Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add mrmarufpro/shopify-embedded-app-verify/plugin install shopify-embedded-app-verifyWrote 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/mrmarufpro/shopify-embedded-app-verify/run-embedded-app-verify)<a href="https://agentmods.dev/skills/mrmarufpro/shopify-embedded-app-verify/run-embedded-app-verify"><img src="https://agentmods.dev/badge/skills/mrmarufpro/shopify-embedded-app-verify/run-embedded-app-verify/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/mrmarufpro/shopify-embedded-app-verify/run-embedded-app-verify"><img src="https://agentmods.dev/badge/skills/mrmarufpro/shopify-embedded-app-verify/run-embedded-app-verify.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 | $0.00058 | $0.02369 |
| Opus 5 | $0.00029 | $0.01184 |
| Sonnet 5 | $0.00012 | $0.00474 |
| Haiku 4.5 | $0.00006 | $0.00237 |
Grade A, and why
run-embedded-app-verify scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
probe it — do not curl the `application_url` from `shopify.app.toml` or any How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify an embedded Shopify app change in the real admin
Closed loop: preflight → dedicated verify window → navigate the embedded app → interact → assert against the plan → report. On mismatch: fix the code and loop.
Hard rules:
- The dev server is the developer's responsibility. NEVER start it, and NEVER
probe it — do not curl the
application_urlfromshopify.app.tomlor any tunnel URL:shopify app devmints a fresh tunnel URL per run, so the toml value may not be the one actually serving. Judge dev-server health only by what the app iframe renders (step 4). If it is down, tell the user and stop. - NEVER touch browser tabs other than the verify tab you created. The rest of the browser belongs to the developer.
- Delete every screenshot you take once the report is delivered (see step 6).
1. Load project config
Read .claude/shopify-verify.json in the project root:
{ "appHandle": "...", "storeDomain": "...", "iframeSelector": "iframe[name=\"app-iframe\"]" }
If the file is missing, run the setup-embedded-app-verify skill flow first (same plugin), then continue.
2. Preflight
-
Determine the verification URL first — the preflight opens the browser directly on it when it has to launch one:
https://admin.shopify.com/store/<storeDomain>/apps/<appHandle>/<page-path>(<page-path>= the app route relevant to the change being verified). -
Run:
node ${CLAUDE_PLUGIN_ROOT}/scripts/ensure-browser.mjs --browser "${user_config.browser}" --mode "${user_config.mode}" --port "${user_config.cdp_port}" --url "<the verification URL>"(The
${user_config.*}values are substituted into this skill at load time; blank or literal placeholders are fine — the script defaults to chrome / profile / 9222.)- Exit 0 → CDP is live. Note the
BROWSER_STATE:line in the output —launched-at-url,launched, orreused— step 3 branches on it. - Non-zero → show the script's stderr message to the user verbatim and stop.
(
CDP_BLOCKED_DEFAULT_PROFILEmeans: tell the user to switch the plugin's mode option to "profile" via /plugin → configure.BROWSER_MISMATCHmeans: a browser other than the configured one owns the CDP port — the user must quit it or change the browser/cdp_port option.) Do NOT probe the dev server or any tunnel URL here (hard rule above) — the app iframe render in step 4 is the only dev-server health check.
- Exit 0 → CDP is live. Note the
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 · 199 lines · 58 tokens per session scan A 8c526ddbd027
run-embedded-app-verify is a skill published in the GitHub repository mrmarufpro/shopify-embedded-app-verify (4 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 2,369 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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-search-listing
Amazon search and category listing scraper: extract product listings from any Amazon search results page, keyword search URL, or category browse page and return per-item cards (asin, title, url, image, price, listPrice, stars, reviewCount, badges, isAmazonChoice, isBestSeller, isSponsored, delivery, boughtInPast…
amazon-bestseller-listing
Amazon Best Sellers listing scraper: extract product cards from any Amazon Best Sellers (zgbs) or /gp/bestsellers/ category page — returns rank (position on chart), asin, title, url, image, imageAlt, price, stars, reviewCount, ratingRaw per item, plus category metadata (categoryName, categoryFullName, categoryUrl) and…
etsy-product-detail
Etsy product detail scraper: given an Etsy listing URL, returns full product detail including listingId, title, priceCurrent, priceOriginal, currency, images (all), description, shopName, shopUrl, rating, reviewCount, favorites, inCartCount, variations (with per-option price ranges), highlights, listedDate…
walmart-product-detail
Walmart product detail page extractor: given a walmart.com product URL (walmart.com/ip/...), extract full product data including itemId, title, brand, model, UPC, price, wasPrice, currency, availability, category path, seller info, all images, shortDescription, longDescription, product highlights, full specifications…
walmart-category-listing
Walmart category page scraper: input a walmart.com browse or category URL with optional page number, extract paginated product listings with itemId, url, title, brand, image, price, wasPrice, rating, reviewCount, availability, seller info, fulfillmentBadge, and classType. Use when user mentions walmart category…
broken-link-checker
Scans a website to find broken links (404s, 500s). Crawls internal pages, identifies broken outbound links, and reports source pages for easy fixing. Use this when the user asks to "check for broken links", "find 404s", "audit my links", or "is my site healthy".