customs-classification

customs-classification is a command for Claude Code from Kokai-Data/japan-business-data. It costs 37 tokens per session (166 once invoked), scanned A, original, Apache-2.0.

A command for organizing public reference material and candidate HS classifications for imported goods. HS codes are the international product categories used in customs and tariff systems; the output is reference information, not a final classification.

In plain words
What is it for?
Use it to prepare cited candidate classifications and supporting references for customs review, based on a product’s description, materials, use, and optional HS code.
Why use it?
It gathers cited product, material, use, and code signals without presenting an unlicensed judgment as certain. Final tariff treatment still needs confirmation from a customs broker or customs authority.

Command for Claude Code

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

Part of the kokai-data plugin — 19 skills, 8 commands, 7 agents, 1 MCP server shipped together

Good fit Use it to prepare cited candidate classifications and supporting references for customs review, based on a product’s description, materials, use, and optional HS code.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/kokai-data/japan-business-data/customs-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.

Clone the repo
git clone --depth 1 https://github.com/Kokai-Data/japan-business-data

Made for: Claude Code.

Or install kokai-data, the plugin that ships this one along with the rest of its 19 skills, 8 commands, 7 agents, 1 MCP server.

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 customs-classification

README.md
[![agentmods](https://agentmods.dev/badge/commands/kokai-data/japan-business-data/customs-classification.svg)](https://agentmods.dev/commands/kokai-data/japan-business-data/customs-classification)
Your own site
<a href="https://agentmods.dev/commands/kokai-data/japan-business-data/customs-classification"><img src="https://agentmods.dev/badge/commands/kokai-data/japan-business-data/customs-classification.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 166 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 $0.00037 $0.00166
Opus 5 $0.00018 $0.00083
Sonnet 5 $0.00007 $0.00033
Haiku 4.5 $0.00004 $0.00017

Measured 7d ago against content hash c6f9631861b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

customs-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 7d 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.

plugins/vertical-plugins/kokai-data/commands/customs-classification.md · 11 lines

What it actually says

From the product description, material, use, and HS code (optional), organize public-data reference material / candidate classifications / cited signals for customs classification. Call Kokai Data's customs_classification_advisory tool (or customs_* tools as needed) and present results with citations.

Guidelines:

  • Avoid definitive conclusions or recommendation phrasing.
  • Stay with "candidate classification", "reference material", "signal", "citation".
  • State that the final HS classification, tariff application, and customs procedures must be confirmed by a licensed customs broker / Customs (通関士・税関).
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. 7d ago First seen · 11 lines · 37 tokens per session scan A c6f9631861b8

Subscribe to this mod's changes

customs-classification is a command published in the GitHub repository Kokai-Data/japan-business-data (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 166 once invoked, about $0.0002 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.