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 ThomasMoreAI/legal-skills-open --skill 02git clone --depth 1 https://github.com/ThomasMoreAI/legal-skills-openWrote 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/thomasmoreai/legal-skills-open/02)<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/02"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/02/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/thomasmoreai/legal-skills-open/02"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/02.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 | $0.00113 | $0.04468 |
| Opus 5 | $0.00056 | $0.02234 |
| Sonnet 5 | $0.00023 | $0.00894 |
| Haiku 4.5 | $0.00011 | $0.00447 |
Grade A, and why
02 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 — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
02 诉讼材料及来文管理:从策略到文书的转化
核心理念:阶段一想清楚,阶段二写清楚。本阶段不创造新的事实分析,而是把阶段一的结论转化为格式规范、可直接提交法院的法律文书。
Step 0:读取输入,确认角色与意图
0.1 输入源
本阶段以以下文件夹为唯一输入源,不跨目录读取其他阶段:
01-上一阶段产出/— 阶段一的分析成果02-客户情况说明/诉讼意图情况说明.md— 客户的诉讼意图问卷04-对方来文/— 对方提交的文书(如有)05-法院来文/— 法院送达的文书(如有)
0.2 读取顺序
- 读取
01-上一阶段产出/05-诉讼策略方案书.md,提取"代理方向"(原告/被告/未明确) - 读取
02-客户情况说明/诉讼意图情况说明.md- 如已填写,提取角色、保全意向、调查取证意向、调解意向等
- 如未填写或关键项空白,向用户询问必要信息
- 读取
01-上一阶段产出/01-材料索引与分类.md、02-案件事实时间轴.md、04-法条汇编.md - 检查
04-对方来文/和05-法院来文/是否有文件- 如有,提示用户进入阶段三(
03-庭审交锋/)进行质证和庭审准备
- 如有,提示用户进入阶段三(
- 确认
01-上一阶段产出/原始案件材料(已整理)/可读取
0.3 期限提取与跟踪
读取全部法院来文(05-法院来文/),提取并跟踪以下期限:
| 期限来源 | 期限事项 | 法定基准 | 优先级 |
|---|---|---|---|
| 应诉通知书 | 答辩期 | 15 日 | 法院指定 > 法定 |
| 举证通知书 | 举证期限 | 法院指定(通常 ≥30 日) | 法院指定 > 法定 |
| 传票 | 开庭日期 | 法院指定 | 法院指定 |
| 判决书/裁定书 | 上诉期 | 判决 15 日 / 裁定 10 日 | 法院指定 > 法定 |
规则:
- 如法院来文载明特定期限,以法院指定为准
- 如法院未指定或指定不明,适用法定期限
- 将提取的期限写入《关键期限跟踪表.md》,附于本阶段全部产出文件
- 关键期限到达前 3 日提醒用户
0.4 特殊案由检测与模板调用
- 读取阶段一产出中的案由标注:
- 如为普通案由(合同/侵权等)→ 使用通用模板
- 如为特殊案由(代位权/撤销权/人格否认/股东出资/执行异议之诉)→ 调用
02-参考模板/特殊案由适配/下对应案由的模板
- 如检测到特殊案由,在生成的起诉状/答辩状首部标注:"本案为【案由】,已按案由适配规则调整"
0.5 角色判定规则
| 情况 | 处理方式 |
|---|---|
| 策略方案书明确原告/被告 | 按策略方案书执行 |
| 策略方案书未明确,但情况说明已勾选 | 按情况说明执行 |
| 均未明确 | 询问用户:"您是代理原告起诉,还是代理被告应诉?" |
| 两者矛盾 | 以用户最新确认的版本为准 |
0.6 模式切换
- 原告模式(Builder):生成起诉状、证据目录、证据说明、诉讼费用计算表
- 被告模式(Breaker):需要
04-对方来文/中有原告起诉状;生成答辩状、证据目录、证据说明
⚠️ AI能力边界声明:本阶段AI生成的是法律文书初稿,必须经律师审核修改后才能提交法院。AI不保证符合受理法院的具体格式要求(如某些法院要求的特殊要素),用户需按法院要求调整。
Step 1:起草起诉状/答辩状
1.1 原告模式 — 起诉状
输入:策略方案书(诉讼请求、事实与理由、法律依据)+ 时间轴 + 材料索引 + 客户情况说明
输出:06-阶段产出/01-起诉状.md
撰写要点:
- 首部:原告、被告信息完整,与材料索引中的主体信息一致。如为特殊案由,按
角色判定规则.md调整当事人地位 - 案由:与策略方案书中的案由一致
- 管辖:如为特殊案由,按案由适配规则确认管辖法院(如撤销权为债务人/相对人住所地,代位权为次债务人住所地)
- 诉讼请求:
- 精确表述每一项请求,金额具体化(如有计算依据,注明来源)
- 如客户情况说明中勾选了"申请保全",在事实与理由中提及保全意向
- 如发现金额缺少计算依据,列入
07-待补充材料清单.md - 特殊案由调整:
- 代位权:诉讼请求必须明确"代位范围以债权人的债权为限"
- 撤销权:诉讼请求必须同时包含"撤销"+"恢复原状/返还财产/折价补偿"
- 人格否认:诉讼请求为"请求股东对公司债务承担连带责任"
- 事实与理由:
- 按时间轴顺序叙述,客观陈述
- 客观陈述事实,不在事实叙述中穿插证据编号
- 引用法条汇编中的法律依据作为请求权基础
- 如客户情况说明中"不接受调解",措辞应更坚决;如"接受调解",可保留调解空间
- 尾部:具状人、日期、附注(副本份数、证据份数)
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 · 301 lines · 113 tokens per session scan A 22544f07faf3
02 is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (72 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 113 tokens to every session and 4,468 once invoked, about $0.0006 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
pia-generator
Generate structured privacy impact assessments so Claude can organize project privacy risks, controls, and decision points into a review-ready report.
audit-scope-checklist
Generate a scoped IT audit program with controls mapped to roles and compliance frameworks. Use this skill for audit planning, control checklist generation, and auditprogram.json creation.
compliance-checker
Compare system configuration evidence against common control frameworks and produce a concise compliance assessment with gaps and remediation priorities.
compliance-controls-playbook
Guide Claude through a structured compliance audit workflow covering framework selection, evidence planning, control testing, exception handling, and reporting.
evidence-tracker
Manage audit evidence requests, collection progress, and status reporting so Claude can keep audits organized and identify overdue or blocked evidence items.
consent-checker
Review privacy policy or notice text against common privacy frameworks so Claude can explain coverage gaps, strengths, and compliance priorities.