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 neuratechcompany-ops/kettu-marketplace-mcp --skill dns-connectorgit clone --depth 1 https://github.com/neuratechcompany-ops/kettu-marketplace-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/neuratechcompany-ops/kettu-marketplace-mcp/dns-connector)<a href="https://agentmods.dev/skills/neuratechcompany-ops/kettu-marketplace-mcp/dns-connector"><img src="https://agentmods.dev/badge/skills/neuratechcompany-ops/kettu-marketplace-mcp/dns-connector/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/neuratechcompany-ops/kettu-marketplace-mcp/dns-connector"><img src="https://agentmods.dev/badge/skills/neuratechcompany-ops/kettu-marketplace-mcp/dns-connector.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 | $0.00067 | $0.00726 |
| Opus 5.5 | $0.00027 | $0.00290 |
| Sonnet 5.5 | $0.00013 | $0.00145 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
dns-connector 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 1mo 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.
This is a copy
92% identical to dns-connector — 13 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DNS-Shop Connector
Reads DNS-Shop inside the operator's Chrome over CDP. Qrator's JavaScript proof-of-work answers every dynamic page with HTTP 401 + a challenge script — no header trick clears it, but a real Chrome executes it natively. The connector renders the page and reads the DOM.
When to use
- Search DNS electronics catalog by text
- One product's price, old price, availability
Tools available
dns_search(query)— tiles from the rendered search pagedns_card(product_url)— one card. The URL carries/product/<id>/, where the id is a 16-hex string:/product/b7a1667f9b19ed20/. A bare id also works.dns_selfcheck()— tri-state canary
A green selfcheck does NOT mean the data is right
This connector is why that sentence appears throughout this repo. In July 2026
the product-id regex was fixed, search began returning 24 links, and
dns_selfcheck went green — while every item still came back with
title: null and price: null. The transport was fine; the parser understood
nothing.
dns_selfcheck answers one question: did the page load and did the extractor
return a shape. If a number has to be trusted, open the product page in the same
Chrome and read it.
The price on a DNS tile is not the smallest number on it
Three traps, all confirmed against the live grid on 2026-07-28:
- An instalment sits next to the price. A tile showing
58 999 ₽also showsот 5 751 ₽/ мес.. Anything that takes the minimum reports the monthly payment — a number that validates, looks plausible and is wrong. The extractor reads the named price node and skips instalment and bonus nodes. - The strikethrough price carries no currency glyph —
.product-buy__prevrenders a bare54 999, so a filter keyed on₽never sees it. - The first product anchor in a tile is the image link, which has no text.
Tiles are selected by the exact BEM block
.catalog-product, never by walking up from an anchor.
price_rub is None when no price could be read — never 0, never a guess. If
a whole page comes back unpriced the response carries a no_prices_on_page
warning: that is drift to investigate, not "free".
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.
- 1mo ago First seen · 60 lines · 67 tokens per session scan A 8a153e3ec729
dns-connector is a skill published in the GitHub repository neuratechcompany-ops/kettu-marketplace-mcp (5 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 726 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 92% identical to dns-connector, differing in 13 lines, and is treated as a copy.
Other skills, from other repositories
alibaba-supplier-outreach
Codex-native supplier sourcing and outreach workflow for Alibaba using LaunchFast research. Use when the user wants supplier shortlists, outreach messages, reply triage, or negotiation support. Requires supplierresearch. Browser automation is optional but useful when the user wants Codex to interact with Alibaba…
snaplii-autopilot
End-to-end Agent-to-Merchant autopilot: buy a Snaplii gift card with cashback, then drive the browser to redeem it on the merchant/delivery site and place the order — all in one flow. Use when the user wants the agent to actually complete a purchase or food/delivery order (e.g. 'order me a coffee on Uber Eats and pay…
ebay-search-listing
Extracts product listings from any eBay search or category page URL, returning per-item cards (itemNumber, url, title, subtitle, caption, price, priceWithCurrency, currency, wasPrice, bids, shipping, seller, sellerFeedbackCount, sellerPositiveRating, reviewsCount, starRating, image) plus pagination state (currentPage…
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…
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…
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…