children-profiling-limits

children-profiling-limits is a skill for Claude Code, Codex from ThomasMoreAI/legal-skills-open. It costs 76 tokens per session (3,360 once invoked), scanned A, a copy of children-profiling-limits, Apache-2.0.

A compliance framework for limiting profiling and automated decisions involving children. Profiling means using personal data to predict behaviour or tailor content, advertising, or recommendations.

In plain words
What is it for?
Use it to review recommendation systems, targeted advertising, automated decisions, and child-user protections under GDPR, UK, EU, and US rules.
Why use it?
It helps services avoid behavioural advertising and other automated practices that privacy and online-safety rules restrict for minors. It also identifies safeguards where some profiling may be allowed.

Skill for Claude CodeCodex

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

Good fit Use it to review recommendation systems, targeted advertising, automated decisions, and child-user protections under GDPR, UK, EU, and US rules.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thomasmoreai/legal-skills-open/children-profiling-limits
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 children-profiling-limits
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 children-profiling-limits

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/children-profiling-limits"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/children-profiling-limits.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 3,360 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 95% 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 $0.00076 $0.03360
Opus 5 $0.00038 $0.01680
Sonnet 5 $0.00015 $0.00672
Haiku 4.5 $0.00008 $0.00336

Measured 8d ago against content hash 0cbcbac6bccd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

children-profiling-limits 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 8d 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

95% identical to children-profiling-limits — 22 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.

cross-jurisdiction/data-protection/skills/children-profiling-limits/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Children's Profiling Restrictions

Overview

Profiling of children is subject to heightened restrictions under multiple regulatory frameworks. GDPR Recital 71 states that automated decision-making including profiling "should not concern a child." The UK AADC Standard 12 requires profiling to be switched off by default for child users, with exceptions only where the controller can demonstrate a compelling reason and appropriate protective measures. The EU Digital Services Act (DSA) Article 28(2) explicitly prohibits online platforms from presenting targeted advertising based on profiling using the personal data of minors. COPPA prohibits the collection of persistent identifiers from children for behavioural advertising without verifiable parental consent. This skill establishes a comprehensive framework for lawful and ethical data processing that avoids prohibited profiling of children.

GDPR Recital 71 — Children and Automated Decisions

"In any case, such processing should be subject to suitable safeguards, which should include specific information to the data subject and the right to obtain human intervention, to express his or her point of view, to obtain an explanation of the decision reached after such assessment and to challenge the decision. Such measure should not concern a child."

The EDPB interprets "should not concern a child" as a strong presumption against subjecting children to automated decision-making based on profiling that produces legal or similarly significant effects. While "should not" is weaker than "shall not," the EDPB guidance and DPA enforcement practice treat this as an effective prohibition unless exceptional circumstances apply.

GDPR Article 22 — Automated Individual Decision-Making

Art. 22(1): "The data subject shall have the right not to be subject to a decision based solely on automated processing, including profiling, which produces legal effects concerning him or her or similarly significantly affects him or her."

Read the full file on GitHub · 188 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. 8d ago First seen · 188 lines · 76 tokens per session scan A 0cbcbac6bccd

Subscribe to this mod's changes

children-profiling-limits 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 3,360 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to children-profiling-limits, differing in 22 lines, and is treated as a copy.