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 client-comms-loggit 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/client-comms-log)<a href="https://agentmods.dev/skills/zhou210712/claude-for-legal-zh/client-comms-log"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/client-comms-log/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/client-comms-log"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/client-comms-log.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 | $0.01679 |
| Opus 5 | $0.00048 | $0.00839 |
| Sonnet 5 | $0.00019 | $0.00336 |
| Haiku 4.5 | $0.00010 | $0.00168 |
Grade A, and why
client-comms-log 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/client-comms-log
- 使用以下工作流。
- 要求案件编号(未提供则提示)。
- 按标志路由:
--add(默认):记录方向、媒介、学生、摘要、行动事项、后续截止日期。与用户确认。追加(最新在最前)到~/.claude/plugins/config/claude-for-legal/legal-clinic/client-comms/[案件编号]/log.md。--read:显示最近 N 条记录。--summary:一段话简要阅读。--patterns:扫描未回复的沟通、遗漏的后续跟进、语言缺口、语气变化、联系缺口。面向指导的。
- 联动:如果记录创建了截止日期,提议
/legal-clinic:deadlines --add;通过--summary路由到/legal-clinic:semester-handoff。
当事人沟通日志
目的
保留此日志的四个理由:
- 执业风险防范。 如果当事人声称"从没有人告诉过我[X]",一条显示相反的日期记录就是回答。诊所指导老师对学生的执业工作承担执业责任;同期记录保护他们。
- 交接连续性。 下学期的学生接手案件并读取日志;他们不会重新向当事人问已被回答过的问题。
- 指导可见性。 六周内五通未回复的语音留言是一种模式。日志让模式可见,单个学生可能不会自行标记。
- 卷宗保留。 法学院诊所有义务维护完整的当事人档案。沟通历史是其中的一部分。
轻量。仅追加。学生的工作是每次联系后写两句摘要;技能格式化并追加。
加载上下文
~/.claude/plugins/config/claude-for-legal/legal-clinic/client-comms/[案件编号]/log.md(如存在)——追加目标~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md→ 不重度读取;本技能是案件范围的
模式
标志:--add | --read | --summary | --patterns(默认:add)
--add(默认)——记录新条目
输入:
- 案件编号(必需——哪个案件)
- 日期 + 时间(默认:现在)
- 方向:
in(当事人 → 诊所)|out(诊所 → 当事人) - 媒介:
电话 | 邮件 | 短信 | 信函 | 面谈 | 视频 | 留言-已留 | 留言-已收 - 谁(学生):姓名
- 谁(当事人方):当事人姓名,或"第三方:[说明]"如果来自对立方律师、家属等
- 时长/长度(如"10分钟通话""3段邮件""45分钟面谈")
- 摘要:2-4 句话。发生了什么,实质性内容是什么。
- 行动事项:
- 学生欠当事人的(附截止日期)
- 当事人欠学生的(附属预期时间)
- 后续截止日期:如适用
- 备注:任何重要但不属于上述分类的内容——使用的语言、情绪语调、观察到的家庭动态
写入前: 向用户展示格式化的条目并征求确认。诊所记录应在写入前审查,而非写入后。
追加到 ~/.claude/plugins/config/claude-for-legal/legal-clinic/client-comms/[案件编号]/log.md。如果日志不存在,创建它并附页眉:
# 沟通日志 — [案件名称]
**案件编号:** [案件编号]
**当事人:** [姓名]
**建立日期:** [YYYY-MM-DD]
仅追加。最新在最前。
---
然后将新条目置于顶部(最新在最前)。
--read——显示近期条目
打印最近 N 条(默认 5 条)。在学期中接手案件或当事人来电前有用。
--summary——简要阅读
生成一段话的日志摘要——最近联系、总条数、常用媒介、学生方任何待处理行动事项、任何未回复的沟通。输入给 /semester-handoff 和 /status。
--patterns——标记全日志的关注事项
扫描:
- 当事人方未回复的沟通。 当事人来电或邮件 N 次但无回复条目录入。
- 遗漏的后续跟进。 附后续截止日期的行动事项,但之后无条目解决。
- 语言/合理调整问题。 当事人语言标注为非中文;检查发出的沟通是否使用了该语言。
- 升级模式。 当事人语气变化(沮丧/焦虑)贯穿条目。
- 缺口。 在活跃案件中长时间无联系。
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 · 116 lines · 97 tokens per session scan A 109859ed3eaa
client-comms-log 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 1,679 once invoked, about $0.0005 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-lookup
Find and explain company policies in plain language. Trigger with "what's our PTO policy", "can I work remotely from another country", "how do expenses work", or any plain-language question about benefits, travel, leave, or handbook rules.
crisis-holding
Draft crisis holding statements, journalist Q&A posture, and what-not-to-say guidance from confirmed incident facts, with a hard legal-counsel gate. Builds each statement through proven crisis-comms frameworks (holding-statement anatomy, SCCT, CAP order, the legitimate non-answer, bridge/flag/block).
digital-estate-planner
Organizing digital life for legacy, emergency access, and death preparedness. Specializes in password management, account documentation, digital asset preservation, and ensuring loved ones can access what they need.
output-meta-post-flight
Post-flight validation for Output SDK workflow operations. Systematic verification of step completion, convention compliance, quality validation, and deliverable verification.
organizar-minha-caixa-de-entrada-juridica
Eu reviso a sua caixa de entrada em busca de assuntos jurídicos (contratos para revisar, NDAs, solicitações de dados de clientes, qualquer coisa que precise da atenção de um advogado) e te digo o que precisa de você e o que não precisa. Eu só organizo e resumo, nunca respondo.
advogado-criminal-v2
ADVOGADO CRIMINALISTA SENIOR — ESPECIALISTA EM DIREITO PENAL E MARIA DA PENHA workflow skill. Use this skill when the user needs Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal and the operator should…