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-retailgit 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-retail)<a href="https://agentmods.dev/skills/avelikiy/great_cto/vertical-retail"><img src="https://agentmods.dev/badge/skills/avelikiy/great_cto/vertical-retail/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-retail"><img src="https://agentmods.dev/badge/skills/avelikiy/great_cto/vertical-retail.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 72 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00156 | $0.02122 |
| Opus 5 | $0.00078 | $0.01061 |
| Sonnet 5 | $0.00031 | $0.00424 |
| Haiku 4.5 | $0.00016 | $0.00212 |
Grade A, and why
vertical-retail 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 7d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retail & e-commerce — spec it like someone who's run a store
The SMB retail buyer already pays Shopify ($39–399/mo + 2.9%), BigCommerce, Wix, Ecwid, or WooCommerce. They are not naive — so the spec can't be either. A storefront that "has products and a cart" is table stakes; the value is in the parts those platforms do badly. Read this before writing the catalog/inventory/pricing/cart sections of any retail ARCH or PLAN doc.
1. Domain vocabulary (use these exact words)
- SKU vs variant — a variant is one buyable configuration (Red / Large); its SKU is the unique code that variant ships and is counted under. A "product" is the parent; you stock, price, and sell variants, not products.
- Multichannel / omnichannel — selling across several channels (own storefront, Amazon, eBay, in-store POS, Instagram). Omnichannel additionally means one inventory pool behind all of them. Channel-awareness is the whole game for SMB inventory.
- Reorder point — stock level that triggers a purchase order = (avg daily demand × lead time in days) + safety stock. Lead time = supplier days from order to receipt. Safety stock = buffer for demand/lead-time variance. Reordering without all three is wrong.
- COGS (cost of goods sold) and margin = (price − COGS) / price. Landed cost = unit cost + freight + duties + handling; margin must use landed cost, not invoice cost.
- ATS / available to sell = on-hand − allocated (reserved by open orders) − safety stock. Customers buy against ATS, never raw on-hand.
- Backorder vs preorder — backorder = out of stock now, will refill (sell against incoming PO). Preorder = not released yet, future availability date. Different fulfillment promises.
- Cart abandonment rate = 1 − (completed checkouts / carts created); industry ~70%.
- AOV (average order value) and conversion rate = orders / sessions. The two levers pricing/promotions move.
- Fulfillment — pick/pack/ship. Dropship = supplier ships direct, seller never holds stock (so "stock" is the supplier's ATS feed, not yours).
- MAP (minimum advertised price) — supplier-imposed price floor; a pricing rule must respect it or the seller loses the brand.
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.
- 7d ago First seen · 131 lines · 156 tokens per session scan A adc657d283f6
vertical-retail is a skill published in the GitHub repository avelikiy/great_cto (92 stars, last pushed today), licensed MIT. It adds 156 tokens to every session and 2,122 once invoked, about $0.0008 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.