Tech Notes to Self

Writer’s Brief The Hook I ran a code audit on my own personal task system and the reviewers all said the same thing: stop building. Main Points to Cover The meta loop problem - when your task system becomes the biggest consumer of its own output (32% of all tasks were about improving the task system) The “operating system” realization - capture, management, execution, output layers. You’re not building a to-do app. You’re building an OS. And that changes everything about when to stop. The freeze as the hardest feature - choosing to not build anything for a week when the system is exciting and growing fast The Angle Personal discovery. You build something, it works, it grows, and then the growth itself becomes the problem. The system that was supposed to help you ship things becomes the thing you ship. The audit catches it. The panel of imaginary experts all independently say “freeze it.” And you do. ...

Writer’s Brief The Hook In one morning session, applied to an accelerator (including porting a website to a new platform to meet the requirements), ran a full content strategy review across six dimensions, and built a client analytics dashboard. All while sitting in one chair. Main Points to Cover The speed thing is real but the interesting part isn’t speed, it’s what you do with the time you saved (you worry about your ego, obviously) None of it was hands-off. Every piece required real back-and-forth, real editing, real taste. The AI wrote an accelerator application and it was fine but it wasn’t good until Alex rewrote it. The punchline: this entire post is also a promo for the cohort, and that’s the most human thing about it The Angle Not “look how productive I am” but “this is genuinely disorienting and I’m processing it in real time.” The worry about usefulness. The ego thing. Then finding the edge in the weirdness. ...

Writer’s Brief The Hook When your tool doesn’t have a config option you need, sometimes you just read the binary. Main Points to Cover Using strings on a compiled Go binary to extract TOML/JSON struct tags and discover undocumented config fields The two-layer fix: global default via config.toml args field + bulk SQLite update for existing sessions The detective work - tracing from “Chrome mode” display string to use_chrome JSON field to discovering there’s no TOML equivalent, then finding toml:"args" as the backdoor The Angle You hit a wall with a tool you use daily. There’s no docs, no GitHub issue, no Stack Overflow answer. But the binary itself IS the documentation if you know how to read it. ...

Step-by-Step Tutorial What This Does Builds a local web app to review competitor Instagram posts with real images and engagement data. Swipe through posts, vote yes/no, see patterns in what you like. The Prompt I need to do visual competitive research for Stacks+Joules Instagram. Build me a review app where I can swipe through posts from these accounts and vote on which ones I like. What Claude Does Creates HTML/CSS/JS review app with swipeable cards Uses Apify to scrape Instagram profiles (avoids login walls) Downloads actual images locally Generates data file with engagement metrics Fixes various display bugs as they come up Example Results Before: Placeholder images, no real data After: 84 real Instagram posts with likes, comments, captions, and full images