If you have tried to give an AI coding agent access to your task board, you have probably hit the wall I did: the board lives behind an API, and the agent lives in your repo. Here is the low-tech surface I use instead, where both of us read and write the same file.
I maintain a fleet of small OSS projects. The cross-cutting "what do I do next" list used to live in my head, then in a SaaS board, then nowhere useful. What finally stuck is embarrassingly low-tech: a single todo.txt in todo.txt format, plus a few dozen lines of dependency-free shell and Python around it.
The twist is that I'm not the only one reading and writing that file. My AI coding agents read it, grep it, and append to it too. Same file, same format, no API in between. This post is about why a plain-text board turned out to be the right shared surface for a human-plus-agents workflow, and what the moving pieces actually are.
What you'll learn:
Why a plain-text todo.txt is a better shared surface for human-plus-agent work than a hosted board
