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.
git clone --depth 1 https://github.com/deciqAI/knowledge-skillsnpx agentmods add skills/deciqai/knowledge-skills/customs-hts-classification-meceWrote 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/deciqai/knowledge-skills/customs-hts-classification-mece)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/customs-hts-classification-mece"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/customs-hts-classification-mece/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/deciqai/knowledge-skills/customs-hts-classification-mece"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/customs-hts-classification-mece.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 | $0.00071 | $0.00749 |
| Opus 5 | $0.00036 | $0.00375 |
| Sonnet 5 | $0.00014 | $0.00150 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
customs-hts-classification-mece 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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customs — HTS Classification (MECE Decomposition)
Industry front door for mece. Adds domain triggers, example, packs only. Parent Process unchanged. Not legal advice. Classification is fact-specific; use CBP rulings (CROSS) / binding rulings for certainty.
Activate when: classifying merchandise under the HTSUS; ambiguous/multi-function goods; "which heading applies?"; a product spanning multiple chapters. Do NOT activate when: an established binding ruling already governs the exact article.
Why this variant
The parent mece forces mutually-exclusive, collectively-exhaustive buckets. HTS classification via the General Rules of Interpretation (GRI) is literally a MECE walk: headings are meant to be exclusive; GRI 1→6 resolve overlaps so exactly one heading wins.
Domain inputs → parent's Process
- GRI 1: classify by heading terms + section/chapter notes (start here, exhaustively).
- If >1 heading fits (not mutually exclusive on its face): GRI 2 (incomplete/mixtures), GRI 3 (most specific → essential character → last in numerical order), GRI 4 (akin), GRI 5 (containers), GRI 6 (subheadings).
- The goal: a single, defensible heading with the reasoning recorded (reasonable care).
Worked example
A multi-tool with knife, screwdriver, LED light. → Not one obvious heading. Apply GRI 3(b) essential character; if indeterminate, GRI 3(c) last-in-order. Document the GRI path — that record is the reasonable-care defense in an audit.
Compliance anchors
- HTSUS + GRI; Section/Chapter Notes; 19 U.S.C. reasonable care; CBP CROSS rulings; binding-ruling option.
Packs
- Solo broker: GRI decision worksheet per SKU.
- Brokerage: ruling-backed classification library; binding-ruling triggers.
Red flags
- Jumping to a "close enough" heading without the GRI walk.
- Ignoring chapter notes that exclude a heading.
- No documented reasoning for a contestable classification.
Verification
- GRI 1 applied with section/chapter notes
- Overlaps resolved via GRI 2–6 in order
- Single defensible heading selected
- Reasoning recorded (reasonable care); binding ruling considered
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.
- 10d ago First seen · 52 lines · 71 tokens per session scan A 00f728cca3de
customs-hts-classification-mece is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 8d ago), licensed MIT. It adds 71 tokens to every session and 749 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.
Other skills, from other repositories
review-contract
Clause-by-clause contract review — inventories key clauses (term, termination, liability cap, indemnity, IP, payment, confidentiality, governing law, auto-renewal), flags deviations from market-standard positions with RED/YELLOW/GREEN severity and verbatim quotes, drafts redline language, and sets negotiation…
signature-request
Pre-signature gate and routing plan for a finalized document — verifies exact legal entity names, signatory authority, attached exhibits, filled blanks, consistent dates, and counterparty details, then sets the signing order (sequential vs. parallel, with reasons), writes envelope instructions for any e-sign tool, and…
compliance-check
Compliance pre-flight for a feature, campaign, or initiative — maps the data and activity involved, checks applicable regimes (privacy/GDPR-style, consumer protection, marketing rules, sector-specific), lists required approvals and notices, builds a gap list with remediation owners, and ends in a go/no-go…
legal-risk-assessment
Severity-by-likelihood legal risk register for a situation or deal — enumerates concrete risks, scores each one impact 1-5 × likelihood 1-5, renders a heat-map table, attaches mitigations to every risk at or above threshold, defines escalation criteria for immediate human counsel, and sets monitoring triggers. Use…
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
klauselinhalt-und-verbote-pruefen
Prüft eine AGB-Klausel anhand von Kontrollfähigkeit, gesetzlichen Klauselverboten und Interessenabwägung. Für B2C und B2B; liefert ein Klauselvotum mit Leitbild, Gegenposition und konkreter Rechtsfolge.