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 zgbrenner/agentcounsel --skill childrens-privacy-reviewgit clone --depth 1 https://github.com/zgbrenner/agentcounselWrote 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/zgbrenner/agentcounsel/childrens-privacy-review)<a href="https://agentmods.dev/skills/zgbrenner/agentcounsel/childrens-privacy-review"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/childrens-privacy-review/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/zgbrenner/agentcounsel/childrens-privacy-review"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/childrens-privacy-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00052 | $0.03619 |
| Opus 5 | $0.00026 | $0.01809 |
| Sonnet 5 | $0.00010 | $0.00724 |
| Haiku 4.5 | $0.00005 | $0.00362 |
Grade A, and why
Children's Privacy Review 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.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Children's Privacy Review
Purpose
Organize the facts a reviewing attorney needs to assess whether a product or service attracts, is directed to, or is used by minors, and how it currently handles that population. The skill inventories audience-analysis signals, describes age-gating and parental-consent mechanics as implemented, records data-minimization, default, profiling, and advertising practices as facts, flags school/edtech context, and preserves cross-jurisdiction divergence rather than stating any age threshold as settled. It produces draft legal work product for attorney review — not legal advice.
This skill never concludes that a product "is directed to children," that an age gate or consent flow "is compliant," or that any specific age threshold applies. Those are attorney determinations that depend on jurisdiction, sector, and the totality of the facts. The skill's job is to organize the facts so counsel can make that determination — not to make it.
Use When
- A product, app, game, or online service is being reviewed for whether children's-privacy obligations may apply.
- A product team is designing or has implemented an age gate, age-assurance mechanism, or parental-consent flow and wants the mechanics organized for legal review.
- A launch review, feature review, or marketing-claims review has surfaced signals that minors may be part of the actual or likely audience.
- The organization operates or is evaluating a school-facing or edtech product and needs the school/education context flagged for specialized review.
- A vendor, partner, or internal team raises a concern that underage users may be present despite the stated age gate or terms of service.
- The organization needs a periodic children's-privacy fact review as part of a broader privacy or product-legal audit.
Required Inputs
- A description of the product or service — its functionality, how it is accessed (web, app, in-person, school-issued device), and its stated intended audience.
- Audience-analysis facts — content, subject matter, visual design, marketing channels, user testimonials or reviews, app-store category, influencer or ambassador programs, and any usage or analytics data bearing on the actual or apparent audience. Provide these as facts; do not ask the skill to infer an audience from a bare product name.
- The age-gating mechanics as implemented or designed — whether there is an age screen, self-declaration, neutral age screen, or a technical age-verification or age-estimation method, and how it behaves (e.g., what happens on a "too young" answer).
- The parental-consent flow, if any — how it is triggered, what is collected from the parent, how consent is verified, and what happens if consent is withheld or not obtained.
- Data practices — what personal data is collected from users, what the default settings are (visibility, sharing, notifications, geolocation), and whether profiling, personalization, recommendation systems, or targeted/behavioral advertising are used and whether minors are excluded from them.
- School/edtech context — whether the product is offered directly to consumers, through a school or district, under an operator/school agreement, or as an instructional tool, and who is understood to be the contracting party.
- Optional: any known instance of actual knowledge of underage use inconsistent with the stated audience or age gate — for example, a support ticket, a parent complaint, or internal data suggesting users below the stated minimum age.
- Optional: the practice group's
practice-profiles/privacy.mdif populated and loaded alongside this skill. If present, use its Standard Positions and Escalation Thresholds to benchmark the review; if absent, proceed without profile benchmarking.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 149 lines · 52 tokens per session scan A 24d10518e1a0
Children's Privacy Review is a skill published in the GitHub repository zgbrenner/agentcounsel (19 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 3,619 once invoked, about $0.0003 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.
Other skills, from other repositories
data-policy
Use when building internal data-governance machinery: a retention schedule (period, lawful basis, expiry action, system where deletion runs), an Art. 6 lawful-basis register, an Art. 30 ROPA, or a consent capture/withdrawal model. NOT the public privacy notice or DSAR handling (that is gdpr-privacy), NOT SOC 2 posture…
legal-risk-checker
Reviews a story brief, draft article, or broadcast script and flags potential legal risks — including defamation, privacy, contempt of court, and data protection — so you know what to check before publication.
gdpr-data-handling-note
Drafts a plain-language data handling notice for a journalistic or media production project that involves collecting, storing, or processing personal data — structured to meet GDPR transparency requirements while remaining understandable to non-lawyers.
gdpr-note-writer
Drafts a GDPR compliance note for a specific piece of journalistic content or data collection activity — documenting the lawful basis for processing personal data, what data is held, how long it is retained, and who has access.
implementing-gdpr-data-subject-access-request
Automates GDPR Data Subject Access Request (DSAR) workflows including identity verification, PII discovery across databases and files using regex and NER, data mapping, response templating per Article 15 requirements, deadline tracking, and audit logging. Covers ICO/EDPB guidance compliance, exemption handling, and…
privacy-compliance
Use this skill when implementing GDPR or CCPA compliance, designing consent management, conducting DPIAs, or managing data processing agreements. Triggers on GDPR, CCPA, data privacy, consent management, DPIA, data subject rights, privacy policy, cookie consent, and any task requiring privacy regulation compliance or…