Chat on WhatsApp
  • Sign In
  • Create an Account
Toggle Nav
My Cart
Account
The Claude Code setup guide

Claude Code, end-to-end.

Install in 60 seconds. Configure with CLAUDE.md. Ship slash-commands, MCP servers, hooks, and sub-agents. The complete 2026 setup playbook for Anthropic’s official Claude CLI — from a fresh laptop to production-grade AI-paired delivery.

  • Install to first PR in 5 minutes
  • 100+ production-tested slash-commands shipped
  • MCP-ready · Sub-agents · Hooks · Privacy-first
Book a setup workshop See the 5-step setup
Adobe Certified Magento + Hyvä Developer Trained 60+ teams on Claude Code
  • 5 min Install to first PR

    One npm i -g @anthropic-ai/claude-code, one CLAUDE.md, and Claude Code is reading your repo. Your first AI-paired commit lands in under five minutes.

  • 100+ Slash-commands shipped

    Production-tested slash-commands for Magento, Hyvä, setup-patches, MFTF, db_schema, indexers — copy them into .claude/commands/ and ship.

  • MCP Server-ready

    Connect Claude to GitHub, Linear, Sentry, Postgres, your Magento DB — via the Model Context Protocol. No bespoke glue code, no leaky API keys in your prompt.

  • Sub-agents + hooks supported

    Run audit, build, and test in parallel sub-agents. Block rm -rf and force-pushes with hooks. Production-grade safety on day one.

What Claude Code gives you

Six features every developer should know about

Claude Code isn’t a chat window with a code-export button. It’s a CLI that reads your repo, edits files, runs your tests, and ships PRs end-to-end. Here’s what makes it different.

  • Install in 60 seconds

    A single npm i -g @anthropic-ai/claude-code installs the CLI globally. Run claude in any repo to start a session — no daemon, no IDE plugin, no system service. Authenticate once with your Anthropic API key or Claude Pro/Team account.

  • CLAUDE.md project rules — write once, AI follows forever

    Drop a CLAUDE.md at your repo root with your project conventions: PSR-12, no vendor edits, plugin-over-rewrite, db_schema not raw SQL, MFTF tests required. Claude Code re-reads it every session — your rules become muscle memory for the AI.

  • Slash-commands for repeated workflows

    Drop reusable prompts as Markdown files in .claude/commands/. We ship /scaffold-module, /setup-patch, /test-coverage, /db-schema-add-column, /hyva-port-block — the AI runs them with one keystroke each.

  • MCP servers connect Claude to your stack

    The Model Context Protocol lets Claude Code talk to GitHub, Linear, Sentry, Postgres, your Magento DB, even your design system — via standardised servers. No bespoke API integration code, no API keys leaked into prompts. Add a server, restart, done.

  • Hooks gate dangerous commands

    Pre-tool hooks block rm -rf, force-pushes, vendor-path writes, and prod credentials before Claude can run them. Post-tool hooks auto-run phpcs, phpstan, and composer validate after every file edit. Your safety net is built into the CLI, not bolted on.

  • Sub-agents parallelise long-running tasks

    Spawn parallel sub-agents for audit, build, and test — each with its own context window. Run a 30-minute Magento codebase audit while another agent ports a Luma block to Hyvä and a third writes MFTF tests — all in parallel, all reporting back to your main session.

How to set up

Five steps from a fresh laptop to a production AI workflow

Follow these in order. Steps 1–3 take under an hour. Steps 4–5 take a focused day. After that, you ship 3–5× faster forever.

  1. 01

    Install

    Run npm i -g @anthropic-ai/claude-code. Authenticate with claude login using your Anthropic API key or Claude Pro/Team subscription. Verify with claude --version.

    PT5M
  2. 02

    CLAUDE.md

    Create CLAUDE.md at your repo root with project rules: tech stack, coding standards, “never edit vendor”, test requirements, deploy flow. Claude Code re-reads it every session — this is your single source of AI truth.

    PT15M
  3. 03

    Slash-commands

    Drop reusable workflows as Markdown files in .claude/commands/. Start with /scaffold-module, /setup-patch, /test-coverage — one slash, one repeated job done in seconds.

    PT30M
  4. 04

    MCP + hooks

    Wire MCP servers (GitHub, Linear, Sentry, your DB) in .claude/mcp.json. Add pre-tool hooks to block rm -rf and vendor edits, post-tool hooks to auto-run linters. Production-grade safety in 30 minutes.

    PT30M
  5. 05

    Production workflow

    Adopt the daily loop: plan in chat, build with slash-commands, review on staging, commit through your hooks. Spawn sub-agents for parallel audit + build + test runs. You are now shipping 3–5× faster.

    PT1D
Setup & onboarding pricing

Get your team set up — faster than DIY

You can absolutely set up Claude Code yourself for free — the docs are good. We charge for speed, custom <code>CLAUDE.md</code>, and the 100+ slash-commands we’ve already battle-tested in production.

  • Setup Workshop

    $ 499 USD

    2-hour live setup · you and your team

    Best for: A solo developer or 2–3 person team that wants Claude Code installed, configured with CLAUDE.md, and shipping its first PR — in one live session.

    • Live screen-share setup — install to first PR in 2 hours
    • Custom CLAUDE.md for your stack (Magento, Hyvä, Laravel, Next.js)
    • Starter pack of 10 slash-commands tailored to your workflows
    • Hooks configured to block rm -rf, force-push, vendor edits
    • Recording + written runbook so you can re-onboard new devs
    • 14-day Slack support after the workshop
    Book workshop
  • Most popular

    Team Onboarding Sprint

    $ 1,999 USD

    1 week embedded · most popular

    Best for: A 4–15 person engineering team that wants Claude Code rolled out across the squad — with shared CLAUDE.md, slash-commands, MCP servers, and team training.

    • Everything in Setup Workshop, plus:
    • 5 days embedded with your team (async + 2 live sessions / day)
    • Repo audit + custom CLAUDE.md per service / monorepo path
    • 30+ slash-commands tailored to your team’s tickets
    • MCP servers wired: GitHub, Linear/Jira, Sentry, your DB
    • Sub-agent + parallel-task playbook for your release cadence
    • 60-day Slack support, monthly “new tricks” office hours
    Reserve sprint

  • Embedded AI Coach

    Custom

    Monthly retainer · ongoing AI coaching

    Best for: Engineering orgs (15+ devs) that want continuous Claude Code coaching — new slash-commands monthly, MCP integrations, sub-agent patterns, AI-paired code review on every PR.

    • Everything in Team Onboarding Sprint, plus:
    • Embedded into your engineering Slack / Teams
    • Monthly AI-workflow review — what’s working, what to drop
    • Custom MCP server builds for your internal tools
    • AI-paired code-review on team PRs (sample basis)
    • Quarterly “new Claude features” training
    • On-call support for AI workflow incidents
    Get retainer quote

Prices in USD. Quotes available in GBP / EUR / AUD / INR — ask in the booking form. Anthropic API costs (Claude Pro / Team / API) are billed directly by Anthropic and are not included in our setup fees.

Book your setup

Get Claude Code shipping in your team this week

Booking takes 2 minutes — we reply with a written setup plan + quote within 24 business hours.

We will get back to you shortly.

What teams say

Engineering teams already shipping faster with Claude Code

5-star average across Upwork, Clutch, and direct LinkedIn referrals. Real teams, real workflows.

great professional with enthusiasm, knowledge, skill and exceptional patience in solving problems.

“great professional with enthusiasm, knowledge, skill and exceptional patience in solving

D

Dennis

Bay Tech

Kishan works very hard, with a lot of knowledge about Magento 2.

“Kishan works very hard, with a lot of knowledge about Magento 2. He helped us getting our website to a new level. I would highly recommend Kishan and I'm giving Kishan 5 stars without any hesitation and look forward to working with him again on future

K

Kennard

Sporthuis

I had the pleasure of working with Kishan Savaliya on our Magento 2 project, and I was thoroughly impressed with his work.

“I had the pleasure of working with Kishan Savaliya on our Magento 2 project, and I was thoroughly impressed with his work. Kishan is not just a Magento developer, he is a true professional who sets a high standard with his top-notch technical skills. His task was to install a...

MA

Mohammed AL-Mayahi

Kishan is surely the best freelancer I worked with on upwork.

“Kishan is surely the best freelancer I worked with on upwork. Always there to use his knowledge to help and sort any issue you may have in a pleasant and professionnal

NC

Nicolas Chevillot

Ecofone

This freelancer is the best i've used at Magento.

“This freelancer is the best i've used at Magento. Absolutley brilliant at what they do. Would have no hesitation in recommending them

PS

Peter Stewart

CEO, No79 Design

Kishan has done an excellent job in a timely manner He is very knowledgeable, has a very positive attitude, easy to communicate.

“Kishan has done an excellent job in a timely manner He is very knowledgeable, has a very positive attitude, easy to communicate. All in all, the best you can ask for. Will definitely rehire when I have jobs to be

ZK

Zisos Katsiapis

Komputron Monoprosopi IKE

Specialty playbooks

You’ve got the general setup. Now go deeper into the workflow that matches your stack — each playbook ships with stack-specific <code>CLAUDE.md</code>, slash-commands, and MFTF / Tailwind / Figma patterns.

Setup workshops delivered for teams in

  • United States
  • United Kingdom
  • Canada
  • Australia
  • Germany
  • France
  • Netherlands
  • India
FAQ

Everything you wanted to know about Claude Code

What is Claude Code?

Claude Code is Anthropic’s official command-line interface for Claude. It’s a Node.js CLI you install with npm i -g @anthropic-ai/claude-code and run from your terminal inside any repo. Unlike the chat-window claude.ai, Claude Code reads your real source tree, edits files in place, runs your tests, executes shell commands you authorise, and ships PRs end-to-end. It’s designed to be an AI pair-programmer — you steer, Claude does the keystrokes. Built and maintained by Anthropic, the same company that makes Claude itself.

How is Claude Code different from Cursor, GitHub Copilot, or Aider?

Three key differences:

  • Vs. Copilot: Copilot is autocomplete-in-IDE. Claude Code is a CLI agent that plans, edits multiple files, runs tests, and commits PRs — not just inline suggestions.
  • Vs. Cursor: Cursor is an IDE (VS Code fork) with chat. Claude Code is editor-agnostic — works in your existing VS Code, JetBrains, Vim, or terminal. Same agent, no IDE lock-in.
  • Vs. Aider: Aider is similar in shape (CLI pair-programmer) but provider-neutral. Claude Code is Anthropic-native, so you get first-party access to Claude features (extended thinking, prompt caching, computer use, MCP) without a translation layer. Sub-agents and hooks are also first-party.

For Magento & Hyvä work specifically, Claude Code wins on: real codebase reads, MCP-database access, hook-gated safety, and the slash-command library.

What Claude models does Claude Code use?

By default, the latest production-tier Anthropic model — currently Claude Opus 4.7 for heavy coding tasks and Claude Sonnet 4.6 for fast routine work (May 2026). You can pin specific models with --model or set defaults in your .claude/config.json. Extended thinking mode kicks in automatically for complex tasks (architectural decisions, debugging). You can also route Claude Code via AWS Bedrock or GCP Vertex AI if your org requires cloud-vendor billing — the CLI picks up ANTHROPIC_BEDROCK_BASE_URL / ANTHROPIC_VERTEX_PROJECT_ID env vars.

How do I install Claude Code?

Three steps, ~60 seconds total:

  1. Install the CLI: npm i -g @anthropic-ai/claude-code (requires Node.js 18+).
  2. Authenticate: Run claude login — opens browser, signs in with your Anthropic account (Pro / Team / API). Or set ANTHROPIC_API_KEY env var if you’re using API direct.
  3. Run it: cd into any repo, type claude, ask your first question. That’s it.

For corporate setups behind a proxy, see the 5-step setup section above. For Magento-specific install + CLAUDE.md, see our Magento playbook.

What is a CLAUDE.md file and why does every project need one?

CLAUDE.md is a Markdown file at your repo root that holds your project rules — coding standards, “never edit vendor”, “always write MFTF tests”, deploy flow, naming conventions, links to internal docs. Claude Code re-reads it at the start of every session, so your team’s rules become muscle memory for the AI. Write once, AI follows forever.

A good Magento CLAUDE.md includes: tech stack (Magento 2.4.x + Hyvä), “no vendor edits”, “plugin-over-rewrite”, “db_schema not raw SQL”, “MFTF tests required”, deploy commands, and a list of internal modules with their purpose. Sub-folders can have their own CLAUDE.md files that compose with the root one — useful for monorepos.

Are slash-commands like Cursor’s @-mentions?

Different shape, similar goal. Cursor @-mentions reference files / docs / web pages inline in chat. Claude Code slash-commands are reusable prompt templates stored as Markdown files in .claude/commands/. When you type /scaffold-module, Claude Code injects the contents of .claude/commands/scaffold-module.md as your prompt — with optional argument substitution.

Slash-commands are repeatable workflows — you write the prompt once (“scaffold a Magento module with these conventions, db_schema, registration, MFTF test stub”), then any team member runs it with one keystroke. Claude Code also supports arguments ($ARGUMENTS placeholder) and file references (@path/to/file) inside command files, so you get the best of both worlds.

What are MCP servers and why should I use them?

The Model Context Protocol (MCP) is an open standard (open-sourced by Anthropic) for connecting AI assistants to external tools and data sources. An MCP server exposes a specific resource — GitHub, Linear, Sentry, your Postgres database, your Magento DB, your design system — through a standardised interface that Claude Code can call.

You wire MCP servers in .claude/mcp.json. Once wired, Claude Code can read your GitHub issues, query your Magento DB, fetch Sentry stack traces, file Linear tickets — all without you copy-pasting context into chat. Crucially, your API keys live in MCP server config, not in your prompts — so they don’t leak into your conversation logs. Anthropic + the community ship 100+ official MCP servers; building your own is a 50-line Node script.

What are hooks in Claude Code?

Hooks are shell scripts that run before or after Claude Code performs an action — editing a file, running a Bash command, finishing a tool call. They’re your safety net.

  • PreToolUse hooks can block dangerous actions: refuse to rm -rf /, refuse to push to main branch, refuse to write into vendor/, refuse to edit prod credentials. Hook returns non-zero exit, action is cancelled, you stay safe.
  • PostToolUse hooks auto-run lint / format / tests after every file edit. phpcs + phpstan + composer validate on every Magento file change — built into the CLI, not bolted on.
  • Stop hooks run when Claude finishes a session — great for auto-committing or running test suite.

Configure hooks in .claude/settings.json. They’re the difference between “cool AI demo” and “production-grade workflow.”

What are sub-agents and when should I spawn them?

Sub-agents are parallel Claude Code instances spawned by your main session, each with its own context window, working independently on a task you delegate. Useful when:

  • Parallel work: spawn three sub-agents to audit, build, and test in parallel — they each get a fresh context window, so a 30-min audit doesn’t blow your main session’s context.
  • Long-running tasks: a sub-agent can grind on “port these 80 Luma blocks to Hyvä” for an hour while you keep planning in your main session.
  • Specialised personas: a sub-agent with a stricter CLAUDE.md (e.g. “you are a security auditor; only output findings, never edit”) gives you focused output without polluting your main agent’s instructions.

Spawn with the Task tool. They report back to the main session when done — you get the summary, not the keystroke-by-keystroke noise.

How much does Claude Code cost — Claude Pro vs Team vs API?

Three billing options:

  • Claude Pro ($20/mo): unlimited Claude Code usage with model auto-routing. Best for solo devs — effectively flat-rate AI pair-programming.
  • Claude Team ($25/seat/mo, 5+ seats): Pro features + admin controls + shared workspace + SSO. Best for engineering teams.
  • Anthropic API (pay-per-token): $3/M input + $15/M output for Sonnet, $15/M + $75/M for Opus. With prompt caching enabled, repeated reads of vendor/ drop ~90% of input cost. Best for pipelined / CI / sub-agent-heavy workflows.

For most Magento dev work, Claude Pro flat rate is the right answer — you don’t want to think about per-token cost while shipping. For agentic / parallel sub-agent workflows, API with prompt caching is more economical.

Privacy — does Anthropic train models on my code?

No — not on commercial-tier inputs. Under Anthropic’s Commercial Terms of Service, customer inputs and outputs (Claude Pro, Claude Team, Anthropic API) are not used for model training. That’s contractual, not just a setting.

For zero-data-retention setups (regulated industries, NDA-heavy work), Anthropic supports a zero-data-retention mode on the API and Bedrock / Vertex routes — inputs aren’t logged at all past the live request. Free-tier claude.ai consumer use can opt-in to training (the consumer privacy notice differs), but Claude Code does not run on free-tier accounts. Net effect: your codebase stays in your VCS — nothing leaves except the API call you made.

What are the best Claude Code workflows for ecommerce dev?

Six workflows that compound massively in ecommerce dev:

  1. Setup-patch generation: a /setup-patch slash-command that scaffolds idempotent DataPatchInterface patches with dependency wiring — for seeding configs, products, categories, FAQs.
  2. db_schema → migration: describe the column you want, Claude Code writes db_schema.xml + db_schema_whitelist.json + a setup-patch for backfill.
  3. Hyvä port: a /hyva-port-block command that takes a Luma block and spits out the Hyvä equivalent with Tailwind classes + Alpine.js.
  4. MFTF + PHPUnit: features ship with tests in the same PR — non-negotiable in CLAUDE.md.
  5. Sub-agent audit: nightly sub-agent that audits your repo against Magento Coding Standard + EQP, files Linear tickets via MCP.
  6. SEO page builder: a slash-command that scaffolds a new Tier-1 pillar page (block + layout + template + LESS + 3 setup-patches) following your established pattern. (We use this exact one to ship our SEO landing pages.)

For the deep-dive, see our Magento playbook and Hyvä playbook.