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 finsilabs/awesome-ecommerce-skills --skill magento-graphqlgit clone --depth 1 https://github.com/finsilabs/awesome-ecommerce-skillsWrote 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/finsilabs/awesome-ecommerce-skills/magento-graphql)<a href="https://agentmods.dev/skills/finsilabs/awesome-ecommerce-skills/magento-graphql"><img src="https://agentmods.dev/badge/skills/finsilabs/awesome-ecommerce-skills/magento-graphql/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/finsilabs/awesome-ecommerce-skills/magento-graphql"><img src="https://agentmods.dev/badge/skills/finsilabs/awesome-ecommerce-skills/magento-graphql.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 | $0.00033 | $0.03362 |
| Opus 5 | $0.00016 | $0.01681 |
| Sonnet 5 | $0.00007 | $0.00672 |
| Haiku 4.5 | $0.00003 | $0.00336 |
Grade A, and why
magento-graphql 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.
How it starts
The opening of the file, as written. The whole thing — 441 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Magento GraphQL API
Overview
Magento 2 (and Adobe Commerce) ships a comprehensive GraphQL API for storefront operations — product catalog, search, cart, checkout, customer authentication, and order history. The endpoint is /graphql and does not require an admin token for public catalog data. Cart and customer operations require a guest cart ID (UUID) or a Bearer token from customer login. PWA Studio (Venia) is built entirely on this API, making it the reference implementation for headless Magento.
When to Use This Skill
- When building a React, Vue, or Next.js headless storefront on Magento 2
- When creating a native mobile app that needs Magento product and checkout data
- When implementing PWA Studio extensions that fetch custom data via GraphQL resolvers
- When replacing REST API calls with more efficient GraphQL queries in existing headless projects
- When building a custom GraphQL resolver to expose third-party or custom module data
- When integrating a headless CMS with Magento's product catalog
Core Instructions
-
Set up the GraphQL client
Magento GraphQL uses standard HTTP POST to
/graphql. Use Apollo Client or a lightweight fetch wrapper:// lib/magento.ts const MAGENTO_URL = process.env.NEXT_PUBLIC_MAGENTO_URL; // e.g. https://magento.example.com export async function magentoQuery<T>( query: string, variables: Record<string, unknown> = {}, token?: string ): Promise<T> { const headers: Record<string, string> = { "Content-Type": "application/json", Store: process.env.NEXT_PUBLIC_MAGENTO_STORE_CODE ?? "default", }; if (token) { headers["Authorization"] = `Bearer ${token}`; } const response = await fetch(`${MAGENTO_URL}/graphql`, { method: "POST", headers, body: JSON.stringify({ query, variables }), next: { revalidate: 300 }, // Next.js ISR caching }); if (!response.ok) { throw new Error(`Magento GraphQL HTTP error: ${response.status}`); } const { data, errors } = await response.json(); if (errors?.length) { throw new Error(errors[0].message); } return data as T; }
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/cart-lifecycle-and-customer-authenticati/criteria.json 2.8 KB
- evals/cart-lifecycle-and-customer-authenticati/task.md 1.6 KB
- evals/graphql-client-setup-and-auth-security/criteria.json 2.8 KB
- evals/graphql-client-setup-and-auth-security/task.md 1.7 KB
- evals/product-catalog-queries-with-polymorphic/criteria.json 2.8 KB
- evals/product-catalog-queries-with-polymorphic/task.md 1.7 KB
- tile.json 211 B
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.
- 8d ago First seen · 441 lines · 33 tokens per session scan A 6506cad0f02f
magento-graphql is a skill published in the GitHub repository finsilabs/awesome-ecommerce-skills (52 stars, last pushed 6mo ago), licensed MIT. It adds 33 tokens to every session and 3,362 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
vendure-cli
Use the Vendure CLI (vendure) to scaffold, run, build, migrate and maintain a Vendure ecommerce project. Use whenever working inside a Vendure project that needs a dev server, a production build, database migrations, plugin/entity/service scaffolding, GraphQL schema generation, diagnostic checks, or codemods.
radix-to-base-ui-migration
Migrates Vendure Dashboard extensions from Radix UI patterns to Base UI patterns (@vendure-io/ui).
vendure-dashboard-migration
Migrates Vendure Admin UI extensions (legacy Angular-based) to the new React Dashboard.
shopline-oauth
SHOPLINE app authorization and request signing. Use when implementing OAuth 2.0 authorization (public/custom apps), exchanging codes for access tokens, refreshing tokens, signing GET/POST requests with HMAC-SHA256, or verifying SHOPLINE webhook/callback signatures.
shopline-graphql
SHOPLINE Admin GraphQL and Storefront GraphQL APIs. Use when designing or generating GraphQL queries/mutations for SHOPLINE (Admin or Storefront), working with global IDs (gid://shopline/...), or validating GraphQL code against the SHOPLINE schema.
shopline-webhook
SHOPLINE webhooks. Use when building webhook subscriptions, webhook endpoints (ack, retry, idempotency), verifying webhook signatures (X-Shopline-Hmac-Sha256), or debugging missed/duplicated events.