customs-adcvd-tariff-exposure

customs-adcvd-tariff-exposure is a skill for Claude Code, Codex from deciqAI/knowledge-skills. It costs 84 tokens per session (764 once invoked), scanned A, original, MIT.

A framework for tracing the later consequences of import decisions involving antidumping or countervailing duties, special tariffs, and product scope. Antidumping duties address unfairly low-priced imports, while countervailing duties address certain foreign subsidies.

In plain words
What is it for?
It helps review tariff classification and origin choices, check whether goods fall within a duty order or special tariff list, and examine transshipment, liquidation, and successor-liability risks.
Why use it?
It helps importers look beyond the duty charged at entry and notice risks such as retroactive charges, cash deposits, origin concerns, and importer liability.

Skill for Claude CodeCodex

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

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is **Industry front door for [second-order-thinking](../second-order-thinking/SKILL.md).** Adds domain triggers, example, packs only. Parent Process unchanged..

Good fit It helps review tariff classification and origin choices, check whether goods fall within a duty order or special tariff list, and examine transshipment, liquidation, and successor-liability risks.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/deciqAI/knowledge-skills
agentmods
npx agentmods add skills/deciqai/knowledge-skills/customs-adcvd-tariff-exposure

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 customs-adcvd-tariff-exposure

README.md
[![agentmods](https://agentmods.dev/badge/skills/deciqai/knowledge-skills/customs-adcvd-tariff-exposure/github.svg)](https://agentmods.dev/skills/deciqai/knowledge-skills/customs-adcvd-tariff-exposure)
Your own site
<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/customs-adcvd-tariff-exposure"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/customs-adcvd-tariff-exposure/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 customs-adcvd-tariff-exposure

Your own site · 80×15
<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/customs-adcvd-tariff-exposure"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/customs-adcvd-tariff-exposure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 764 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 $0.00084 $0.00764
Opus 5 $0.00042 $0.00382
Sonnet 5 $0.00017 $0.00153
Haiku 4.5 $0.00008 $0.00076

Measured 12d ago against content hash 712f6cfc539a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

customs-adcvd-tariff-exposure 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.

customs-adcvd-tariff-exposure/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Customs — AD/CVD & Tariff Exposure Cascade

Industry front door for second-order-thinking. Adds domain triggers, example, packs only. Parent Process unchanged. Not legal advice. Scope is order-specific; consult AD/CVD scope rulings / counsel.

Activate when: goods may fall under an antidumping/countervailing duty order or Section 301; sourcing changes; "are we exposed to AD/CVD or 301?"; scope ambiguity. Do NOT activate when: product clearly outside any order and no special tariff applies.

Why this variant

The parent second-order-thinking traces downstream consequences others miss. AD/CVD and Section 301 exposure is a second-order trap: a classification or origin choice that looks fine at entry can, orders later, mean retroactive duties, cash deposits, and importer liability — the broker's reasonable-care exposure too.

Domain inputs → parent's Process

  • 1st order: stated HTS + origin → duty at entry.
  • 2nd order: does the product fall within an AD/CVD scope (by description, not just HTS)? Section 301 China list?
  • 3rd order: transshipment/evasion risk (EAPA), retroactive liquidation, importer's cash-deposit rate, successor liability.
  • Parties: importer, surety, broker reasonable-care.

Worked example

Steel component classified cleanly, origin "Malaysia," inputs from China. → Second-order: AD/CVD orders are scope-based; a Chinese-origin input transshipped through Malaysia can trigger evasion (EAPA) findings + retroactive duties. Verify substantial transformation and scope before entry; a binding scope ruling may be warranted.

Compliance anchors

  • AD/CVD orders + scope rulings (Commerce); Section 301 (USTR); EAPA (evasion); reasonable care.

Packs

  • Solo broker: AD/CVD + 301 screen per product/origin.
  • Brokerage: scope-ruling trigger list; high-risk origin flags.

Red flags

  • Assuming HTS alone determines AD/CVD (it's scope-based).
  • Origin claims that look like transshipment.
  • No scope check on sourcing changes.

Read the full file on GitHub · 53 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 · 53 lines · 84 tokens per session scan A 712f6cfc539a

Subscribe to this mod's changes

customs-adcvd-tariff-exposure is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 10d ago), licensed MIT. It adds 84 tokens to every session and 764 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.