baby-formula-compliance

baby-formula-compliance is a skill for Claude Code from Cleo-Labs-IA/skills_library. It costs 91 tokens per session (4,354 once invoked), scanned A, original, MIT.

A compliance guide for selling infant formula and related products, such as follow-on formula, toddler milk, and specialty formula. It covers rules in the European Union, United States, China, and other listed markets, including labeling and marketing limits.

In plain words
What is it for?
Use it to classify a formula product, check its nutrient profile, prepare facility and product registrations, review labels and marketing, track batches, and plan post-market complaint handling.
Why use it?
It helps identify regulatory steps and reduce risks around product approval, required nutrition information, restricted promotion, recalls, and product tracking.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the compliance-product-guidance plugin — 53 skills shipped together

Good fit Use it to classify a formula product, check its nutrient profile, prepare facility and product registrations, review labels and marketing, track batches, and plan post-market complaint handling.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cleo-labs-ia/skills_library/baby-formula-compliance
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 Cleo-Labs-IA/skills_library --skill baby-formula-compliance
Clone the repo
git clone --depth 1 https://github.com/Cleo-Labs-IA/skills_library

Made for: Claude Code.

Or install compliance-product-guidance, the plugin that ships this one along with the rest of its 53 skills.

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 baby-formula-compliance

README.md
[![agentmods](https://agentmods.dev/badge/skills/cleo-labs-ia/skills_library/baby-formula-compliance/github.svg)](https://agentmods.dev/skills/cleo-labs-ia/skills_library/baby-formula-compliance)
Your own site
<a href="https://agentmods.dev/skills/cleo-labs-ia/skills_library/baby-formula-compliance"><img src="https://agentmods.dev/badge/skills/cleo-labs-ia/skills_library/baby-formula-compliance/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 baby-formula-compliance

Your own site · 80×15
<a href="https://agentmods.dev/skills/cleo-labs-ia/skills_library/baby-formula-compliance"><img src="https://agentmods.dev/badge/skills/cleo-labs-ia/skills_library/baby-formula-compliance.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 4,354 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 $0.04354
Opus 5 $0.00046 $0.02177
Sonnet 5 $0.00018 $0.00871
Haiku 4.5 $0.00009 $0.00435

Measured 12d ago against content hash 0693b8813b15, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

baby-formula-compliance 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 12d 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.

skills/baby-formula-compliance/SKILL.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Baby Formula Compliance

Full regulatory workflow for infant formula and follow-on products. Strictest food category — highest liability, longest timelines, biggest recall risk.

Decision Flow

digraph {
  rankdir=TB; node [shape=box style=rounded fontsize=10];
  classify [label="1. Classify product:\ninfant 0-6 / follow-on 6-12 /\ngrowing-up 12-36 / FSMP"];
  nutrient [label="2. Build nutrient profile\nper Reg 2016/127 / 21 CFR 107.100 /\nGB 10765"];
  facility [label="3. Facility approval:\nFDA Sec 412 verification,\nNMPA factory audit,\nEU FBO registration"];
  formula [label="4. Per-brand-per-factory-per-stage\nregistration (NMPA, FSANZ)"];
  label [label="5. Mandatory labeling:\nWHO Code 1981 compliance,\nnutrition declaration"];
  marketing [label="6. Marketing restrictions:\nNo IF advertising,\nno promotional discount,\nno HCP samples"];
  pms [label="7. Post-market surveillance:\ncomplaint logging,\nbatch traceability,\n24-month retention"];
  sell [label="8. Place on market"];
  classify -> nutrient -> facility -> formula -> label -> marketing -> pms -> sell;
}

EU -- Regulation 609/2013 (FSG) + Delegated Regulation 2016/127

Aspect Detail
Parent regulation Reg (EU) 609/2013 on food for specific groups (FSG) — replaces former Dietetic Foods directive
Infant formula (0-6 months) + follow-on formula (6-12 months) Delegated Reg (EU) 2016/127
Processed cereal-based foods + baby foods Delegated Reg (EU) 2016/128
FSMP (Foods for Special Medical Purposes) Delegated Reg (EU) 2016/128 — includes hypoallergenic + medical formulas
Growing-up milk (12-36 months) NOT covered by 609/2013 — falls under General Food Law Reg 178/2002. EFSA opinion 2013: not necessary in EU diet. Some MS impose national rules

Nutrient Composition -- Annex I of 2016/127

Nutrient Infant Formula Min Infant Formula Max
Energy 250 kJ/100 mL 295 kJ/100 mL
Protein (cow milk) 1.8 g/100 kcal 2.5 g/100 kcal
Protein (soy isolate) 2.25 g/100 kcal 2.8 g/100 kcal
Fat 4.4 g/100 kcal 6.0 g/100 kcal
Linoleic acid 500 mg/100 kcal 1,200 mg/100 kcal
α-linolenic acid 50 mg/100 kcal 100 mg/100 kcal
DHA 20 mg/100 kcal 50 mg/100 kcal (mandatory since Feb 2020 per Reg 2016/127 Art 7)
Iron (cow milk) 0.3 mg/100 kcal 1.3 mg/100 kcal
Vitamin D 2 μg/100 kcal 3 μg/100 kcal

Read the full file on GitHub · 250 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. 12d ago First seen · 250 lines · 91 tokens per session scan A 0693b8813b15

Subscribe to this mod's changes

baby-formula-compliance is a skill published in the GitHub repository Cleo-Labs-IA/skills_library (1 stars, last pushed 3mo ago), licensed MIT. It adds 91 tokens to every session and 4,354 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 2026-08-31.

Related

Other skills, from other repositories

bfsg-dienstleistung-ecommerce

Barrierefreiheit von Dienstleistungen im elektronischen Geschäftsverkehr – Pflichten des Dienstleistungserbringers § 14 BFSG, Barrierefreiheitsinformationen nach Anlage 3 Nr. 1 mit Beschreibung, Erläuterung, Konformitätsdarlegung und Angabe der Marktüberwachungsbehörde, materielle Anforderungen der §§ 12, 13 und 19…

borghei/AI-Skills-German-Law · 237 tokens

e-commerce-pflichten

Prüfung der Pflichten eines Online-Shops im elektronischen Geschäftsverkehr: allgemeine Pflichten (§ 312i BGB), besondere Verbraucherpflichten und Button-Lösung (§ 312j BGB) sowie Widerrufsrecht (§ 312g, § 355 BGB), inklusive der Folgen von Verstößen. Use when ein Online-Shop oder Bestellprozess auf gesetzliche…

borghei/AI-Skills-German-Law · 96 tokens

einbeziehung-online-clickwrap-browsewrap

Für Einbeziehung Online Clickwrap Browsewrap: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.

Klotzkette/claude-fuer-deutsches-recht · 42 tokens

kurzfristige-preiserhoehung-lieferfrist

Für Kurzfristige Preiserhöhung 309: prüft Frist, Form, Zuständigkeit und Eilbedarf; Ergebnis: Fristen- und Risikoampel. Fachgebiet: AGB-Recht-Prüfer. Route: kurzfristige-preiserhoehung-lieferfrist.

Klotzkette/claude-fuer-deutsches-recht · 72 tokens

plattform-online-gate-rollout-rangfolge

Für Plattform und Online Checkout: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: plattform-online-gate-rollout-rangfolge.

Klotzkette/claude-fuer-deutsches-recht · 62 tokens

commerce-ad-claim-compliance-kr

A pre-publication check for Korean advertising and product-page wording. It reviews claims against South Korea's advertising, food-safety, and e-commerce laws.

modu-ai/moai-cowork · 381 tokens