what is your hook into such a sprint; how do you get started? Do you just prompt "so uh teach me something about linux admin" and go from there?

I think this has been my biggest hurdle with LLM-based learning, even though I think the concept may be quite powerful...

Happy to hear more about your approach :)

On the same lines: "hi, let's get started" and it begins understanding my setup and as per the initialization protocol, it has the latest state:

This is the main hook in AGENT.md file:

   ## 3. Initialization Protocol (Read This First)

   Upon being activated in this directory, you MUST:

   1. **Read `CURRENT.md`** to understand the current topic under study. The current topic's content and files are under its dedicated directory. **Ignore** all other topic directories.

   2. **Read the topic-specific `README.md`**: (e.g., in `/mcp/`) to understand the specific mental models and technical constraints of the current subject.

   3. **Read `PROGRESS.md`**: To understand exactly where the last session ended and what the "Current Frontier" is.

   4. **Acknowledge State**: Start the session by briefly confirming the current learning milestone you've identified from the files.

Mostly, the agent concludes the session once it guages that 15-20 minute sprint-worthy concepts have been covered. Try it. If you want, I can share the full notes sans-my personal info through gist.