It feels like it was just a couple days ago that I wrote up "How I'm using coding agents in September, 2025".
At the beginning of that post, I alluded to the fact that my process had evolved a bit since then.
I've spent the past couple of weeks working on a set of tools to better extract and systematize my processes and to help better steer my agentic buddy. I'd been planning to start to document the system this weekend, but then this morning, Anthropic went and rolled out a plugin system for claude code.
If you want to stop reading and play with my new toys, they're self-driving enough that you can. You'll need Claude Code 2.0.13 or so. Fire it up and then run:
/plugin marketplace add obra/superpowers-marketplace /plugin install superpowers@superpowers-marketplace
After you quit and restart claude , you'll see a new injected prompt:
That's the bootstrap that kicks off Superpowers . It teaches Claude a couple important things:
You have skills. They give you Superpowers. Search for skills by running a script and use skills by reading them and doing what they say. If you have a skill to do something, you must use it to do that activity.
The coding workflow #
... continue reading