02

02 is a skill for Claude Code, Codex from ThomasMoreAI/legal-skills-open. It costs 113 tokens per session (4,468 once invoked), scanned A, original, Apache-2.0.

A civil-litigation document workflow for China that turns a case strategy into formal court papers and manages documents from the opposing party and the court.

In plain words
What is it for?
Use it to draft complaints and defenses, prepare evidence lists, process incoming court documents, and track important litigation deadlines.
Why use it?
It organizes the facts, evidence, legal rules, roles, and deadlines needed to prepare a lawsuit or defense.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to draft complaints and defenses, prepare evidence lists, process incoming court documents, and track important litigation deadlines.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thomasmoreai/legal-skills-open/02
Install

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.

Any agent
npx skills add ThomasMoreAI/legal-skills-open --skill 02
Clone the repo
git clone --depth 1 https://github.com/ThomasMoreAI/legal-skills-open

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for 02

README.md
[![agentmods](https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/02/github.svg)](https://agentmods.dev/skills/thomasmoreai/legal-skills-open/02)
Your own site
<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.

agentmods 80×15 button for 02

Your own site · 80×15
<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>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,468 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash 22544f07faf3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

cn/litigation/skills/02/SKILL.md · 301 lines

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:

  1. 01-上一阶段产出/ — 阶段一的分析成果
  2. 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
  3. 04-对方来文/ — 对方提交的文书(如有)
  4. 05-法院来文/ — 法院送达的文书(如有)

0.2 读取顺序

  1. 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)
  2. 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
  3. 读取 01-上一阶段产出/01-材料索引与分类.md02-案件事实时间轴.md04-法条汇编.md
  4. 检查 04-对方来文/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
  5. 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

  1. 如法院来文载明特定期限,以法院指定为准
  2. 如法院未指定或指定不明,适用法定期限
  3. 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
  4. 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

  1. 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
  2. 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

  1. 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
  2. 案由:与策略方案书中的案由一致
  3. 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)
  4. 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"
  5. 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
  6. 尾部:具状人、日期、附注(副本份数、证据份数)

Read the full file on GitHub · 301 lines

Changes

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.

  1. 9d ago First seen · 301 lines · 113 tokens per session scan A 22544f07faf3

Subscribe to this mod's changes

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.