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 anhnguyen0905/codex-mcp --skill ecommerce-operationsgit clone --depth 1 https://github.com/anhnguyen0905/codex-mcpWrote 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/anhnguyen0905/codex-mcp/ecommerce-operations)<a href="https://agentmods.dev/skills/anhnguyen0905/codex-mcp/ecommerce-operations"><img src="https://agentmods.dev/badge/skills/anhnguyen0905/codex-mcp/ecommerce-operations/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/anhnguyen0905/codex-mcp/ecommerce-operations"><img src="https://agentmods.dev/badge/skills/anhnguyen0905/codex-mcp/ecommerce-operations.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 | $0.00098 | $0.01376 |
| Opus 5 | $0.00049 | $0.00688 |
| Sonnet 5 | $0.00020 | $0.00275 |
| Haiku 4.5 | $0.00010 | $0.00138 |
Grade A, and why
ecommerce-operations 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E-commerce Operations (funnel, AOV, promos, returns, fulfillment)
The funnel, measured at every gate
sessions → product page views → add-to-cart → checkout started → order
CVR (conversion rate) = orders / sessions (state the session definition and window)
PDP conversion = add-to-cart / product page views
cart abandonment = 1 − (checkout started / carts created)
checkout abandonment = 1 − (orders / checkouts started)
AOV = gross order revenue / orders
revenue per session = CVR × AOV ← the number both levers roll up to
Diagnose by which gate leaks, segmented by device, traffic source, and new vs returning — a blended CVR moves whenever the traffic mix moves and says nothing about the store. Mobile checkout abandonment is routinely the largest single leak; check it before redesigning anything upstream.
Product pages and listings
- One listing = one buyer question set: what is it, does it fit my need, why trust you, what does it cost all-in. Title and first image carry most of the click decision; specs, sizing, and photos from every angle carry the conversion.
- Search terms belong in titles and attributes (that's what search indexes match); keyword-stuffed titles that read as spam lower click-through and, on marketplaces, invite suppression.
- Reviews ops: ask post-delivery (timed after actual use), make it one click, respond to negatives publicly with a fix. Never incentivize positive-only reviews — platform bans aside, a spotless 5.0 converts worse than a credible 4.6.
- Out-of-stock and inventory sync: oversells destroy marketplace account health; a buffer stock threshold per channel and a single source of truth for inventory beat manual reconciliation every time.
Pricing and promotion mechanics
- Every promo needs pre-declared math: expected uplift in units × contribution margin after discount vs baseline margin forgone on units that would have sold anyway. A promo that "did great revenue" while paying full margin away on baseline demand lost money invisibly.
- Discount depth trains customers: predictable sitewide sales teach everyone to wait. Prefer targeted mechanics (first-order, bundle, threshold "spend X get Y" — which lifts AOV) over blanket percentages.
- Cart abandonment recovery: the sequence (reminder → objection-handling → incentive last, hours to days apart) recovers a meaningful fraction; leading with a discount in email #1 just reprices everyone who was coming back anyway.
- Price changes on marketplaces interact with buy-box/ranking algorithms — change one variable at a time and hold a measurement window, or you learn nothing.
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 · 108 lines · 98 tokens per session scan A f1578db984f9
ecommerce-operations is a skill published in the GitHub repository anhnguyen0905/codex-mcp (3 stars, last pushed today), licensed MIT. It adds 98 tokens to every session and 1,376 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 2026-08-31.
Other skills, from other repositories
amazon-reviews-api-skill
This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…
amazon-competitor-analyzer
Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
food-order
Reorder previous Foodora orders, preview cart contents, and track delivery ETA/status with ordercli. Use when the user wants to reorder food, check delivery status, or browse recent Foodora order history. Never confirm an order without explicit user approval.
product-description-generator
E-commerce product description generator for any platform. Generates optimized titles, bullet points, descriptions, and backend keywords using competitor research + keyword scoring + FABE copywriting. Two modes: (A) Create — generate listing from product specs with optional competitor analysis, (B) Optimize — improve…
amazon-price-tracker
Amazon price monitoring and competitive pricing intelligence. Real-time price tracking, Buy Box analysis, promotion detection, and dynamic pricing strategy optimization. Use when the user asks about price monitoring, competitor pricing, Buy Box tracking, or pricing strategy.