breach-multi-jurisdiction

breach-multi-jurisdiction is a skill for Claude Code, Codex from ThomasMoreAI/legal-skills-open. It costs 91 tokens per session (2,139 once invoked), scanned A, original, Apache-2.0.

A framework for handling data-breach notifications across multiple countries and legal systems. A data breach is an unauthorised loss, exposure, or access to personal information.

In plain words
What is it for?
Use it to map affected jurisdictions, identify reporting deadlines, determine who must be notified, and coordinate notices to regulators and affected people.
Why use it?
It helps teams coordinate reports when different countries impose different deadlines, thresholds, and notification contents. It highlights the European Union’s GDPR 72-hour supervisory-authority deadline alongside other regimes.

Skill for Claude CodeCodex

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

Good fit Use it to map affected jurisdictions, identify reporting deadlines, determine who must be notified, and coordinate notices to regulators and affected people.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/breach-multi-jurisdiction"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/breach-multi-jurisdiction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,139 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 $0.00091 $0.02139
Opus 5 $0.00046 $0.01069
Sonnet 5 $0.00018 $0.00428
Haiku 4.5 $0.00009 $0.00214

Measured 9d ago against content hash 457e9795b42c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

breach-multi-jurisdiction 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.

cross-jurisdiction/data-protection/skills/breach-multi-jurisdiction/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Managing Multi-Jurisdiction Breach Notification

Overview

When a data breach affects individuals across multiple legal jurisdictions, the controller must navigate overlapping and sometimes conflicting notification requirements. The EU GDPR imposes a 72-hour supervisory authority notification deadline; US state laws impose varying timelines and content requirements; and other jurisdictions (Canada, Australia, Brazil, Japan, South Korea) have their own regimes. This skill provides the framework for coordinated notification across jurisdictions.

Jurisdiction Mapping — Notification Requirements

European Union — GDPR (All Member States)

Element Requirement
SA notification timeline 72 hours from awareness (Art. 33(1))
SA notification threshold Unless breach is "unlikely to result in a risk"
DS notification timeline Without undue delay when "high risk" (Art. 34(1))
Lead SA determination One-stop-shop: Art. 56 lead SA based on main establishment
Cross-border mechanism Lead SA notified; other concerned SAs informed via Art. 60
Content requirements Art. 33(3)(a)-(d) for SA; Art. 34(2) for data subjects

United States — State Breach Notification Laws

State Timeline AG Notification Threshold Key Differences
California Most expedient time possible, no unreasonable delay Yes, if 500+ CA residents Name + specified data element Substitute notice for 500,000+ affected; specific template for health data
New York Most expedient time possible, no unreasonable delay AG, DFS, DOCS simultaneously Private information (name + data element) SHIELD Act: 30-day AG notification for NY residents
Texas 60 days from determination AG if 250+ TX residents Name + sensitive personal information Expanded definition of sensitive data includes biometric identifiers
Florida 30 days from determination FDLE within 30 days if 500+ Name + specified data element One of the shortest statutory deadlines
Massachusetts As soon as practicable AG + OCABR simultaneously Name + specified data element Requires description of remedial services offered
Illinois Most expedient time possible, no unreasonable delay AG if 500+ IL residents Name + specified data element BIPA adds biometric data breach notification requirements
Virginia 60 days from discovery AG + affected individuals Name + specified data element VCDPA adds consumer data rights context
Colorado 30 days from determination AG within 30 days if 500+ Name + specified data element Among the shortest deadlines alongside Florida
Pennsylvania Without unreasonable delay AG if notifying Name + specified data element Broad definition of personal information
Washington 30 days from discovery AG within 30 days if 500+ Name + specified data element Biometric and health data included

Read the full file on GitHub · 153 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 · 153 lines · 91 tokens per session scan A 457e9795b42c

Subscribe to this mod's changes

breach-multi-jurisdiction is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (72 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 91 tokens to every session and 2,139 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 2026-09-03.