
Pete Hodgson (@thepete.net on bluesky)
7.6K posts

Pete Hodgson (@thepete.net on bluesky)
@ph1
@thepete.net on bluesky Independent consultant helping engineering teams tackle thorny problems. Sociotechnical architect 🧐. Formerly Earnest, ThoughtWorks.








new blog post just dropped come get your excalidrawslop

@gregpr07 this may surprise you that thus is coming from me but I think we’re in for a 1-3 year period where stuff might break at 3am and if you’re relying on loops to fix it and nobody understands what’s under the hood, you’re looking at an existential threat to your company


@leo_trapani Yeah well that used to be called “agent” but the word “harness” was made necessary because the saas slop industrial complex broke our terminology by trying to call everything an “agent”




This 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱 file will make you 10x engineer 👇 It combines all the best practices shared by Claude Code creator: Boris Cherny (creator of Claude Code at Anthropic) shared on X internal best practices and workflows he and his team actually use with Claude Code daily. Someone turned those threads into a structured 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱 you can drop into any project. It includes: • Workflow orchestration • Subagent strategy • Self-improvement loop • Verification before done • Autonomous bug fixing • Core principles This is a compounding system. Every correction you make gets captured as a rule. Over time, Claude's mistake rate drops because it learns from your feedback. If you build with AI daily, this will save you a lot of time.








Important instruction for AI Coding agents writing tests: "Don't write tests for what the type system already guarantees." Helps hint against an entire class of shit tests.

you're writing a CLAUDE dot md? let me guess. "this project uses React with TypeScript." brother claude can see the tsconfig.json. you wrote 200 lines describing your file tree to an agent that can do `ls`. you explained that ~/projects/to-do-app is a todo app. the only lines that matter are the ones where your project is weird and you know it. "run yarn test:unit not npm test." "don't touch anything in src/legacy/ or three enterprise clients lose their minds." "the auth middleware is load-bearing, yes all of it, don't be a hero." that's it, that's the whole file. if claude would've figured it out from reading your code, you're wasting context window. start with nothing. wait for claude to do something wrong. tell claude to remember to not do that. that's your CLAUDE md.


tbqh the whole industry should realize it its just an argument of vim vs emacs use a top N harness+model, and then focus on how to use the technology vs pretending a fractional improvement to the model is going to unlock things for you









