refactor-functions

A procedure for reorganizing commercetools API functions in the agent-essentials package.

In plain words
What is it for?
Use it when moving namespace functions into base, customer, store, or other scope files while implementing read, create, and update operations.
Why use it?
It sets boundaries for the refactor and encourages reusable base functions, reducing duplicated API logic and helping updates use the current entity version.

Cursor rule for Cursor

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.

agentmods
npx agentmods add rules/commercetools/mcp-essentials/refactor-functions
Clone the repo
git clone --depth 1 https://github.com/commercetools/mcp-essentials

Made for: Cursor.

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,247 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00016 $0.01247
Opus 5 $0.00008 $0.00624
Sonnet 5 $0.00003 $0.00249
Haiku 4.5 $0.00002 $0.00125

Measured 2d ago against content hash e3d75804b506, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

refactor-functions 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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/rules/refactor-functions.mdc · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refactoring a tool Function in @commercetools/agent-essentials

This document outlines the steps taken to refactor a function in @commercetools/agent-essentials to connect to commercetools API.

The following steps are defining implementation of an example cart.read. So the (namespace) here refers to cart.

NOTES:

1. CRUD functions are read, update and create. do not add delete functions.
2. DO NOT MODIFY `parameters.ts` or `prompts.ts` or `tools.ts`
3. when creating update base functions, use get (by id or key) base functions to first fetch the entity, and use the version from the fetched entity in the update payload

Refactor steps

  1. Create a base.functions.ts file in the namespace directory. This file will export a couple of basic CRUD functions that will be used inside other files in this namespace. you can extract this base functions from current functions.ts file in the namespace.

    • IMPORTANT: base functions should be generic as possible, e.g. instead of having a separate function for query cart for a specific user and another one for user in a store, we create one that accepts a "where" cluase.
    • Note: sometimes the commercetools SDK has different endpoint when a parameter is present, like query in store (look to the code sample below). in that case, we check that parameter inside the base function but keep the function as simple as possible and low complexity.
    • GOAL: the goal of this step is maximize reusability.
    • example: base functions created for 'cart.read' are: readCartById, readCartByKey, queryCart, queryCarts.
    • file example: typescript/src/shared/cart/base.functions.ts
    • code sample:
    const queryCart = async (
        apiRoot: ApiRoot,
        projectKey: string,
        queryArgs: any,
        storeKey?: string
        ) => {
        if (storeKey) {
            const carts = await apiRoot
            .withProjectKey({projectKey})
            .inStoreKeyWithStoreKeyValue({storeKey})
            .carts()
            .get({queryArgs})
            .execute();
            return carts.body;
        }
        const carts = await apiRoot
            .withProjectKey({projectKey})
            .carts()
            .get({queryArgs})
            .execute();
        return carts.body;
        };
    

Read the full file on GitHub · 109 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. 2d ago First seen · 109 lines · 16 tokens per session scan A e3d75804b506

Subscribe to this mod's changes

refactor-functions is a cursor rule published in the GitHub repository commercetools/mcp-essentials (13 stars, last pushed 15d ago), licensed MIT. It adds 16 tokens to every session and 1,247 once invoked, about $0.0001 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 2026-08-30.