hs-classification

hs-classification is a skill for Claude Code from Cleo-Labs-IA/skills_library. It costs 77 tokens per session (2,812 once invoked), scanned A, original, MIT.

A method for assigning the Harmonized System code used to classify goods in international customs. That code helps customs authorities determine duties, restrictions, and related trade requirements.

In plain words
What is it for?
It helps classify products from their description, materials, and use; compare national tariff codes; apply customs interpretation rules; and prepare a case for a binding tariff ruling.
Why use it?
A guessed or inconsistent customs code can lead to incorrect duties, shipping restrictions, or compliance problems. The same product may also need to be reconciled with local tariff systems.

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 It helps classify products from their description, materials, and use; compare national tariff codes; apply customs interpretation rules; and prepare a case for a binding tariff ruling.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cleo-labs-ia/skills_library/hs-classification
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 hs-classification
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 hs-classification

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/cleo-labs-ia/skills_library/hs-classification"><img src="https://agentmods.dev/badge/skills/cleo-labs-ia/skills_library/hs-classification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,812 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 $0.00077 $0.02812
Opus 5 $0.00039 $0.01406
Sonnet 5 $0.00015 $0.00562
Haiku 4.5 $0.00008 $0.00281

Measured 10d ago against content hash b46551c47a66, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

hs-classification 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 10d 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/hs-classification/SKILL.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HS Classification

The customs nomenclature layer. One classification drives duty rate, import/export controls, dangerous-goods rules, and product restrictions — so the code must be defensible, not guessed. This skill classifies from a part number, description, and composition using the General Rules of Interpretation, reconciles the code across national nomenclatures, and routes the result to the regimes it unlocks.

Boundary: customs-and-trade owns duty calculation, landed cost, dual-use and sanctions screening; dangerous-goods-transport owns UN transport rules; the vertical skills own product safety. This skill owns the classification itself — the input every one of those depends on.

MCP Tools

# Classify from description / composition (returns candidate headings + confidence)
mcp__claude_ai_CLEO_LEGAL_API__customs/classify
  description: "<commercial + technical description>"
  composition: "<materials / chemistry>"
  intended_use: "<function>"

# Search for classification and nomenclature-change signals
mcp__claude_ai_Cleo_Insight__search_signals(q="HS code reclassification", limit=25)
mcp__claude_ai_Cleo_Insight__search_signals(q="combined nomenclature update", limit=25)
mcp__claude_ai_Cleo_Insight__search_signals(q="tariff classification ruling", limit=25)

# Pull the restrictions that attach to a classified code
mcp__claude_ai_Cleo_Insight__get_regulation(id="<regulation-id>")

Classification Decision Tree

digraph {
  rankdir=TB; node [shape=box style=rounded fontsize=10];
  start [label="Part number / product\n+ description + composition + use"];
  cand [label="Identify candidate\nheadings (4-digit)"];
  notes [label="Read Section + Chapter\nNotes (legally binding)" shape=diamond];
  gri [label="Apply GRI 1 -> 6\nin order"];
  ec [label="Essential character\n(GRI 3b) for mixtures\n/ composite goods" shape=diamond];
  sub [label="Resolve 6-digit HS,\nthen national subheading\n(CN8 / HTS10 / TN VED...)"];
  conf [label="Confidence?" shape=diamond];
  bti [label="Request Binding Tariff\nInformation / advance ruling"];
  feed [label="Route to: duty, controls,\ndangerous goods, restrictions"];

  start -> cand -> notes -> gri -> ec -> sub -> conf;
  conf -> feed [label="high + single heading"];
  conf -> bti [label="ambiguous / high value"];
  bti -> feed;
}

Read the full file on GitHub · 181 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. 10d ago First seen · 181 lines · 77 tokens per session scan A b46551c47a66

Subscribe to this mod's changes

hs-classification is a skill published in the GitHub repository Cleo-Labs-IA/skills_library (1 stars, last pushed 3mo ago), licensed MIT. It adds 77 tokens to every session and 2,812 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 2026-08-31.

Related

Other skills, from other repositories

hipaa-validate

HIPAA validator: PHI exposure, audit logging, encryption, access control, BAA refs. Triggers: HIPAA, PHI, healthcare compliance, audit log, BAA.

softspark/ai-toolkit · 43 tokens

standards-expert

Expert-level ISO standards, quality management, compliance, and certification. Use when the user mentions ISO standards, quality management, compliance, or certification, or when the task involves Compliance & Certification, Auditing, or Continuous Improvement.

personamanagmentlayer/pcl · 50 tokens

soc2-expert

Expert in SOC 2 compliance, trust service criteria, audit preparation, controls implementation, and security frameworks. Use when the user mentions compliance, audit, trust services, AICPA, controls, or security framework, or when the task involves Trust Service Criteria, SOC 2 Types, Security Common Criteria, or…

personamanagmentlayer/pcl · 71 tokens

lawyer-expert

Expert-level legal systems, contracts, compliance, and legal technology. Use when the user mentions legal, contracts, compliance, law, or legal tech, or when the task involves Legal Systems, Legal Technology, Compliance Frameworks, or Contract Management.

personamanagmentlayer/pcl · 54 tokens

audit-expert

Expert-level security auditing, compliance, code review, and vulnerability assessment. Use when the user mentions compliance, security review, code review, vulnerability assessment, SOC 2, or GDPR, or when the task involves Audit Types, Audit Frameworks, Audit Process, or Authentication Review.

personamanagmentlayer/pcl · 60 tokens

hr-payroll

Help HR operations specialists, payroll administrators, and compensation teams understand, design, and run payroll processing, compliance, and payroll-related HR operations. Use when asked to set up a payroll process, run a payroll compliance audit, design a payroll calendar, handle a payroll discrepancy, build a…

tuanductran/hr-skills · 88 tokens