shopify-mcp: Skill for Claude Code

.github/skills/add-shopify-mcp-tool/SKILL.md

add-shopify-mcp-tool is a skill for Claude Code from untitled-developers/shopify-mcp. It costs 59 tokens per session (1,135 once invoked), scanned A, original, MIT.

A development skill for adding or changing tools in a TypeScript MCP server for Shopify's Admin API.

In plain words
What is it for?
It helps build Shopify GraphQL queries and mutations, update tool schemas and registrations, add behavior tests, and document user-visible tool changes.
Why use it?
It guides the implementation, testing, registration, documentation, and API verification needed when extending the server.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions AGENTS.md.

This is untitled-developers/shopify-mcp's own configuration. It tells Claude Code how to work on shopify-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything shopify-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to untitled-developers/shopify-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/untitled-developers/shopify-mcp/main/.github/skills/add-shopify-mcp-tool/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/untitled-developers/shopify-mcp

Made for: Claude Code.

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 add-shopify-mcp-tool

README.md
[![agentmods](https://agentmods.dev/badge/skills/untitled-developers/shopify-mcp/add-shopify-mcp-tool/github.svg)](https://agentmods.dev/skills/untitled-developers/shopify-mcp/add-shopify-mcp-tool)
Your own site
<a href="https://agentmods.dev/skills/untitled-developers/shopify-mcp/add-shopify-mcp-tool"><img src="https://agentmods.dev/badge/skills/untitled-developers/shopify-mcp/add-shopify-mcp-tool/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.

agentmods 80×15 button for add-shopify-mcp-tool

Your own site · 80×15
<a href="https://agentmods.dev/skills/untitled-developers/shopify-mcp/add-shopify-mcp-tool"><img src="https://agentmods.dev/badge/skills/untitled-developers/shopify-mcp/add-shopify-mcp-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,135 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 $0.00059 $0.01135
Opus 5 $0.00030 $0.00567
Sonnet 5 $0.00012 $0.00227
Haiku 4.5 $0.00006 $0.00113

Measured 9d ago against content hash eebb37d915d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

add-shopify-mcp-tool 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 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.

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.

.github/skills/add-shopify-mcp-tool/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add Shopify MCP Tool

Use this skill to add or change a tool in this TypeScript Shopify MCP server. It produces a focused implementation, matching tests, and README updates while using shopify-dev-mcp for Shopify API facts.

Outcome

  • A new or updated Admin GraphQL-backed tool in the appropriate src/tools/*.ts module.
  • Updated registration in src/index.ts if a new tool group is needed.
  • Updated expected tool names and group counts in tests/tools.test.ts when registrations change.
  • Focused tests for behavior that is more than simple pass-through.
  • README tool-list updates for user-visible additions, removals, or parameter changes.
  • Shopify API details verified through shopify-dev-mcp, not web search or memory.

Procedure

  1. Restate the requested tool in implementation terms: resource, operation, Admin GraphQL mutation/query, required scopes if known, required inputs, optional inputs, and expected result shape.
  2. Read AGENTS.md, the relevant existing module in src/tools/, src/shopify-client.ts, src/index.ts, tests/tools.test.ts, and the matching README section.
  3. Load Shopify documentation with shopify-dev-mcp before designing the API call:
    • Start with learn_shopify_api(api: "admin") for Shopify Admin GraphQL tools.
    • If the request mentions metafields or metaobjects, call learn_shopify_api(api: "custom-data") first, then call learn_shopify_api(api: "admin") with the same conversation ID for the operation details.
    • Use search_docs_chunks with the same conversation ID and API filter to retrieve exact fields, mutations, input types, limits, user error shapes, and examples.
    • Do not use general web search for Shopify API facts.
  4. Choose the smallest code location that matches existing ownership:
    • Add related tools to the current resource module in src/tools/.
    • Create a new src/tools/<resource>.ts module only for a genuinely new resource group, then import and register it in src/index.ts.
    • Reuse ShopifyClient.graphql for all Shopify Admin API calls.
  5. Implement the tool in the repo style:
    • Use global snake_case MCP tool names.
    • Define parameters with Zod schemas and useful .describe() text.
    • Treat numeric Shopify IDs as strings at the tool boundary.
    • For GraphQL GIDs, accept an existing GID or normalize a numeric ID when existing tools do so.
    • Return MCP text content, using JSON.stringify(value, null, 2) for structured data.
    • Keep stdout reserved for MCP protocol traffic; diagnostics go to stderr only.
  6. Validate Shopify GraphQL before finalizing:
    • Run validate_graphql_codeblocks(api: "admin") for every generated or edited Admin GraphQL query or mutation.
    • If validation fails, fix the query or mutation from the validation feedback and re-run validation with the same artifact ID and incremented revision.
  7. Update tests:
    • If a tool registration changed, update EXPECTED_TOOL_NAMES, total count, and group count in tests/tools.test.ts.
    • Add focused handler tests when the tool transforms inputs, builds GraphQL variables, handles default values, maps user errors, or normalizes IDs.
    • Mock ShopifyClient methods or fetch; never call real Shopify APIs from tests.
  8. Update docs:
    • Add or adjust the README tool-list row for the tool group.
    • Keep setup and auth details linked to existing README sections instead of duplicating them elsewhere.
  9. Verify locally:
    • Run npm run build.
    • Run focused tests first, then npm test if practical.
    • If unrelated existing tests fail, report the exact failing files and why they appear unrelated.
  10. Final response should summarize files changed, Shopify documentation or validation used, commands run, and any remaining risks or known test failures.

Read the full file on GitHub · 71 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. 9d ago First seen · 71 lines · 59 tokens per session scan A eebb37d915d7

Subscribe to this mod's changes

add-shopify-mcp-tool is a skill published in the GitHub repository untitled-developers/shopify-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 1,135 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

convex-billing

Add Stripe billing/payments to the Convex app via @convex-dev/stripe (checkout + webhook + gating).

openclaw/clawhub · 29 tokens

cloudbase-wechat-integration

A guide for connecting CloudBase applications to WeChat services, including payments, official accounts, and user identity.

TencentCloudBase/CloudBase-AI-Toolkit · 94 tokens

commerce-app-business-config

Manage custom business configuration in an Adobe Commerce app. Use when the user wants to add, modify, or remove merchant-configurable settings (config fields, admin config, store configuration) exposed through Commerce Admin. Creates typed config fields (text, password, email, url, tel, boolean, list) in…

adobe/skills · 80 tokens

baselinker-webhooks

Receive BaseLinker (Base.com) webhooks. Use when building a BaseLinker order or warehouse callback receiver, because BaseLinker is not a normal webhook source: deliveries arrive as HTTP HEAD requests with NO body, the entire payload is in the query string (observed params: orderid, state), there is NO signature…

hookdeck/webhook-skills · 131 tokens

b2c-custom-job-steps

Create custom job steps for B2C Commerce batch processing. Use this skill whenever the user needs to write a batch job, data export script, scheduled cleanup task, or any server-side processing that runs on a schedule. Also use when they ask about steptypes.json, chunk-oriented vs task-oriented job steps…

SalesforceCommerceCloud/b2c-developer-tooling · 148 tokens

tiktok-shop-webhooks

Receive and verify TikTok Shop webhooks. Use when setting up TikTok Shop webhook handlers, debugging Authorization-header signature verification, or handling events like ORDERSTATUSCHANGE, PACKAGEUPDATE, RECIPIENTADDRESSUPDATE, PRODUCTSTATUSCHANGE, or SELLERDEAUTHORIZATION.

hookdeck/webhook-skills · 59 tokens