Writing

Blog

Agentic development, developer tooling, and what I'm learning along the way.

Seventeen comments

An agent built working backend code. Review pushed it into the right domain boundaries.

agentic-ai claude-code developer-tooling · 8 min read

CLAUDE.md as project constitution

Our AGENTS.md hit 700 lines. I audited it and about half was stuff the model already knows.

agentic-ai claude-code developer-tooling · 6 min read

Composing over reimplementing: how I structure Claude Code skills

I run a personal copy of every skill in my dotfiles and a team copy in the repo. This is how that works.

agentic-ai claude-code developer-tooling · 7 min read

Ship-it: a Claude Code skill for the last mile

Lints, tests, code review, PR, ticket update. I automated the end-of-ticket sequence so I stop forgetting steps.

agentic-ai claude-code developer-tooling · 6 min read

Five revisions of start-ticket: how a Claude Code skill learned to start work

I kept missing steps when picking up tickets. Five revisions later the skill handles it.

agentic-ai claude-code developer-tooling · 9 min read

Building a knowledge vault that costs zero LLM tokens at retrieval

I kept losing context between Claude Code sessions. Decisions, patterns, gotchas, all gone next morning. So I built a vault.

agentic-ai memento-vault architecture · 7 min read

The programming atrophy problem: AI makes you worse at coding

Three studies say AI tools make you worse at coding. I use them every day so I wanted to know how bad it actually is.

agentic-ai developer-tooling research · 6 min read

Harness engineering: the model is just the horse

Same model, same benchmark, 36-point score difference just from the setup around it. Most of my engineering work now is on that environment, not the prompts.

agentic-ai harness-engineering developer-tooling · 7 min read

Hello

Who I am, what I'm working on, why I started writing.

personal · 1 min read