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 pa1nrui1/legal-skills --skill quaigit clone --depth 1 https://github.com/pa1nrui1/legal-skillsWrote 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/pa1nrui1/legal-skills/quai)<a href="https://agentmods.dev/skills/pa1nrui1/legal-skills/quai"><img src="https://agentmods.dev/badge/skills/pa1nrui1/legal-skills/quai/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/pa1nrui1/legal-skills/quai"><img src="https://agentmods.dev/badge/skills/pa1nrui1/legal-skills/quai.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 | $0.00033 | $0.00884 |
| Opus 5.5 | $0.00013 | $0.00354 |
| Sonnet 5.5 | $0.00007 | $0.00177 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
法律文章quai味道 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 2mo 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.
What it actually says
法律工作总控规则（强制）
执行本 Skill 前，必须先遵循：
- skills/legal/法律工作总控/references/practice-profile.md
- skills/legal/法律工作总控/references/matter-workspace-protocol.md
- skills/legal/法律工作总控/references/document-reading-protocol.md
- skills/legal/法律工作总控/references/source-boundary-protocol.md
- skills/legal/法律工作总控/references/ocr-correction-protocol.md
- skills/legal/法律工作总控/references/pkulaw-mcp-legal-verification-protocol.md
本 Skill 只处理「法律文章quai味道」专业任务；案件隔离、事项路径、文件读取、OCR 复查、来源披露、缺口归档、法规/案例/Wiki 核验和复盘台账更新均按法律工作总控共享协议执行。
旧规则废止（强制）
- 旧文中直接写死的客户目录、阶段目录、旧式台账写入、旧本地读取协议均不作为执行规则。
- 事项路径、当前事项、系统记录、业务文件区和复盘台账统一以法律工作总控
matter-workspace-protocol.md为准。 - 不得静默写入复盘台账；确需更新时，先确认属于复盘台账更新并向用户说明。
De AI Polish
轻量入口
本文件是瘦身后的触发入口，只保留任务边界、执行顺序和按需读取索引。完整流程、模板、清单、专项规则和长示例已迁移至 references/完整流程.md。
何时使用
- 用户明确提到「法律文章quai味道」或本 Skill frontmatter 描述中的任务。
- 用户请求生成、审查、分析、计算、管理或推进与「法律文章quai味道」对应的法律工作成果。
- 法律工作总控或上游 Skill 路由到本 Skill。
执行顺序
- 先按法律工作总控确认当前事项、业务文件区、系统记录区和来源边界。
- 判断用户任务是否可以用本轻量入口完成；如只是路由、状态判断或简短提示，不默认读取完整流程。
- 需要生成正式文书、报告、清单、计算结果、可视化、专项审查或复杂分析时，按需读取
references/完整流程.md的相关章节。 - 读取外置细节时，只读取当前任务需要的章节；不要为一个小问题整篇加载完整流程。
- 输出前同步披露已读取材料、已核验内容、未核验/存疑内容、法规案例检索状态和需要用户判断事项。
按需读取索引
references/完整流程.md：瘦身前完整正文，含详细流程、模板索引、专项规则、交互规范和注意事项。references/：本 Skill 的专业规则、清单、方法论和外置参考材料。templates/：文书、报告、表格等输出模板；仅在需要生成对应成果时读取。assets/、scripts/、checklists/、reference/：如目录存在，仅在完整流程或当前任务明确需要时读取。
输出底线
- 不跳过用户提供的材料；读取失败必须说明。
- 不用模型记忆替代法律法规核验；引用法规、案例、Wiki 或网页搜索时必须标注来源和核验状态。
- 材料不足时提示缺口，不悄悄补全。
- 需要写入系统记录、复盘台账、飞书文档或飞书日历时，按总控和对应飞书 Skill 规则执行。
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 57 lines · 33 tokens per session scan A 806f019ee0df
法律文章quai味道 is a skill published in the GitHub repository pa1nrui1/legal-skills (113 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 884 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
法律文章quai味道 compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| 法律文章quai味道pa1nrui1/legal-skills | Skill | 113 | 4mo ago | MIT | A | 33 | Claude Code, Codex |
| litigation-prep-skill-cnyxk-lawyer/litigation-prep-skill-cn | Skill | 23 | 4mo ago | none | A | 47 | Claude Code, Codex |
| contract-drafterrohasnagpal/legal-ai-skills | Skill | 201 | 27d ago | MIT | A | 192 | Claude Code, Codex |
| investment-and-shareholder-agreement-reviewerrohasnagpal/legal-ai-skills | Skill | 201 | 27d ago | MIT | A | 207 | Claude Code, Codex |
| negotiation-position-plannerrohasnagpal/legal-ai-skills | Skill | 201 | 27d ago | MIT | A | 118 | Claude Code, Codex |
| redline-proposerrohasnagpal/legal-ai-skills | Skill | 201 | 27d ago | MIT | A | 118 | Claude Code, Codex |
| citation-integrity-checkerrohasnagpal/legal-ai-skills | Skill | 201 | 27d ago | MIT | A | 180 | Claude Code, Codex |