Noos - Where Thought, Code, and Craft Converge

Tokuin v0.2.0 is here with the feature I promised: rule-based, structure-aware prompt compression. Here's how it works and why you might actually use it.

Notes from implementing RLS in a multi-tenant setup—what worked, what surprised me, and what I'd do differently.

Breaking down GitHub's 2026 pricing changes for Actions—what's free, what's changing, and what it means for your projects.

A proposal-style exploration of a rule-based, structure-aware prompt compression engine for Tokuin—and a call for expert feedback.

A look at Tokuin, a ground-up token analysis and load-testing CLI for LLM prompts, why it exists, what it offers today, and where it's headed next.