的事。当事人将重新学习体验为退步——在新学生追赶上之前电话无人应答，已回答的问题被重新问。
受众
指导老师或离届学生。指导老师运行它来协调整群体协助；单个学生可在其学期中转出（毕业、退出）时针对自己的案件运行。
加载上下文
~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md→ 诊所画像、学期、实践领域、指导风格~/.claude/plugins/config/claude-for-legal/legal-clinic/deadlines.yaml→ 所有活跃截止日期，按案件分组~/.claude/plugins/config/claude-for-legal/legal-clinic/client-comms/[案件编号]/log.md（按案件） → 沟通历史- 诊所维护的案件文件 / 接待摘要
- 学生名册——谁在交接中负责什么
工作流
第1步：识别案件和负责人
- 拉取所有活跃案件（来自接待记录 +
~/.claude/plugins/config/claude-for-legal/legal-clinic/deadlines.yaml案件编号 + client-comms 文件夹） - 每个案件：当前负责学生是谁？他们是留任还是离开？
- 映射：离届负责人 → 新接手人（如已知；否则标记"待定——指导老师分配"）
如果诊所不维护中央活跃案件列表，技能需要一个输入：活跃案件列表。询问。不要猜测。
第2步：按案件交接备忘录
每个案件：
# 案件交接 — [案件名称] — [结束学期]
**案件编号：** [案件编号]
**实践领域：** [领域]
**离届学生：** [姓名]
**新接手学生：** [姓名或"待定"]
**指导律师：** [指导老师]
**当事人：** [姓名或当事人编号]
---
## 当前状态
[一段话：当前态势。已完成什么、待处理什么、案件走向。如案件处于自然暂停点或提交之间，说明。]
## 待处理截止日期
*从 `~/.claude/plugins/config/claude-for-legal/legal-clinic/deadlines.yaml` 拉取。新接手学生的第一项工作是确认这些准确并已认领。*
| 截止日 | 类型 | 说明 | 备注 |
|---|---|---|---|
| [日期] | [类型] | [一行] | [如紧迫："紧急——学期开始[N]天内到期"] |
## 已完成事项
- [本学期关键行动：接待、提交、庭审、主要信函]
- [已产出的文件——附存放位置指引]
## 待处理事项
- [待决策事项：如"当事人尚未决定是否接受和解方案"]
- [检索缺口：如"需要确认[省份]是否允许[救济措施]"]
- [待回复沟通：如"等待对立方律师办公室回复"]
## 当事人关系
- [学生与当事人联系的频率？电话、邮件、面谈？]
- [下一位学生应了解的任何关系背景：语言偏好、信任建立说明、影响时间安排的情况]
- [即将到来的计划联系或预约]
## 已起草/已提交文件
*指引，非内容。*
- [日期] [文件类型] — [路径或文件引用] — [状态：已提交 / 已起草 / 在审查队列中]
## 沟通历史摘要
*来自 `~/.claude/plugins/config/claude-for-legal/legal-clinic/client-comms/[案件编号]/log.md`。此处三段式摘要；新接手学生阅读完整日志。*
[近期联系模式的简要摘要——如"自接待以来3次通话，当事人偏好晚上联系。最后联系：2026-04-15，确认了庭审通知地址。"]
## 指导老师给新接手学生的标记
*由指导老师在交接备忘录发给新接手学生前审查时添加。可包括："本案涉及敏感家庭动态——联系当事人前仔细阅读接待记录"；"当事人要求所有邮件发至邮政信箱而非家庭住址"；"我们尚未解决本案的范围问题——在第一周与我确认。"*
[标记，或"无"]
## 新接手学生第一周优先事项
1. [具体——如"接手案件后48小时内致电[当事人]。自我介绍。确认你已收到案件文件。"]
2. [截止日期驱动——如"驱逐答辩状截止于[日期]。审查离届学生的草稿，修改，提交。"]
3. [知识缺口——如"在4/28状态会议前阅读离届学生关于可居住性抗辩的备忘录。"]
---
**交接由：** [离届学生] 准备
**日期：** [YYYY-MM-DD]
**审查人：** [指导律师，如按指导模式适用]
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 · 97 tokens per session scan A 5c6f45ca421c
semester-handoff 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 97 tokens to every session and 2,741 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to client-intake, differing in 265 lines, and is treated as a copy.
Other skills, from other repositories
vendor-review
Evaluate a vendor — cost analysis, risk assessment, and recommendation. Use when reviewing a new vendor proposal, deciding whether to renew or replace a contract, comparing two vendors side-by-side, or building a TCO breakdown and negotiation points before procurement sign-off.
entity-compliance
Entity compliance tracker — initialize, report upcoming deadlines, update status, run health audit, export to CSV. Maintains a compliance-tracker.yaml built from the entity table, calculates filing deadlines by entity and jurisdiction, and surfaces what's due in the next 30/60/90 days. Use when user says "entity…
integration-management
Post-closing M&A integration tracker — phased workplan, consent tracking, contract assignment at scale, weekly status reports. Initializes from whatever deal artifacts are available (purchase agreement, deal summary, closing checklist) and connects to deal-context.md and closing-checklist.yaml from the M&A cold-start.…
matter-workspace
Manage matter workspaces — new, list, switch, close, or detach (practice-level). File-management logic for keeping one client or engagement's context separate from every other. Use when working across multiple clients or matters, when the user says "new matter", "switch matter", "list matters", "close matter", or when…
patent-docket
A workflow coordinator for patent case files, from an inventor's technical disclosure to patent application documents. A patent docket is the tracked record of a patent matter, including its stage, questions, drafts, and handoffs.
performance-management
Runs performance systems that change behavior — expectations, feedback, review cycles, calibration, and handling underperformance. Use this to design or fix a review process, run calibration, write or coach on feedback, address sustained underperformance, or work out why reviews consume weeks and change nothing.