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 rules/brahim-benzarti/shopify_store-mcp/code-patternsgit clone --depth 1 https://github.com/Brahim-Benzarti/Shopify_store-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/rules/brahim-benzarti/shopify_store-mcp/code-patterns)<a href="https://agentmods.dev/rules/brahim-benzarti/shopify_store-mcp/code-patterns"><img src="https://agentmods.dev/badge/rules/brahim-benzarti/shopify_store-mcp/code-patterns.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 | $0.00960 | $0.00960 |
| Opus 5 | $0.00480 | $0.00480 |
| Sonnet 5 | $0.00192 | $0.00192 |
| Haiku 4.5 | $0.00096 | $0.00096 |
Grade A, and why
code-patterns 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 3d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Patterns & Conventions
TypeScript
- ES Modules — Use
.jsextension in imports (TypeScript compiles to ESM) - Strict mode — All types must be explicit, no
any - Const assertions — Use
as constfor literal types
// Good
import { foo } from "./foo.js";
// Bad
import { foo } from "./foo";
Console Output
CRITICAL: Never use console.log — STDIO transport uses stdout for MCP protocol.
// Good — stderr for logging
console.error("[shopify-store-mcp] Starting...");
// Bad — breaks MCP protocol
console.log("Starting...");
Error Handling
Use utilities from errors.ts:
import {
formatSuccessResponse,
formatErrorResponse,
formatGraphQLErrors,
formatUserErrors,
normalizeGid,
} from "../errors.js";
// In tool handler
try {
const response = await client.request(query, { variables });
if (response.errors) {
return formatGraphQLErrors(response);
}
// Check for userErrors in mutations
const userErrors = response.data?.someOperation?.userErrors;
if (userErrors?.length) {
return formatUserErrors(userErrors);
}
return formatSuccessResponse(response.data);
} catch (error) {
return formatErrorResponse(error);
}
GraphQL Queries
All queries use #graphql tag for IDE support:
export const GET_PRODUCTS = `#graphql
query GetProducts($first: Int!) {
products(first: $first) {
edges {
node {
id
title
}
}
}
}
`;
Organize in:
src/graphql/admin/common/— Frequently used queriessrc/graphql/admin/specialized/— Complex/specific queries- Export all from
src/graphql/admin/index.ts
Tool Registration
import { z } from "zod";
import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
server.registerTool(
"tool_name",
{
title: "Human-Readable Title",
description: "What this tool does, when to use it, what it returns.",
inputSchema: {
param: z.string().describe("Parameter description"),
optional: z.number().optional().describe("Optional param"),
},
annotations: {
readOnlyHint: true, // Doesn't modify state
destructiveHint: false, // No permanent side effects
idempotentHint: true, // Safe to retry
openWorldHint: false, // Limited domain
},
},
async ({ param, optional }) => {
// Implementation
}
);
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.
- 3d ago First seen · 181 lines · 960 tokens per session scan A 54a9169efe2d
code-patterns is a cursor rule published in the GitHub repository Brahim-Benzarti/Shopify_store-MCP (3 stars, last pushed 6mo ago), licensed ISC. It adds 960 tokens to every session, about $0.0048 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 cursor rules, from other repositories
docs
All documentation files use MDX format with a specific structure.
development-conventions
Development conventions, code style, and best practices for the Kaneo project.
ts
Cursor rule "ts" from un-pany/v3-admin-vite, covering ts 开发规范, 类型, 命名, 代码组织 and 错误处理.
bundling
The project uses a custom type bundling system to provide full TypeScript IntelliSense support in the Monaco editor for @bubblelab/bubble-core and its dependencies. This is necessary because Monaco cannot directly resolve workspace packages or external dependencies.
typescript-patterns
TypeScript patterns for code organization, classes, types, and symbols as it relates to this project.
ts-inspect
Use ts-inspect for exact TypeScript semantic type information (parameters, return types, properties, signatures, definitions, type at a location) instead of reading many source files or guessing from call sites.