More rules should mean better output. That's the intuition. I spent weeks building a comprehensive CLAUDE.md — 200 lines covering naming conventions, security rules, error handling, architectural patterns, import ordering, type safety requirements, and more. I was proud of it. I'd thought through every scenario. Then I scored the output. 79.0 / 100. My carefully crafted documentation was actively
The problem: too many clients, too few discovery hooks We expose Supabase Edge Functions as MCP (Model Context Protocol) servers. The clients that hit them are heterogeneous — Claude Desktop, Codex CLI, Cursor, VS Code Continue, a couple of in-house browser extensions. None of them ship with a hard-coded "use WorkOS AuthKit, scope is tool:ai_chat, audience must contain urn:jibun:tool:<tool>" rec
Have you ever looked at code you wrote six months ago and thought: "Who wrote this monster?"? Relax, it happens to all of us. In software engineering, writing code that a machine understands is the easy part. The real challenge is writing code that other humans (including your future self) can understand, maintain, and scale. This is exactly where Software Design Principles come into play. In this
A Fully Native, Dependency‑Free Web5 Case Study TL;DR: This case study demonstrates how the Ascoos OS Kernel 1.0.0 performs OAuth2 authentication, event‑driven processing, torrent file creation, and secure P2P upload using raw sockets — all without frameworks, external libraries, or middleware. 🔗 Full source code: https://github.com/ascoos/oauth2-torrent-upload Modern decentralized systems
Part 1 of 5 in The New Engineering Contract — what it means to lead engineers when AI is doing more of the coding. SWE-CI tested 18 AI models across 71 consecutive commits. Most broke something on commit 47 they'd already broken on commit 1. That's not an intelligence problem. That's a learning system that isn't learning. A paper made me uncomfortable this month. Not because of what it found about