shopify-app

shopify-app is a skill for Claude Code from mentilead/shopify-app-skill. It costs 52 tokens per session (2,353 once invoked), scanned A, original, MIT.

A development skill containing implementation patterns for embedded Shopify apps. It covers Shopify’s interface components, GraphQL API, billing, webhooks, App Proxy pages, and AWS services such as DynamoDB, Lambda, SQS, and CDK.

In plain words
What is it for?
Use it when creating Shopify app pages, API calls, billing flows, webhooks, proxy pages, data storage, or serverless infrastructure.
Why use it?
It helps an agent follow established patterns for common Shopify app tasks and avoid known integration mistakes, such as navigation breaking inside Shopify’s embedded frame.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the shopify-app-skill plugin — 1 skill, 10 commands shipped together

Good fit Use it when creating Shopify app pages, API calls, billing flows, webhooks, proxy pages, data storage, or serverless infrastructure.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mentilead/shopify-app-skill/shopify-app
Install

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.

Any agent
npx skills add mentilead/shopify-app-skill --skill shopify-app
Clone the repo
git clone --depth 1 https://github.com/mentilead/shopify-app-skill

Made for: Claude Code.

Or install shopify-app-skill, the plugin that ships this one along with the rest of its 1 skill, 10 commands.

Wrote 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.

agentmods badge for shopify-app

README.md
[![agentmods](https://agentmods.dev/badge/skills/mentilead/shopify-app-skill/shopify-app.svg)](https://agentmods.dev/skills/mentilead/shopify-app-skill/shopify-app)
Your own site
<a href="https://agentmods.dev/skills/mentilead/shopify-app-skill/shopify-app"><img src="https://agentmods.dev/badge/skills/mentilead/shopify-app-skill/shopify-app.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,353 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.02353
Opus 5 $0.00026 $0.01177
Sonnet 5 $0.00010 $0.00471
Haiku 4.5 $0.00005 $0.00235

Measured 8d ago against content hash 5078020fd316, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

shopify-app 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 8d 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.

skills/shopify-app/SKILL.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRITICAL GOTCHAS (Top 10)

1. Never Use Polaris url Prop for Internal Navigation

// WRONG — breaks out of iframe
<Button url="/app/pricing">Upgrade</Button>

// CORRECT — stays in iframe
const navigate = useNavigate();
<Button onClick={() => navigate('/app/pricing')}>Upgrade</Button>

Rule: url prop is only safe for external URLs. Use useNavigate() for internal routes.

2. Never Use NODE_ENV for Billing isTest Flag

// WRONG — always false on Lambda (staging included)
isTest: process.env.NODE_ENV !== 'production'

// CORRECT — detect via Shopify API
isTest: await isDevelopmentStore(admin)

3. useFetcher Data Goes to fetcher.data, Not useActionData()

// WRONG — always undefined when using fetcher
const actionData = useActionData<typeof action>();

// CORRECT — read from fetcher
const fetcher = useFetcher();
const fetcherData = fetcher.data as { ok?: boolean; error?: string } | undefined;

4. useState Doesn't Sync with Loader After Save

// WRONG — state diverges from loader after save
const [brandColor, setBrandColor] = useState(settings.brandColor);

// CORRECT — sync from loader when data changes
const lastSyncRef = useRef(settings.updatedAt);
useEffect(() => {
  if (settings.updatedAt !== lastSyncRef.current) {
    setBrandColor(settings.brandColor);
    lastSyncRef.current = settings.updatedAt;
  }
}, [settings.updatedAt, settings.brandColor]);

5. Parent + Child Loaders Run in Parallel (Billing Race Condition)

// CORRECT — redirect after billing sync to force clean second load
const url = new URL(request.url);
if (url.searchParams.has('charge_id')) {
  url.searchParams.delete('charge_id');
  throw redirect(url.pathname + url.search);
}

6. App Proxy: GET Only, No External CSS/JS

Constraint Detail
GET only Proxy only forwards GET. POST must go directly to the app URL.
No external CSS/JS <link> and <script src> resolve against storefront domain and 404.
No Tailwind ?inline Tailwind 4's Vite plugin doesn't process @tailwind for ?inline imports.
No client-side hydration React Router JS bundles don't load through the proxy.

Read the full file on GitHub · 272 lines

Changes

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.

  1. 8d ago First seen · 272 lines · 52 tokens per session scan A 5078020fd316

Subscribe to this mod's changes

shopify-app is a skill published in the GitHub repository mentilead/shopify-app-skill (5 stars, last pushed 6mo ago), licensed MIT. It adds 52 tokens to every session and 2,353 once invoked, about $0.0003 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.

Related

Other skills, from other repositories