I Tried to Catch Coding Agents Cheating. They Mostly Didn't.
I built cheatguard, a linter that blocks the shortcuts coding agents take to make checks pass. Then I ran 798 agent runs to prove it works. Not one cheated.
#claude-code
Posts
Who Made This Decision?
We built in two months a product that would have taken a year. When we reviewed it, a small change touched 80 files. The AI didn't write bad code: it made design decisions nobody reviewed.
I Audited a Claude Code Plugin That Reads All Your Browser Cookies
A security review of millionco/expect — a Claude Code plugin that runs AI-driven browser tests via Playwright. The skill is safe. The CLI decrypts every cookie in your browser.
Everyone's Sharing Claude Code Skills. Nobody's Checking What's Inside.
The skills ecosystem is growing fast. A recent study found malicious payloads in 13% of published skills. Here's what that looks like in practice and what you can do about it.
Claude Code Loves Worktrees. Your Infrastructure Doesn't.
Claude Code's instinct to parallelize with worktrees is powerful — until your project has Docker Compose, env secrets, and 5 services fighting for the same port.
Scaling Vibe Coding: A Framework for Teams Using Claude Code
Vibe coding works great solo as is. But what happens when your team grows exponentially?
Essays
Models Don't Have Scar Tissue
For the first time in my career, I feel like this craft is in danger. And at the same time, every day working with agents tells me it isn't. An attempt to hold both thoughts at once.
Notes
Have you faced issues already scaling up your vibe coding team? I have, and here are some learnings I’d like to share. #VibeCoding #ClaudeAI #BestPractices #buildinpublic