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 agentmods add skills/msapps-mobile/claude-plugins/shopify-mcpnpx skills add MSApps-Mobile/claude-plugins --skill shopify-mcpgit clone --depth 1 https://github.com/MSApps-Mobile/claude-pluginsWrote 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/msapps-mobile/claude-plugins/shopify-mcp)<a href="https://agentmods.dev/skills/msapps-mobile/claude-plugins/shopify-mcp"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/shopify-mcp.svg" alt="Measured on agentmods" 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 | $0.00133 | $0.01220 |
| Opus 5 | $0.00067 | $0.00610 |
| Sonnet 5 | $0.00027 | $0.00244 |
| Haiku 4.5 | $0.00013 | $0.00122 |
Grade A, and why
shopify-mcp 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 5d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shopify MCP — multi-tenant storefront operator
Use this skill whenever Claude needs to act on a Shopify store through the
opsagent-shopify MCP server. Prefer these tools over raw fetch calls or
the generic apify-scraping skill — they are tokened, rate-aware, and
multi-tenant.
When to trigger
- "What's in
<client-handle>'s catalog right now?" - "Find products in shop X under $50 that contain 'linen'."
- "Build me a cart with three of variant ID ..."
- "Read the shipping policy of
foo.myshopify.com." - "Describe the storefront of this shop before we swap the theme."
- "Why is
selectModel()returning undefined on the product page of<shop>?" → callshopify_describe_themefirst to confirm which theme + version is live before diving into theme JS.
Mental model
One install, every store. Each tool takes an optional shop argument of
the form <handle>.myshopify.com. If omitted, the server falls back to
SHOPIFY_DEFAULT_SHOP (set per-client in the MCP config). Never hardcode a
shop inside the skill — pass it explicitly when the user mentions one.
Two backends, one surface:
- Public catalog + cart ops go to Shopify's Storefront MCP endpoint
(
https://{shop}/api/mcp). No token. Tools:shopify_search_products,shopify_get_cart,shopify_update_cart. - Richer read ops (products by handle, policies, collections, shop metadata)
go to Storefront GraphQL. Needs
SHOPIFY_STOREFRONT_TOKEN.
If a GraphQL tool errors with "Storefront GraphQL requires a token," surface that to the user and ask them to paste one into the plugin config — don't silently degrade.
Plan → Act → Verify
- Plan — Identify the shop and the intent (read vs cart-mutation vs checkout-mutation). Read ops are cheap; cart mutations should be confirmed with the user if the cart is real (not a throwaway test cart).
- Act — Call the narrowest tool. Prefer
shopify_search_productsover pulling the whole catalog. Prefershopify_get_productfor detail pages. - Verify — For cart mutations, re-fetch with
shopify_get_cartand show the resulting line items. For checkout starts, return the URL and tell the user what will happen if they open it.
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.
- 5d ago First seen · 102 lines · 133 tokens per session scan A 637cd63c75ea
shopify-mcp is a skill published in the GitHub repository MSApps-Mobile/claude-plugins (9 stars, last pushed 9d ago), licensed MIT. It adds 133 tokens to every session and 1,220 once invoked, about $0.0007 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
cs-channel-message
NCM 프레임워크(Need→Channel→Moment→Message→CTA)로 검색·광고·CRM·앱 푸시 채널별 메시지를 자동 생성하는 단일 채널 메시지 엔진입니다 — 채널 분기 메시지 15종 + 채널별 운영 카피(광고·톡톡·푸시·이메일) + 앱 푸시 기획(4원칙·3요소·변형 3안)을 한 곳에서 처리합니다. 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: "채널별 메시지 만들어줘", "검색광고 카피 15종", "CRM 메시지 뽑아줘", "스마트스토어 배너 카피", "쿠팡 광고 문구", "카카오 알림톡 문구", "SNS 광고 카피 5종", "광고 헤드라인…
commerce-detail-page-copy
이커머스 고전환 상세페이지를 위한 카피 생성 전문 스킬입니다. 3가지 모드를 지원합니다.
commerce-detail-page-planner
한국 이커머스 상세페이지의 기획안(원 메시지·오프닝 유형·본문 뼈대·유통 채널 전략·사진 체크리스트)을 만들어 드립니다. 카피·코드·이미지를 만들기 전, 무엇을 어떤 구조와 톤으로 보여줄지 먼저 확정하는 단계입니다. 다음과 같은 요청 시 사용하세요: "상세페이지 기획해줘" "상세페이지 구조 짜줘" "이 제품 원 메시지 잡아줘" "와디즈 펀딩 상세페이지 전략 세워줘" "스마트스토어 상세페이지 사진 체크리스트 만들어줘" "화장품 상세페이지 어떻게 구성할지 기획해줘" 완성한 기획안은 moai-seller:commerce-detail-page-copy(카피) →…
commerce-ad-claim-compliance-kr
한국 셀러가 상세페이지·광고 소재·리스팅·SNS 광고에 사용할 카피를 발행하기 전, 표시광고법·식약처 규정·전자상거래법 3개 축으로 표현의 적법성을 점검하는 사전 게이트 스킬입니다.
commerce-automation-audit
이커머스 셀러가 자기 매장의 운영 자동화 가능성을 자체 진단하고 우선순위·로드맵을 자동 생성하는 컨설팅용 스킬.
commerce-integrated-strategy
선행 스킬 산출물(commerce-market-research·commerce-jtbd-persona·commerce-product-naming·cs-channel-message·commerce-detail-page-copy 결과)과 매장 운영 데이터를 종합해 매출 향상 통합 전략 1장 + 실행 우선순위 Top 3을 자동 생성하고, 채널 믹스·가격·프로모션 캘린더·리텐션·KPI까지 단계별(런칭/성장/안정)로 설계합니다. 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: "오늘 배운 것 종합 전략으로 정리해줘", "통합 전략 뽑아줘", "실행 우선순위 정해줘"…