Comment by atworkc
15 hours ago
I've settled on just a simple folder called `workbench` for some reason the new models know exactly what's up with it. Git ignored
The only "prompt" is in AGENTS.md saying that this thing exists and there's a map.md <- which is a one liner reference to whatever the agent stores in there.
And usually, I tackle a new feature, and at some point tell it to store to jot down notes in workbench if I'm comfortable with it (and if it needs to be stored in memory)
This makes it easy to just spawn other agents and such from a good point, I just point them that stuff is in workbench.
Token costs, seem decent and I can always just delete stuff in there as its purpose is ephemeral.
Plug here for a python app I wrote, no dependencies. It uses a skill to maintain an index, links, archival, and works with a separate opinionated dev playbook nicely. The best part is now the docs/specs folder maintains itself. (and I can spawn a new session with all the relevant context every time)
https://github.com/ArtRichards/docs-cli
and
https://artrichards.github.io/agent-playbook-suite/blog/
Looks slick. One thing you might find useful is Pydantic schemas for the core fields in each record type, it's helpful for generating good error messages on the record create path as well as keeping the overall tool code tidier.
Cool tool, thanks for sharing.