My Agentic Coding Setup, July 2026 | Domenic Denicola

Since breaking free of my corporate shackles, I’ve gotten to experiment with a variety of approaches to AI-assisted development. After months of tinkering, I’m quite happy with my current setup, and want to capture and share it.

Things are changing very fast, and I have no illusions that this will be a timeless nugget of wisdom. But talking to some friends and scrolling through X posts, it does seem that I might have some techniques in play that are not widespread. At least, this will be a fond time capsule to look back on as we proceed further into the singularity. And the end state is quite nice: I’ve ended up with the ability to have frontier models fix production bugs from my phone, on a train.

My requirements

After a couple of months with raw Claude Code, it became clear what I was missing:

The agents need to be running on Linux. Agentic coding is essentially impossible on Windows, as the agents are heavily trained on Bash and other Unix tools. Although some pretend to have PowerShell support, they invariably trip over themselves on quoting issues, UTF-8 support gaps, etc.

I want to be able to work from either my desktop or laptop, with seamless handoff of project progress, including preserving agent sessions, working tree state, and gitignored files (like .env files or build artifacts).

I want the work to continue even if I close my laptop to transition locations.

I want various user-global settings (e.g., AGENTS.md, skills, harness configurations) to be available no matter where I work, and backed up and version-controlled.

I want to be able to review the agents’ current work in Visual Studio Code, not just in their harness UI or as part of a GitHub pull request checkpoint.

I want the agents to be able to stand up development servers reflecting their current work for me to poke at. These servers, in some cases, need to be secure contexts, i.e., https: or http://localhost. Ideally, only I should be able to access them.

I want to be able to run multiple parallel workstreams on the same project, without the agents stepping on each other’s toes.

I want approval interruptions minimized, ideally all the way to --dangerously-skip-permissions / --yolo modes, so that I can run parallel workstreams and step away from the computer. (Spoiler: this means a disposable VM.)

None of these requirements are that hard, and several of them synergize. It’s just a matter of finding and stitching together all the right tools, with a minimum of fuss. I’ll outline my setup below, although not as a step-by-step guide. Since you have agents now, you can ask them to do the fiddly parts.

The key ingredients

Summary : The biggest unlocks are using Tailscale and a dedicated Linux VM running on my always-on home desktop. If you combine this with various features of the ChatGPT desktop app (formerly known as Codex), you’ve basically got it. Some extra goodies come from using Portless and chezmoi.

The whole setup, as diagrammed by Claude Fable 5.

The VM and Tailscale

First, we need a disposable Linux VM. You could use a cloud-hosted one, but I keep my desktop running all the time anyway, so I just set one up using an Ubuntu Server ISO. Give it a good chunk of RAM and disk space, and be sure to enable nested virtualization support, as we want agents to be able to spin up their own containers or VMs as necessary.

(You might think that Ubuntu Server could be limiting, compared to Ubuntu Desktop, since without a GUI, you couldn’t log in to websites or take screenshots of work under development. This has not proven to be a problem for me in practice, as agents are perfectly capable of installing and using tools like Playwright or Xvfb when you ask them to perform tasks that need such things.)

At first, the VM is a bit annoying to access. We want to be able to SSH into it, both to streamline initial setup and as part of our grand plan. This is where Tailscale comes in.

Tailscale is a wonderful piece of software which I had not known about until this adventure. It ties together all of your machines—in my case, my desktop, my laptop, and my Linux VM—into a private network, where they can access each other by hostname over SSH, HTTP(S), etc. So even if I’m out at a coffee shop on some random Wi-Fi, I can run ssh agents-base and I’ll be inside my VM, working with my agents. Or I can access https://agents-base.tail234567.ts.net:8443/ to check out the web server my agent has spun up for me. And since SSH is the foundational technology for various other parts of our stack, such as the agentic harnesses themselves and VS Code, Tailscale’s “magic SSH across the internet” makes everything else just work.

(Also, it’s free! They have a neat article explaining why it stays free.)

So immediately after setting up the VM, install Tailscale on it and on all your other machines. Then you can SSH in and set up your dev environment by installing the usual tools. Or, install Claude...