(2025-11-26) Emanuel Im A Huge Fan Of Steve Yegges Great Beads Project

Jeffrey Emanuel: I'm a huge fan of Steve Yegge's great beads project, which is a task management system for use by coding AI agents. In fact, I probably type or paste the string "beads" 500+ times a day nowadays across all my coding agent sessions.

I'm usually having GPT-5 Pro make plans to my specifications and iterate on them a bunch of times, usually with help from Claude Opus 4.5, Grok 4.1, and Gemini 3. Then I tell codex or Claude Code to take the plan and turn it into beads for me. Or, as I usually say it in my pasted in blurb: "OK, so please take ALL of that and elaborate on it more and then create a comprehensive and granular set of beads for all this with tasks, subtasks, and dependency structure overlaid, with detailed comments so that the whole thing is totally self-contained and self-documenting (including relevant background, reasoning/justification, considerations, etc.-- anything we'd want our "future self" to know about the goals and intentions and thought process and how it serves the overarching goals of the project.)"

Anyway, this morning I wished I had a better way to just browse the beads and see what's going on with them. And sure, I get it, beads aren't for me as a human, they're for the agents.

Plus I had an idea that there was additional useful information lurking in the "graph" of beads of a sufficiently complex project comprising enough beads across various epics with lots of dependency structure on top.

So I started making beads_viewer (bv for short) this morning while I worked on 5 other projects concurrently, and I'm pleased to say that it's already pretty amazingly polished, full-featured, and useful.

And as a tool for use with beads, I'd be remiss if I didn't make sure that my AI robot brethren also enjoyed using it, so I added a mode just for them that is easy and useful for them.

To get your agents to use it, simply drop this blurb into your AGENTS dot md or CLAUDE dot md file:...