policy-starter

policy-starter is a skill for Claude Code from zhou210712/claude-for-legal-ZH. It costs 56 tokens per session (2,607 once invoked), scanned A, a copy of smart-search, Apache-2.0.

A drafting tool for an AI-use policy, the document that explains how a company uses artificial intelligence and what rules apply. It uses the company’s listed AI systems, regulatory requirements, risk preferences, and stated boundaries to prepare a draft for legal review.

In plain words
What is it for?
Use it to draft a policy for employees, the public, customers, or more than one audience. It helps describe permitted tools, prohibited uses, data handling, disclosures, and approval expectations.
Why use it?
Starting an AI policy from scratch makes it easy to omit systems, data practices, or required disclosures. This creates a first draft tied to the company’s recorded practices and leaves unresolved decisions for people to make.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Part of the ai-governance-legal plugin — 10 skills, 3 MCP servers shipped together

Good fit Use it to draft a policy for employees, the public, customers, or more than one audience. It helps describe permitted tools, prohibited uses, data handling, disclosures, and approval expectations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zhou210712/claude-for-legal-zh/policy-starter
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 zhou210712/claude-for-legal-ZH --skill policy-starter
Clone the repo
git clone --depth 1 https://github.com/zhou210712/claude-for-legal-ZH

Made for: Claude Code.

Or install ai-governance-legal, the plugin that ships this one along with the rest of its 10 skills, 3 MCP servers.

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 policy-starter

README.md
[![agentmods](https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/policy-starter/github.svg)](https://agentmods.dev/skills/zhou210712/claude-for-legal-zh/policy-starter)
Your own site
<a href="https://agentmods.dev/skills/zhou210712/claude-for-legal-zh/policy-starter"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/policy-starter/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 policy-starter

Your own site · 80×15
<a href="https://agentmods.dev/skills/zhou210712/claude-for-legal-zh/policy-starter"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/policy-starter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,607 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 84% copy Near-identical to another mod 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 $0.00056 $0.02607
Opus 5 $0.00028 $0.01303
Sonnet 5 $0.00011 $0.00521
Haiku 4.5 $0.00006 $0.00261

Measured 13d ago against content hash 50c35884dbcb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

policy-starter 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.

Origin

This is a copy

84% identical to smart-search — 288 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

ai-governance-legal/skills/policy-starter/SKILL.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/policy-starter

  1. 读取 ~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md → 监管注册表(适用法规)、AI系统清单(已在使用的AI)、公司的实践位置(风险偏好、透明度承诺)。
  2. 运行以下工作流。
  3. 确定受众 → 选择模板 → 填充公司的具体内容 → 输出草案。
  4. 附一份"仍需决定"清单——政策初稿解决不了的问题,需要由人来拍板。
/ai-governance-legal:policy-starter "内部员工AI使用政策"
/ai-governance-legal:policy-starter "面向用户"
/ai-governance-legal:policy-starter
[省略参数以获取受众选择提示]

AI使用政策起草

目的

没有AI使用政策的AI实践是在裸奔。监管机构、客户和用户都想知道:你用AI吗?用在哪里?怎么用?哪些数据被用于训练?这项技能基于你的实际实践和监管义务起草一份AI使用政策初稿。

加载当前状态

读取 ~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md

  • ## 监管注册表 — 适用的法规,决定了政策的合规底线
  • ## AI系统清单 — 已经在使用或计划使用的AI——政策不能比实际做得多或做得少
  • ## 红线 — 绝对不做的——政策应反映这些红线
  • ## 实践位置 — 公司的风险偏好、透明度立场、AI使用原则

工作流

第1步:确定受众和范围

受众 目的 典型内容
面向用户/公众 告知用户公司如何使用AI处理其数据或提供服务 AI系统的存在、AI决策的性质、用户如何获取人工介入、数据如何使用
内部员工 规范员工对公司AI工具的使用行为 可用的工具、禁止的行为、数据安全要求、审批流程
合作伙伴/客户(B2B) 告知商业客户AI在其服务中的应用 AI功能的可用性、数据保护、责任承诺

如果用户未指定,询问:"这项政策是面向谁的?(1) 面向用户/公众,(2) 内部员工,(3) 二者兼有。"

第2步:从清单和注册表中提取内容

必须纳入政策的具体内容来源于已存在的配置:

  • ## AI系统清单 中提取:
    • 已部署AI系统列表(按风险等级和功能分类)
    • 哪些涉及个人信息处理
    • 哪些面向公众,哪些是内部的
  • ## 监管注册表 中提取:
    • 法规要求的披露义务(例如《生成式人工智能服务管理办法》第15条要求标识AI生成内容 [法条原文]
    • 法规要求的用户权利(投诉举报机制、拒绝自动化决策的权利等)
    • 行业特定要求
  • ## 红线 中提取:
    • 绝对禁止的AI用例类型
    • 需要在政策中公开声明的底线原则

第3步:起草政策

面向用户/公众的AI使用政策模板
# AI使用说明

最后更新:[日期]

## 我们使用的AI技术

[公司名称]在以下服务和功能中使用了人工智能(AI)技术:

| AI功能 | 用途 | 涉及的个人信息 | 是否有自动化决策 |
|--------|------|---------------|-----------------|
| [功能] | [用途] | [数据类别] | 是/否 |
| [功能] | [用途] | [数据类别] | 是/否 |

## AI如何影响你

### 内容推荐
[如果使用算法推荐:说明推荐逻辑的基本原则,如何关闭个性化推荐]

### AI生成内容
[如果提供生成式AI服务:说明生成内容的标识方式,不构成专业建议的声明]

### 自动化决策
[如果使用自动化决策:说明决策的逻辑,用户获得人工介入和拒绝仅通过自动化决策的方式]

## 我们不会用AI做的事

[基于红线清单列出底线原则,例如:]
- 我们不使用AI进行社会信用评分
- 我们不基于种族、民族、性别等因素在交易条件上实行差别待遇
- 我们不会在未取得你同意的情况下,将你的个人信息用于AI模型训练

## 你的权利

[根据适用的法规(《个人信息保护法》《生成式人工智能服务管理办法》等),你享有以下权利:]
- [权利及行使方式]
- 如果你对我们的AI使用有任何问题或投诉,请通过[联系方式]联系我们。我们会在[时间]内回复。

## 我们如何管理AI风险

- 我们在部署新的AI功能前进行安全评估
- 我们对AI生成内容进行内容管理和人工审核
- [其他措施]

Read the full file on GitHub · 239 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. 13d ago First seen · 239 lines · 56 tokens per session scan A 50c35884dbcb

Subscribe to this mod's changes

policy-starter 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 56 tokens to every session and 2,607 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 84% identical to smart-search, differing in 288 lines, and is treated as a copy.

Related

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.

wanshuiyin/Auto-claude-code-research-in-sleep · 49 tokens

regulatory-research-fallback

Fallback workflow for regulatory research when web extraction tools fail on government PDFs.

HKUDS/OpenSpace · 20 tokens

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.

x-cmd/x-cmd · 57 tokens

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.

Klotzkette/claude-fuer-deutsches-recht · 69 tokens

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…

cwinvestments/memstack · 121 tokens

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…

LegalQuants/lq-ai · 79 tokens