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 avelikiy/great_cto --skill vertical-logisticsgit clone --depth 1 https://github.com/avelikiy/great_ctoWrote 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/avelikiy/great_cto/vertical-logistics)<a href="https://agentmods.dev/skills/avelikiy/great_cto/vertical-logistics"><img src="https://agentmods.dev/badge/skills/avelikiy/great_cto/vertical-logistics/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/avelikiy/great_cto/vertical-logistics"><img src="https://agentmods.dev/badge/skills/avelikiy/great_cto/vertical-logistics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00129 | $0.02345 |
| Opus 5 | $0.00064 | $0.01172 |
| Sonnet 5 | $0.00026 | $0.00469 |
| Haiku 4.5 | $0.00013 | $0.00234 |
Grade A, and why
vertical-logistics 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 9d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vertical: Logistics & supply chain — spec it like you've shipped a pallet
SMB shipping & inventory has a deep vocabulary and a pile of rules that look optional until a real customer's data hits them. The incumbents (ShipHero, CartonCloud, Descartes ShipRush, GoFreight, AfterShip, FreightPOP) encode decades of this. A naive spec models a "shipment" as a tracking number and a "warehouse" as a quantity column — and ships a toy. This skill is the domain framing so architect/pm don't.
The four products and their incumbents:
| Product | Archetype | Wedge | Closest incumbent |
|---|---|---|---|
| shipment-tracking | dashboard | branded customer-facing tracking | AfterShip (lite) |
| warehouse-lite | crud | small-warehouse WMS | ShipHero / CartonCloud |
| route-optimization | booking | multi-stop route optimization | Descartes / FreightPOP |
| po-mgmt | crud | purchase-order lifecycle | GoFreight / FreightPOP |
1. Domain vocabulary (use these terms in the spec, not paraphrases)
- TMS vs WMS — Transportation Management System (moving goods between places: carriers, rates, routes, tracking) vs Warehouse Management System (goods at rest inside a building: SKUs, locations, pick/pack/ship). Don't conflate them; route-optimization + shipment-tracking are TMS-flavoured, warehouse-lite is WMS, po-mgmt straddles.
- Multi-carrier — a shipment can go via USPS / UPS / FedEx / DHL / regional carriers. Each has its own API, label format, status codes, and webhook shape.
- Rate shopping — given a parcel, query carriers and pick cheapest/fastest meeting the SLA. Drives carrier choice; depends on dimensional weight.
- Zones — carrier distance bands (origin→dest); rate is a function of zone × weight.
- Dimensional weight (DIM) — billable weight = max(actual weight, L×W×H / DIM divisor). A big light box bills as if heavy. Ignoring DIM under-quotes every rate.
- BOL (Bill of Lading) — the carrier contract / receipt for a shipment (esp. freight).
- ASN (Advance Ship Notice) — supplier's heads-up of an inbound shipment; feeds receiving so the warehouse knows what's arriving before it lands.
- SKU + lot/batch — SKU identifies the product; lot/batch identifies a specific production run (expiry, recall, FIFO). Same SKU, different lots, are not interchangeable.
- Pick / pack / ship — the outbound fulfilment sequence inside a warehouse.
- Putaway — placing received inventory into its storage location.
- Cycle count — periodic partial inventory audit (vs full physical count); keeps on-hand honest without shutting the warehouse.
- Reorder point + safety stock + lead time — reorder when on-hand ≤ (demand × lead-time) + safety stock. Drives PO creation timing.
- 3PL — third-party logistics provider; runs the warehouse/shipping on behalf of others.
- PO → receiving → put-away — the inbound lifecycle: order goods, receive against the PO, put away into locations.
- Dropship — supplier ships direct to the end customer; inventory never touches your warehouse.
- Last-mile — final leg to the customer's door; where most delivery cost/failure lives.
- Proof of delivery (POD) — signature / photo / timestamp confirming delivery.
- SLA / transit time — promised delivery window; the constraint rate-shopping optimises against.
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.
- 9d ago First seen · 154 lines · 129 tokens per session scan A 6c232c3be2e3
vertical-logistics is a skill published in the GitHub repository avelikiy/great_cto (93 stars, last pushed yesterday), licensed MIT. It adds 129 tokens to every session and 2,345 once invoked, about $0.0006 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
spec-drift
Standalone plan-vs-code audit on any branch: runs /ship Step 8's plan-completion section from disk (hash-pinned) against an explicit plan and base. Report, JSON, exit code. Never edits code.
third-lens-review
After Claude self-pitfall + Codex on a ship-worthy/architecture/RT/security/contract change: run a third external model house (distant training distribution → different blind spots) on the patched artifact, then adversarial synthesis.
quality-review
After a PRD, spec, or plan, before implementation: hunt perceived-quality pitfalls (silent failures, missing loading/empty states, error recovery, state drift) that make a product feel cheap. Complements pitfall-verification.
boundaries
Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
triage
Triage review findings interactively — approve, skip, or prioritize each issue. Use after /phx:review to filter findings before fixing.