Skip to main content
← /writing

topic · 14 essays

Claude Code

Claude Code is Anthropic's coding agent, and I've used it every day for more than a year. These essays are field notes from that use on my own apps. They cover what I configured, what it cost, what broke, and what I'd tell a team adopting it.

The main lesson is that discipline doesn't scale and automation does. For the first few months I wrote careful prompts and pasted in style guides, and it worked until I got distracted. Things improved when I stopped writing instructions and started writing enforcement. That meant hooks that run checks, subagents that review, commands for the rituals, and a denylist for what must never happen.

The same pattern holds at larger scale. A refined spec, a layer of standards, and specialist agents beat one long conversation. Agent teams are a more expensive coordination pattern, so they have to earn their cost. In one morning a tech lead agent and its team produced 64 pull requests across three of my apps. A bug I merged past showed where my own judgment still fell short.

The costs are worth knowing before you scale it. Over 26 days I ran $2,556 of API-priced work on a $200 subscription, which says as much about current pricing as it does about the tool. I built a small CLI to keep that ledger automatically. Permissions deserve the same attention as prompts. I treat them as safety equipment, and I keep a lessons file so the next session starts with what the last one got wrong.

Little of this is specific to one vendor. I've run the same workflow across Claude Code, Codex, Goose, Pi, and OpenCode to check that the engineering system survives a change of agent. Start with the essays below.

start here · 8 essays

The essays to read first

  1. 01
    Claude Code Is a Build System, Not a Chatbot
    18 min read

    Six principles from 13 months of daily use, from shared standards to permissions.

  2. 02
    Spec, Standards, Specialists: How I Actually Build with AI
    25 min read

    The working loop up close: one refined spec, house standards, and a bench of specialist agents.

  3. 03
    From Copy-Paste to Skill: What Thousands of AI Coding Sessions Taught Me About Guardrails
    10 min read

    Lessons from thousands of AI coding sessions, distilled into a reusable skill of guardrails.

  4. 04
    The Agent Team Tax: When AI Agents Need to Argue
    16 min read

    When agent teams earn their cost, and when they are just expensive subagents.

  5. 05
    64 PRs Before Lunch
    15 min read

    A tech lead agent, 64 merged PRs across three apps in one morning, and the bug I merged past.

  6. 06
    The Subsidy, Itemized
    10 min read

    What 26 days of usage cost at API prices, and what the gap buys.

  7. 07
    The Instrument and the Ledger
    8 min read

    The hand-built usage ledger becomes an afternoon of tooling, built by the thing it measures.

  8. 08
    Eleven Years, One Week, and an AI Co-Pilot: Rebuilding TravelTimes for iOS 26.4
    13 min read

    Six major features on a decade-old codebase in one week, and where the AI got it wrong.

go deeper

the full list · 14 essays

Every essay on this topic

Agentic SDLC

I Gave the Agents the Merge Button

The lead agent coordinated a weekend of changes across three GSD apps. Shared credentials and incomplete checks showed why every merge needs the same evidence, including mine.

13 min read · 2.5k words
★
Agentic SDLC

64 PRs Before Lunch

I merged 64 agent-built PRs across three apps in one morning. The kickoff carried my judgment into the work. A bug I merged past showed me where that judgment still fell short.

15 min read · 2.8k words
★
AI Economics

The Instrument and the Ledger

In June I itemized the AI subsidy by hand. This month I built the instrument that does it for me. It took an afternoon, and it was built by the very thing it measures.

8 min read · 1.6k words
★
AI Economics

The Subsidy, Itemized

Twenty-six days of Claude Code showed $2,556 of API-priced work against a $200 subscription. The lesson was not the total. It was cache behavior, model routing, and a government kill switch that landed in my usage chart. Value lives in verified outcomes, not tokens, and the work has to survive the stop.

10 min read · 2.0k words
★
AI Coding

Claude Code Is a Build System, Not a Chatbot

After thirteen months of daily Claude Code use, I stopped treating AI coding as a prompt discipline problem and started treating it like an engineering system: configurable, layered, observable, and built to learn.

18 min read · 3.6k words
GenAI

They're Using Claude to Ship Claude (And It Shows)

Anthropic has shipped more meaningful product features in the last few weeks than most teams ship in a quarter. A theory, and what it tells us about what AI-assisted development actually unlocks when a team uses their own product to build it.

6 min read · 1.1k words