Towards the Dark Factory: The Agent Sets the Pace
Self-paced agents on one Mac: slots for Swift builds and simulators, ledgers that survive a crash, detached gates, and one night hour by hour.
Read more
Towards the Dark Factory: The Wall
The validation layer for agent-written Swift: 100% coverage, a mutation runner that fails the build, plans replayed byte for byte, and one holdout rule.
Read more
Towards the Dark Factory: Level 2 to Level 3 in a Week
An iPhone app in Swift, a language we had never shipped, built by Claude Code agents: the contract file, worktrees, adversarial specs, and week one in numbers.
Read more
Linting the Prompt Layer
We wrote our conventions in CLAUDE.md, then said prose doesn't fail a build. So we turned the prose into a skill with executable gates, pointed a linter at the skill, and open-sourced the result. Here's what the linter caught — including three broken images on this very site.
Read more
Architecture Tests as a Seatbelt Against Agentic Drift
When a tireless AI agent makes a hundred plausible-looking changes, what stops the architecture from quietly eroding? We wired ArchUnit into the CrushLog backend as an executable seatbelt — and the rules found bugs a human audit missed.
Read more
140 Pull Requests in a Week: Orchestrating Claude Code Agents at a Hackathon
Lessons from a hackathon that capped off a months-long service renovation with massive AI assistance — how to run Claude Code agents in parallel, the keyboard shortcuts that keep you sane, what survives a reload, and a status line that keeps you oriented.
Read more
How We Use Claude Code Skills to Codify Our Development Patterns
A practical guide to teaching your AI coding assistant your codebase conventions using Claude Code Skills — reusable Markdown templates that prevent repeated code review corrections.
Read more