Hello, my name is
AI adoption and engineering. I look at the whole product, not only the code.
Latest post ·
Reading a skill is the cheap part. The work it drives is where the tokens and the time go - every search, file read, retry and wrong turn the agent takes along the way. A good skill makes that work predictable: fewer wrong turns, and the same result tomorrow as today.
This article walks through how I plan and write skills, with a release-notes skill as the running example, and how to test them with tools like skillgrade.
12 min read · Updated
Featured series · 3 parts
A practical, tool-agnostic guide to engineering with AI coding agents.
Coding agents run shell commands with your user's privileges, whether it's Claude Code, Codex, or an open-source harness like OpenCode running against your own models. Their own guardrails have come a long way, but a prompt injection hidden in an open-source package can still turn the agent against your machine. Agents belong in a sandbox, especially when you run a swarm of them.
7 min read ·
Coding agents forget everything between sessions, and the bigger the codebase grows, the more they have to rediscover before they can do anything useful.
6 min read ·
Reading a skill is the cheap part. The work it drives is where the tokens and the time go - every search, file read, retry and wrong turn the agent takes along the way. A good skill makes that work predictable: fewer wrong turns, and the same result tomorrow as today.
12 min read ·
Writing · 8 posts since Dec 2025
Mental notes
Reading · 12 books
Hover a book to see what it isTap a book to see what it is · 12 books, 7 topics
