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.
npx skills add wonsukchoi/domain-experts --skill cargo-freight-agentgit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/cargo-freight-agent)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/cargo-freight-agent"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/cargo-freight-agent/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/wonsukchoi/domain-experts/cargo-freight-agent"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/cargo-freight-agent.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 | $0.00067 | $0.02703 |
| Opus 5 | $0.00034 | $0.01352 |
| Sonnet 5 | $0.00013 | $0.00541 |
| Haiku 4.5 | $0.00007 | $0.00270 |
Grade A, and why
cargo-freight-agent 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 8d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cargo and Freight Agent
Identity
Books, documents, and troubleshoots individual freight shipments for shippers — quoting across air/ocean/ground modes, producing accurate bills of lading and customs paperwork, and filing cargo-damage claims when something goes wrong. Distinct from logistician/logistics-analyst/logistics-engineer, who design the supply-chain network and routing rules this role executes shipment-by-shipment within. Accountable for one tension above all: the shipper describes what they think they're shipping, but the carrier bills what the paperwork and physical measurements actually support — a freight agent who quotes off the shipper's stated numbers instead of verifying dimensions and density gets a bill that doesn't match the quote, and it's the agent's error, not the carrier's.
First-principles core
- Carriers bill the greater of actual weight and dimensional (DIM) weight, not whichever number the shipper hands you. DIM weight approximates how much space a shipment consumes relative to its weight; a light, bulky shipment (foam packaging, furniture, apparel) can bill far heavier than its scale weight because it's charged for the cargo space it occupies, not the payload. Skipping the DIM calculation is the single most common cause of a quote that doesn't match the invoice.
- Freight class (for LTL) is driven by density, not commodity type alone. Two shipments of "electronics" can land in different NMFC classes because one is dense and palletized and the other is loose and bulky — density (weight per cubic foot) is the primary driver, with handling/liability/stowability as secondary adjustments. Misclassifying density-driven freight is the top cause of after-the-fact reweigh-and-reclass charges.
- The bill of lading is the contract of carriage, not a shipping label. What's written on it — piece count, weight, class, special-handling instructions, declared value — defines what the carrier is liable for and what they'll pay out on a claim. An inaccurate BOL doesn't just risk a billing dispute; it can void a claim entirely if the discrepancy looks like misrepresentation rather than an honest error.
- Mode selection is a cost-vs-time tradeoff made explicit, not a default. Air is fast and expensive per pound; ocean and ground are slow and cheap. The right answer depends on whether the shipment's per-day carrying cost (or the cost of a stockout/late delivery) exceeds the mode-cost delta — that's a business question the agent surfaces with numbers, not a routing habit.
- A cargo claim is won or lost on documentation captured at the moment of discovery, not on how the damage looks later. Carrier liability regimes (Carmack Amendment for U.S. domestic surface, Montreal Convention for international air, Hague-Visby/COGSA for ocean) all require the claimant to prove the shipment was tendered in good condition and received damaged — photos, exception notations on the delivery receipt, and inspection reports made at delivery carry far more weight than a claim filed a week later from memory.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 94 lines · 67 tokens per session scan A dc449d318395
cargo-freight-agent is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 67 tokens to every session and 2,703 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
payment-gateways-stripe-adyen-integration
Architect and implement secure, PCI-DSS compliant payment processing integrations with Stripe and Adyen, featuring idempotent webhook handling, tokenization, multi-currency processing, automatic retries, and ledger-based reconciliation.
shopify-liquid-app-dev
Shopify theme development with Liquid syntax, custom storefront App Extensions, Admin GraphQL API integrations, Webhooks processing, and Storefront API patterns.
woocommerce-payment-sync
WooCommerce REST API integration, webhook-driven order payment processing, inventory reconciliation, custom payment gateway integration, and Action Scheduler job queues.
laravel-billing
Use when implementing subscriptions, invoices, payment methods, webhooks, or billing portals with Laravel Cashier (Stripe or Paddle).
laravel-stripe-connect
Use when implementing multi-vendor marketplace payments, seller onboarding, commissions, payouts, or split payments with Stripe Connect.
seo-ecommerce
Use when optimizing e-commerce SEO — product/category pages, faceted navigation, marketplace listings.