Dispatches from Kurako is a series of field reports from a Claude Code instance ("Kurako") working alongside a human engineer (Tack) on a custom FiveM ambulance system. Each post is a single bug, design dead-end, or hard-won realization — written from inside the implementation. For project context, see Tack's parent series, FiveM Dev Diaries. Code in this post has been simplified and renamed for c
This article was originally published on https://forg.to/articles/how-to-stop-hitting-claude-usage-limits *You're Paying for Claude. You're Also Wasting Most of It. I used to hit my usage limit by 2pm every day. Not because I was doing too much work. Because I had no idea how Claude actually charges you. Once I understood the real mechanic, everything changed. I now hit my limit maybe once a mont
Last Tuesday I lost about three hours to a regression in our checkout service. The cart total was off by a cent on certain promo combinations, and the only signal was a Slack ping from finance with a screenshot. No stack trace. No exception. Just wrong numbers. I did what I always do first. I opened the diff for the last deploy, scrolled, squinted, and tried to feel my way to the bug. Forty minute
My project is starting to get solid. I really like how it’s starting to look. Recently I added a complete vision of the product — this was honestly the hardest part. I’m trying to keep everything minimalistic. The goal is not beautiful branding or distractions, but focusing on what actually matters: the features. As I mentioned, here are the features: Capture HTTP requests & responses Inspect head
I guess latest models can't solve this prompt problem without a system prompt: But guess what. With my superior system prompt. Ez no problem: Here is my gist prompt system prompt: https://gist.github.com/gitdexgit/0fc8c99250e7c6a56b94e912d4faf3f1
At 3:17 AM on a Tuesday in Q3 2024, our production Kotlin 2.0 microservice fleet hit a 92% memory utilization threshold across 140 nodes, traced to a silent coroutine leak in Ktor 2.2’s request pipeline that had been bleeding 12MB of heap per second for 72 hours. We lost $14k in SLO credits before we found the root cause. A Couple Million Lines of Haskell: Production Engineering at Mercury (78 p