china-pipl

china-pipl is a skill for Claude Code, Codex from ThomasMoreAI/legal-skills-open. It costs 76 tokens per session (4,051 once invoked), scanned A, original, Apache-2.0.

A compliance guide for China’s Personal Information Protection Law, the main Chinese law governing personal information. It covers consent, international data transfers, and duties for certain important systems.

In plain words
What is it for?
Use it to assess consent requirements, cross-border transfer options, separate-consent cases, and obligations linked to critical information infrastructure.
Why use it?
It helps identify which privacy rules apply when collecting, using, or sending people’s information across borders in China.

Skill for Claude CodeCodex

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

Good fit Use it to assess consent requirements, cross-border transfer options, separate-consent cases, and obligations linked to critical information infrastructure.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/china-pipl/github.svg)](https://agentmods.dev/skills/thomasmoreai/legal-skills-open/china-pipl)
Your own site
<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/china-pipl"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/china-pipl/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 china-pipl

Your own site · 80×15
<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/china-pipl"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/china-pipl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,051 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 $0.00076 $0.04051
Opus 5 $0.00038 $0.02025
Sonnet 5 $0.00015 $0.00810
Haiku 4.5 $0.00008 $0.00405

Measured 9d ago against content hash 0f2f55548582, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

china-pipl 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/data-protection/skills/china-pipl/SKILL.md · 291 lines

How it starts

The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.

China PIPL Compliance

Overview

The Personal Information Protection Law of the People's Republic of China (PIPL, 个人信息保护法) was adopted by the Standing Committee of the National People's Congress on 20 August 2021 and took effect on 1 November 2021. The PIPL is China's first comprehensive national personal information protection law, operating alongside the Cybersecurity Law (CSL, effective 1 June 2017) and the Data Security Law (DSL, effective 1 September 2021) to form China's data governance framework.

The Cyberspace Administration of China (CAC, 国家互联网信息办公室) is the primary regulator, with enforcement authority shared among the Ministry of Public Security, the Ministry of Industry and Information Technology (MIIT), and sector-specific regulators.

Scope and Extraterritorial Application

Territorial Scope (Art. 3)

The PIPL applies to:

  1. Processing of personal information of natural persons within the territory of the PRC (Art. 3(1))
  2. Processing conducted outside the PRC of personal information of natural persons within the PRC where the purpose is:
    • Providing products or services to natural persons within the PRC (Art. 3(2)(i))
    • Analysing or assessing the behaviour of natural persons within the PRC (Art. 3(2)(ii))
    • Other circumstances provided by laws or administrative regulations (Art. 3(2)(iii))

Extraterritorial Compliance (Art. 53)

Overseas personal information processors falling under Art. 3(2) must:

  • Establish a dedicated entity or designate a representative within the PRC to handle personal information protection matters
  • Report the name and contact information of the entity or representative to the relevant CAC department

Zenith Global Enterprises implementation: Zenith has designated its Shanghai office (Zenith Global Logistics (Shanghai) Co., Ltd) as the PRC representative entity, with the local Data Protection Manager serving as the designated contact.

Lawful Bases for Processing (Art. 13)

Basis PIPL Article Key Requirements
Consent Art. 13(1) Voluntary, explicit, informed; specific consent for sensitive PI, cross-border transfers, and public disclosure
Contract necessity Art. 13(2) Necessary to conclude or perform a contract to which the individual is a party, or for HR management per lawfully adopted labour rules
Statutory duty or obligation Art. 13(3) Necessary to fulfil statutory duties or obligations
Public health emergency Art. 13(4) Necessary to respond to public health emergencies or protect life/property in emergencies
Public interest activities Art. 13(5) Processing for news reporting, public opinion supervision, or other public interest activities within a reasonable scope
Processing within reasonable scope of lawfully disclosed PI Art. 13(6) Information already disclosed by the individual or through other lawful means
Other circumstances in laws/administrative regulations Art. 13(7) Catch-all provision for sector-specific legislation

Read the full file on GitHub · 291 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 · 291 lines · 76 tokens per session scan A 0f2f55548582

Subscribe to this mod's changes

china-pipl is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (72 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 76 tokens to every session and 4,051 once invoked, about $0.0004 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.