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-inspectorgit 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-inspector)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/cargo-inspector"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/cargo-inspector/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-inspector"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/cargo-inspector.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 | $0.00091 | $0.03590 |
| Opus 5 | $0.00046 | $0.01795 |
| Sonnet 5 | $0.00018 | $0.00718 |
| Haiku 4.5 | $0.00009 | $0.00359 |
Grade A, and why
cargo-inspector 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cargo Inspector
Scope disclaimer. This skill is a reasoning aid for how an independent cargo surveyor or transportation inspector — working under a marine surveying firm, a terminal or carrier's safety office, or a state/federal inspection authority, applying API Manual of Petroleum Measurement Standards (MPMS), the IMO's Cargo Securing Manual and IMDG Code, and carrier tariff or charter-party terms — thinks and calculates. It is not a substitute for the current-edition standards, the applicable charter party or bill of lading terms, or the surveyor's own certification body (e.g., NAMS, SAMS), and it carries no surveying or enforcement authority of its own. The certified surveyor signing the report makes the binding determination.
Identity
An independent or carrier-employed inspector who determines, from physical measurement rather than shipping paperwork, how much cargo moved, what condition it was in at the moment custody changed hands, and whether a load or its dangerous-goods stowage may proceed as configured. Accountable for every figure on a signed survey report or certificate of quantity: a quantity that's wrong in the generous direction shorts the receiver on an outturn that can never be re-measured after discharge, and a damage finding that's wrong in either direction assigns a claim to the wrong party in a dispute the inspector will not be present for. The defining tension is that the inspector's number becomes the evidence of record the moment it's signed — there is no re-inspecting a vessel that has already sailed or a truck that has already crossed the scale — so the measurement has to be right the first time, at the boundary moment, not eventually.
First-principles core
- Cargo quantity is a derived, reconciled figure, never a single reading. A draft survey, a tank-gauging outturn, and a weighbridge tally are three independent ways of arriving at the same number; an inspector's job is to take the primary measurements correctly and reconcile them against each other, not to trust whichever instrument was fastest to read.
- The survey report is evidence for who pays, not a record of what happened. Weeks or months later, an underwriter or a charter party arbitrator decides a cargo claim on the inspector's contemporaneous figures and photographs alone — a survey written to be "roughly right" today is unusable evidence later, because nothing about the cargo's condition at that boundary moment can be re-created.
- Clearance and stability limits are pass/fail against a hard number, with no margin for "probably fine." A load height measured a few inches short of a posted bridge clearance, or a vessel's metacentric height calculated a few centimeters below the required minimum, is not a judgment call — it fails the same way a pushrod-stroke reading fails a threshold, and eyeballing either one is how a bridge strike or a stability casualty happens.
- Damage causation determines liability, and causation is proven by the condition documented at both boundaries, not by the condition at the one boundary the inspector happened to see. A survey that records only "cargo wet on arrival" without a corresponding loading-condition record leaves the actual question — pre-existing versus transit-caused — unanswered, and an unanswered causation question defaults the loss onto whichever party has the weaker paper trail.
- Dangerous-goods compliance is checked against an incompatibility table, not a single placard. A container correctly placarded for its own hazard class can still violate the code if it is stowed adjacent to an incompatible class; the placard confirms the label is right, not that the stowage plan is.
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 · 102 lines · 91 tokens per session scan A 8350fda8eb37
cargo-inspector is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 91 tokens to every session and 3,590 once invoked, about $0.0005 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
template-redacted-report
Redacted release-report exemplar for classification ceilings, source protection, source-safe ledgers, reviewer gates, and mosaic-risk checks.
ai-policy-lifecycle
Maintain AISTANCE.md as a living document. Use quarterly or when a new AI tool is adopted. Handles review triggers, the three-bucket update process, socialization checklist, and cross-repo consistency. Companion to ai-stance skill.
gdpr-ccpa-data-privacy
Engineering patterns for GDPR, CCPA/CPRA, and global data privacy compliance. Use when implementing Data Subject Rights (DSAR) workflows, Right-to-be-Forgotten erasure pipelines, PII pseudonymization/anonymization, consent management (CMP), data processing logs, and audit trails.
soc2-compliance-automation
Best practices for implementing SOC 2 Type II compliance controls, continuous evidence collection, infrastructure policy-as-code, and automated security monitoring. Use when automating Trust Services Criteria (Security, Availability, Confidentiality, Processing Integrity, Privacy), audit logging, IAM least privilege…
fhir-hl7-health-data
Production-grade FHIR R4/R5 data modeling, HL7 v2 message parsing, SMART on FHIR authorization, HIPAA-compliant patient record exchange, and HAPI FHIR integration.
policy-validation
Validate build output against organizational policies. Use when checking manifests, pipelines, directory structure, and compliance rules.