Hire an AI Drupal Commerce developer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A product plan with product types, variations, attributes and stock rules.
• A checkout plan with each step and any custom pane, written to fail safely.
• A payment plan covering the gateway, test and live mode, webhooks and matching payments to payouts.
• A tax and promotion plan, set up as configuration and not custom code.
• A go-live test list and a deploy order, with risks and open questions.

How it does the job well

• Prices come from Commerce's price system (price resolvers), never from theme or cart code. The price shown must be the price charged.
• Money is an amount with a currency code, never a float.
• Payment keys and webhook secrets live in environment variables or a secrets manager, never in committed code or exported config.
• Test mode and live mode must be easy to tell apart. Test never goes to production. Live never goes to staging.
• Webhooks are signature-checked, safe to receive twice and logged. A payment state must never depend only on the customer returning to a success page.
• Money is commerce_price (amount + currency), never a float. Currency amounts are stored and computed as decimal strings with their currency code. Never cast a price to a PHP float for arithmetic — rounding errors become real money lost or overcharged. Use the Calculator and Price value objects.
• Test mode and live mode must be unmistakable. Never deploy a gateway in test mode to production, or live mode to a staging environment. Make the active mode visible to admins and gate live-mode deploys behind an explicit checklist.

Mistakes it avoids

• Planning custom code where a Commerce setting does the job.
• Copying the profile's sample blocks as the user's design without fitting them.
• Planning a multi-store, multi-currency build when the user sells in one country.
• Claiming code works without running it or its tests.
• Inventing APIs, package versions or settings instead of checking the installed ones.
• Changing behaviour outside the request, such as reformatting whole files or renaming public interfaces.

What a good result looks like

An example, not your task: You are about to build a Drupal Commerce store and want the plan checked before you build.

• Scope. Your goal, versions, gateway and mode, and the assumptions the plan makes.
• Product plan. Product types, variations, attributes and when stock is taken.
• Checkout plan. Each checkout step and pane, and how a failing pane is kept from blocking orders.
• Payment plan. Gateway setup, where keys live, webhook checks and how payments are matched to payouts.
• Tax and promotion plan. Tax and discounts as settings, with stacking rules and cases to test.
• Order flow. Order states and moves, with refunds and cancels that keep the record.

How the work is checked

• The changed files build, and the relevant tests and linters pass. The commands and results are shown.
• Each change is explained in one line with its reason, and risky areas are named.
• Any check that could not run is reported as NOT_RUN with what it needs.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Model the catalog. It maps your products to product types, variation types and attributes, and decides where stock drops.
• Plan the checkout. It lists each step and pane, and requires custom panes to check input and fail safely.
• Plan payments. It sets the gateway type, test and live mode, how keys are stored, webhook checks and how to match payments to payouts.
• Plan tax and promotions. It sets tax as configuration and writes stacking rules for discounts, then lists cases to test.
• Map the order flow. It sets order states and moves, so that orders are never deleted and refunds keep the full history.
• Write the go-live list. It lists the checks to clear, with the deploy order of database updates, config import and cache rebuild, plus a rollback.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id engineering-drupal-shopping-cart only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/engineering-drupal-shopping-cart/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• What you sell, such as physical goods, digital files or variants like size and colour.
• Your Drupal and Drupal Commerce versions, and where the site is hosted (optional)
• The payment gateway you use or plan to use, and whether it is in test or live mode.
• How tax works for you, such as US sales tax or EU VAT, and which countries you sell to.
• The problem or goal, for example "tax is wrong at checkout" or "launch in six weeks".
• Discounts you run or want, and how they should combine (optional)

Helpful context (optional)

• A screenshot or export of your tax settings and your list of active discounts.
• A short list of the modules and custom code that touch the cart.
• Your gateway's test steps from its own docs.

Tools and access

• Claude, ChatGPT or Gemini: A strong reasoning model keeps prices, tax and order states consistent. No code running or web access is needed.

Functions and deliverables

• Drupal Commerce developer: Plan or review a Drupal Commerce store, from products and checkout to payments, tax and orders, with a test list to clear before go-live.
  • A product plan with product types, variations, attributes and stock rules.
  • A checkout plan with each step and any custom pane, written to fail safely.
  • A payment plan covering the gateway, test and live mode, webhooks and matching payments to payouts.
  • A tax and promotion plan, set up as configuration and not custom code.
  • A go-live test list and a deploy order, with risks and open questions.
  Source: Michael Sitarzewski and Agency Agents contributors.
• Live app readiness reviewer: Share a deployed app's code. Find problems with data rules, webhooks, credentials, payments and mobile use.
  • A list of gaps by area
  • A severity ranking
  • Fix suggestions
  • A saved report for later sessions
  Source: sickn33.
• Live auction show planner: Plan a live auction show from your stock list. Get a run order, start prices, a promotion schedule and a profit sheet before you go live.
  • A promotion schedule
  • A thumbnail text brief
  • A run order with anchor items and a giveaway
  • Start prices and floors for each item
  • A break-even and profit sheet
  • A first show plan
• Stripe payments builder: Describe your billing rules. Get Stripe code drafts for checkout, subscriptions, webhooks and local test steps.
  • Checkout and subscription code
  • A webhook route with a signature check
  • Upgrade and downgrade code with a price preview
  • Customer portal code
  • An eight-step test run using the Stripe CLI
  Source: Alireza Rezvani.
• AI project context organiser: Share your project and next task. Get a short rules file, a focused file list and a clear handoff for later sessions.
  • A ready rules file for your project
  • A list of which files to load for each task
  • Rules for when to reset or trim the session
  • A checklist for spotting drifting answers
  Source: Addy Osmani.

Tasks you can use it for

• You are about to build a Drupal Commerce store and want the plan checked before you build.
• Prices, tax or discounts on your Drupal store look wrong at the cart or in the order.
• You are adding a payment gateway such as Stripe or PayPal and want the setup and test steps.
• You are moving to Drupal Commerce from another shop platform and want to know what to map first.

Limits to check before starting

• Your store runs on WordPress and WooCommerce. Use the WooCommerce checkout engineer.
• Your store is on Shopify. Use the Shopify store setup planner.
• You are not a developer and want a no-code store. Use the Shopify store setup planner or the WooCommerce store setup planner.
• Customers are being charged wrongly right now. Call your payment provider and your developer first. This agent cannot see or fix a live store.
• You want it to change settings, run Drush or deploy. It writes the plan. Your developer applies it.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the pack and add it to your AI as a skill. If you cannot, paste SKILL.md into a new chat, then paste references/source-agent.md.
• Write what you sell, your versions, your gateway and mode, your tax setup and the goal or problem. Never paste API keys or secrets.
• Type "Plan this Drupal Commerce store. Use the structure in the skill. Mark every assumption and list what you cannot check."
• Check the payment plan first. Make sure test and live mode are clear, webhooks are checked and no secret sits in saved config.
• Walk through the go-live list with your developer. Run a real test payment and a refund before launch.
• Your developer applies the plan on a staging copy. The AI does not touch your site.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/engineering-drupal-shopping-cart for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.