Developer Experience in the AI Era — Helping Engineers Stay Competitive

While teaching a Claude workshop, an engineer in the room asked me: how do you think about improving Developer Experience (DevEx) in the AI era? I answered on the spot. This post revisits that as a fully remote CTO. What DevEx used to mean, what AI changed, how leadership provides the environment. The goal: growing engineers who stay competitive in the market, the kind people call excellent even after they move on.

Shortened URLs should not be used for internal sharing - they're full of disadvantages

Why shortened URLs are a poor fit for internal sharing — opacity, redirects, unsearchable, and shutdown risk.

Refactor an existing product fast with Claude Fable 5 and GPT-5.6 Sol first

The previous post's lesson was one I wrote after paying for it. I turned Loop Engineering on for an existing product, and two weeks in, debt really had piled up at ten times the usual speed underneath gates that kept passing. This post is about that regret and the human-driven, high-throughput refactor I went back to run instead, with Claude Fable 5 planning and GPT-5.6 Sol implementing, both on their light settings.

Cutting CI Costs in AI-Driven Solo Development with gh-signoff — Local CI and the Signoff Model

Hand implementation to a coding agent and your push count explodes, quietly inflating the remote CI bill. gh-signoff offers a blunt but sensible answer: run the tests on your own machine and sign off on them yourself.

I Missed a More Popular Same-Name OSS, So I Renamed Mine to hermes-talaria

I later realized my OSS oh-my-hermes shared a name with a repository sitting at about 1.3k stars. It was just confusing, so I renamed mine to hermes-talaria and flipped the extension namespace prefix from omh- to ht- along the way. Since I am currently the only user, the breaking change is fine. For the new name I checked GitHub search first.

Hand It an Issue, Get Back a PR — A Hermes Agent Skill Looping Between Codex and Claude Code

When agents write the code, the highest-value human work is neither writing nor reviewing it. It is building the foundation the loop runs on, and planning the issue. Shipping this skill made that conclusion concrete.

Dropping Loop Engineering onto an existing product piles up technical debt at high speed — rebuild the verification substrate with refactoring first

The previous post argued that a solopreneur-style new product is where Loop Engineering just works. The inverse is that an existing product is where it just does not. Worse, if you turn it on before the verification substrate is real, technical debt piles up underneath gates that keep passing. This post is about the refactoring you have to do first to avoid that.

Loop Engineering works best for solopreneur-style new products — when you built it from scratch and hold the whole design

Loop Engineering is not universal; it works cleanly in some repositories and grinds in others. The dividing line is who owns the spec, whether the verification substrate is real, and whether the merge decision closes back to the same person who wrote the issue. A solopreneur-style new product is one of the few settings where all three line up, which is why the design of Loop Engineering pays off there the most.

macOS Monterey 12.4 System Preferences Memo [May 2022 version]

A personal, section-by-section memo of my macOS Monterey 12.4 System Preferences setup on a new MacBook Pro.

Reviewing a PR with Claude Code and Codex at Once — Automating Multi-Model Review as a Hermes Agent Skill

A code review from a single model inherits that model's blind spots wholesale. So have independent models read the same diff, and trust the findings where they overlap. Here is how that workflow became a single command.

Tabs or Spaces: Considering Indentation from an Accessibility Perspective

An issue attempting to change indentation to spaces led me to reconsider the importance of tabs from an accessibility perspective.