The Mac setup, under the microscope.

The steps, re-examined

Each guide step made one choice for clarity. Here's the reasoning and the roads not taken.

The editor route — VS Code as your agent cockpit

The main guide is terminal-first because every agent ships its CLI first and best. But many people work better in a code editor with a file tree, inline diffs, and a chat pane on the side. Here is the honest, fully-detailed editor path on the Mac — install commands, which extensions actually help, what it gives you, what it costs, and when to pick it over (or alongside) the terminal.

• Homebrew (recommended): brew install --cask visual-studio-code — the same cask flow used elsewhere in the Mac guide.
• Or download the .zip from code.visualstudio.com and drag Visual Studio Code.app into /Applications.
• Privacy-conscious alternative: VSCodium (brew install --cask vscodium) — the same editor, MIT-licensed binary, no Microsoft telemetry. Most extensions work; the Microsoft Remote-* family is license-restricted to Microsoft's own VS Code build.
• Enable the code command in your shell: open VS Code → ⇧⌘P → "Shell Command: Install 'code' command in PATH". Then code . in any project folder opens it.

• Claude Code for VS Code (Anthropic, official) — a companion to the same Claude Code you installed in the terminal, with diffs applied straight into your open files and a chat pane that shares the CLI's session. The natural pick if Claude Code is already your driver.
• GitHub Copilot + Copilot Chat — autocomplete plus a chat panel that backs onto multiple models (Claude Sonnet 4.6, GPT-5.5, Gemini 2.5 — switchable per chat). Subscription: $10/mo individual, free for verified students and open-source maintainers.
• Cline (formerly Claude Dev) — agentic coding inside VS Code; bring your own key (Anthropic, OpenRouter, OpenAI, or a local Ollama endpoint). The closest in-editor analog to Claude Code's autonomous mode.
• Continue — open-source, bring-your-own-model, deeply configurable; the right pick if you want to point at a local Ollama model (where Apple Silicon's unified memory really shines) and stay off the cloud entirely.
• Codex VS Code extension (OpenAI, official) — if you're already paying for Codex or ChatGPT, this surfaces it inside the editor.
• Gemini Code Assist (Google, official) — Google's editor agent; generous free tier still available as of May 2026.

• Sign in once per extension. Each uses its own auth flow — prefer the browser login over pasting API keys (keys land in macOS Keychain rather than a plaintext file).
• Open a real project folder, not single files — every AI extension scopes context to the open workspace.
• Lock down what extensions can read. Add .env, .git, node_modules, .secrets/, and any private folders to files.exclude in .vscode/settings.json so extensions don't index them. Same hygiene as the CLI permissions in Part 5.
• Turn on Settings Sync (built-in, signed in with GitHub or Microsoft) so your extensions and settings follow you between machines.
• Remote-SSH — the killer feature on a Mac that talks to other boxes: install the official Remote Development extension pack, then "Connect to Host…" to your droplet or NAS. The editor lives on the Mac; the agent and files live on the remote box. Pairs especially well with the Linux droplet you already SSH into.

• You see diffs visually. When the agent says "I changed these 7 files," you see exactly what changed before accepting.
• One window for everything: file tree, terminal, git history, debugger, AI chat, and a marketplace of extensions for every language.
• Inline autocomplete — Copilot in particular — lowers friction on routine code in a way no CLI can. Half your typing finishes itself.
• Remote-SSH is genuinely a superpower. Edit code on the droplet or NAS from your Mac as if it were local, with the agent running on the remote box.
• Multi-cursor and structural refactors the agent doesn't bother with — large mechanical renames are still faster as a human editor move.
• Rich extension ecosystem — Markdown preview, REST client, mermaid diagrams, GitLens, every linter and language server. The AI extensions inherit all of it.

• It's heavier. 500 MB–1 GB RAM at idle before you even open a project. The terminal CLI is a few hundred KB. Modern Macs handle it fine; older ones with 8 GB will feel it.
• The extensions lag the CLIs. New agent features (Agent Teams, sub-agents, /goal workflows, auto mode) land in the CLI first and reach the extension weeks later. If you want the bleeding edge, the terminal wins.
• Telemetry, by default. Microsoft VS Code reports usage data; each AI extension reports its own. Switch to VSCodium and tighten telemetry.telemetryLevel if that matters.
• Extension supply-chain risk. A malicious extension can read every file in your workspace and send it anywhere. Stick to publisher-verified extensions with millions of installs; review what permissions each requests.
• Context bloat. An editor with fourteen extensions can make the AI slower and noisier — each one competes for context and CPU. Keep your extension list short.
• It's not designed AI-first. See next bullet — Cursor and Windsurf are VS Code forks that are. If you want the editor experience and aren't deep into VS Code already, those are arguably the better choice and have first-class agent integration baked in.

• Stay terminal-only if: you live in iTerm/Warp/tmux, you want every new agent feature the day it ships, the machine is RAM-tight, or you prefer composable Unix-style tools.
• Use VS Code if: you already use it for non-AI work, you want visual diffs, you do a lot of multi-file refactors, or you're working over Remote-SSH against a droplet or NAS.
• Use Cursor or Windsurf if: you want the editor experience and care most about how good the AI feels, not how broad the editor ecosystem is. Both have Mac casks (brew install --cask cursor / windsurf); both are full VS Code forks so your extensions mostly carry over.
• Use both: the common pattern — long agentic jobs in the terminal, small edits and code review in the editor, both pointed at the same project folder.

What we left out — and why

The guide is deliberately a clean six-step spine. That clarity has a cost: real omissions. Here they are, honestly, with the reason each was cut.

Trending & cool — tools worth a look

Scanning the developer conversation on X and GitHub in May 2026, here's what's hot that the guide doesn't yet mention. All run natively on the Mac, Apple Silicon especially.

Getting ready for Mythos

Mythos is Anthropic's first model specialized for one domain: defensive cybersecurity. Announced April 7 2026 as the engine of Project Glasswing, it has already found a 27-year-old vulnerability in OpenBSD and bugs in FFmpeg. It is invitation-only ($25 / $125 per million tokens), shipped to 12 founding orgs and 40+ critical-infrastructure partners — not a download. Full briefing →

So "getting ready" isn't an install — it's preparing your environment so that when domain-specialized models (Mythos and the wave behind it) open up, you can point them at something useful:

• Get on MCP now. Specialized models reach your code and infrastructure through MCP. A working MCP setup today is the plug Mythos-class tools will use tomorrow.
• Have your code in Git, reachable over Tailscale. A security model is only useful pointed at your systems. Repos in Git + machines on your tailnet = ready to analyze.
• Tighten your own security first (Part 5). The irony: you can't safely run a vulnerability-finding model on a sloppy machine. Hardening is the prerequisite, not the reward.
• Keep a clean Anthropic account & current Claude Code. Access to new models lands through the same account and tooling you already use.
• Watch Glasswing. If you run anything critical (a business, rentals, client sites), the initiative is where defensive tooling will surface first.

Securing the install — the part most guides skip

You're installing tools that can read your files, run commands, and reach the internet, plus a private network and a local model server. That's a lot of power. Here's how to keep it from biting you — Mac specifics first, then universal rules.

• Never paste API keys into files you might share or commit. Anthropic + GitHub run secret-scanning that auto-deactivates leaked Claude keys — helpful, but don't rely on it. Use the browser login flow (no key on disk) where you can.
• Store any keys in the macOS Keychain or environment variables, never in plaintext in a repo.
• Rotate a key the moment you suspect it leaked; give helpers their own keys, never yours.

• Block agent access to secrets. Configure Claude Code's permissions to deny reading .env files, SSH keys, .secrets, and certificates — and to not read its own config (which could be used to manipulate it).
• Start agents in ask-before-acting mode on a new machine; only loosen once you trust the workflow. Don't run "auto/yolo" modes in a folder full of irreplaceable files.
• Work inside a project folder, not your whole home directory — limit what the agent can even see.

• npm install -g and curl … | bash run other people's code. Only use the exact official sources in the guide; don't paste install one-liners from random blog posts or X replies.
• Homebrew formulae and casks are community-audited — prefer them over a raw download when offered.
• Keep everything updated (brew upgrade, npm update -g); most agent fixes ship fast.

• Ollama: setting OLLAMA_HOST=0.0.0.0:11434 exposes your model server to the network. Only do this behind Tailscale — never on a public IP or open Wi-Fi. There's no password on Ollama by default.
• Tailscale ACLs: in the admin console, restrict who can reach port 11434 and who can SSH where. Turn on key expiry so a lost device drops off. Tailscale's new Aperture (alpha) can even keep API keys off your devices entirely, behind your tailnet identity.

• Store secrets in the macOS Keychain, and turn on FileVault so your disk — keys and code at rest — is encrypted if the Mac is lost or stolen.
• Gatekeeper + notarization are your friends: don't carelessly override the "unidentified developer" warning to run unsigned apps. If you must, do it deliberately, not by reflex.
• Run daily work in a standard (non-admin) account; switch to an admin account only when installing.
• Review which apps can see your files, screen, and input under System Settings → Privacy & Security (the TCC permissions) — revoke anything you don't recognize.