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)
atworkc · · focus · HN ↗
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.
ArtRichards · · focus · HN ↗
<a href="https://github.com/ArtRichards/docs-cli" rel="nofollow">https://github.com/ArtRichards/docs-cli
and
<a href="https://artrichards.github.io/agent-playbook-suite/blog/" rel="nofollow">https://artrichards.github.io/agent-playbook-suite/blog/
chrisweekly · · focus · HN ↗