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 NEU-ZHA/legal-ai-skills --skill pkulaw-legal-searchgit clone --depth 1 https://github.com/NEU-ZHA/legal-ai-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/neu-zha/legal-ai-skills/pkulaw-legal-search)<a href="https://agentmods.dev/skills/neu-zha/legal-ai-skills/pkulaw-legal-search"><img src="https://agentmods.dev/badge/skills/neu-zha/legal-ai-skills/pkulaw-legal-search/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/neu-zha/legal-ai-skills/pkulaw-legal-search"><img src="https://agentmods.dev/badge/skills/neu-zha/legal-ai-skills/pkulaw-legal-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00098 | $0.02732 |
| Opus 5 | $0.00049 | $0.01366 |
| Sonnet 5 | $0.00020 | $0.00546 |
| Haiku 4.5 | $0.00010 | $0.00273 |
Grade A, and why
pkulaw-legal-search 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 13d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
北大法宝网页/Computer Use 检索技能
核心原则
本 skill 是用户自建的北大法宝网页检索与兜底流程，不是要替代原生 MCP skill。正确定位是：
- 能用 MCP 快速拿到列表或条文时，先用 MCP。
- MCP 不通、当前会话没加载对应工具、返回 401/403/超时/无结果、结果不足、需要登录详情页、需要网页筛选、需要复制真实 URL、或需要确认页面可见内容时，转入本 skill 的网页/Computer Use 流程。
- 在 Codex 桌面环境中，网页端优先用 Computer Use 操作本机浏览器，因为它更可能保留学校/IP/机构登录状态。
MCP 与网页的分工
统一积分模式下，可以配置 10 项 MCP，但普通检索仍应优先调用以下三个约 25 积分服务：
mcp__pkulaw_law_keyword__get_law_list：检索法律法规-关键词。输入title和/或fulltext，返回法规列表前 10 条。mcp__pkulaw_fatiao__get_law_item_content：精准查找法条-关键词。适合已知法规名、条号或需要条文原文时使用；参数为title和tiao_num。mcp__pkulaw_case__get_case_list：检索司法案例-关键词。输入title和/或fulltext，返回案例列表前 10 条。
法规语义、案例语义、法条识别、引用校验、超链、案号识别和综合检索属于约 125 积分服务。只有关键词检索不足或任务明确需要对应专门能力时才调用；不能把 10 项全部跑一遍。是否可用以当前控制台开关和 MCP tools/list 为准。
优先级必须按以下顺序执行：
- 先用经济型 MCP：法规列表用
get_law_list，精准法条用get_law_item_content，案例用get_case_list。 - 再用网页：MCP 找不到、结果不足、需要登录后详情页或需要确认页面 URL 时，再访问北大法宝网页。
- Codex 中优先 Computer Use：如果在 Codex 桌面环境且页面需要 IP 登录/机构登录/真实浏览器状态，优先用 Computer Use 操作本机浏览器或已登录页面。
- camoufox/Agent Browser 仅作后备：当没有 MCP、没有 Computer Use、或任务明确要求 camoufox/Agent Browser 时，才用 camoufox-cli/Agent Browser。
触发场景
当用户提出以下需求时使用：
- 检索法律法规、司法解释、行政法规、地方性法规
- 检索案例、案号、裁判文书、指导性案例、典型案例
- 为作业、法律意见、论文脚注补充北大法宝法规/案例线索
- 初步验证某个法规或案例是否存在
Step 0：识别可用检索通道
在开始检索前，先判断当前环境有哪些工具。
A. MCP 优先
如果当前工具列表中存在以下北大法宝 MCP，优先使用：
mcp__pkulaw_law_keyword__get_law_list：按标题/正文关键词检索法规列表。mcp__pkulaw_fatiao__get_law_item_content：按法规名、条号精准查找法条。mcp__pkulaw_case__get_case_list：按标题/正文关键词检索案例列表。
MCP 适合快速获得：标题、法条原文、法院、案号、发布日期、案例链接、法规链接。
B. Browser / Computer Use 后备
如果 MCP 不可用、结果太少、链接打不开，或者需要登录状态下确认详情页：
- Codex 桌面环境：优先使用 Computer Use 控制本机浏览器。原因是本机浏览器更可能已有学校/机构 IP 登录状态、cookie、浏览器会话，速度通常也比 camoufox 更快。
- 有 in-app Browser 且页面不需要登录：可用 Browser 打开公开页面确认链接。
- 非 Codex 或明确要求 camoufox：再使用 camoufox-cli/Agent Browser。
Step 1：明确检索对象
先把用户需求归类：
- 法条：法规名称 + 条号，例如《民法典》第153条。
- 法规文件：标题、文号、发布时间、修正时间。
- 案例：案名、法院、案号、案由、关键词。
- 论文/文章：作者、标题、期刊、年份、关键词。
- 综合研究：问题描述 + 需要的材料类型。
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.
- 13d ago First seen · 234 lines · 98 tokens per session scan A 538a3994ccb3
pkulaw-legal-search is a skill published in the GitHub repository NEU-ZHA/legal-ai-skills (64 stars, last pushed 23d ago), licensed MIT. It adds 98 tokens to every session and 2,732 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 2026-08-30.
Other skills, from other repositories
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
nda-review
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…