Pi Agent - Crash Course | Minimal Coding Agent

You are helping me turn one specific YouTube video into real, durable learning.

Source video:
- Title: Pi Agent - Crash Course | Minimal Coding Agent
- URL: https://www.youtube.com/watch?v=N30XGyPrr6I
- Topic: Agent Architecture
- My current learning frame: Learn Pi as a minimal coding-agent runtime: start with a small tool surface, add extensions intentionally, manage sessions and prompts, and compare the workflow to heavier coding agents.
- Why this matters: This is a practical counterweight to bloated agent setups and shows what a smaller runtime needs to be useful.

Transcript anchors from this exact video:
- 1:39 / Evidence 1: "Pi to enable MCP support. You can add sub-agents if you want it. There are no permission pop-ups, but you can either run this in containers or build, ask Pi to build a permission pop-up system which is..."
- 5:37 / Evidence 2: "that whenever you type them, they're going to be your custom prompt. So what you can do is actually ask Pi to create its own custom prompts. And that's a little bit easier. And then you can customize..."
- 7:13 / Evidence 3: "So I go inside agent. And inside it, you can see that I have extensions, prompt sessions, etc. So this prompt was stored in prompt. So I go to prompts. And right there, you will see that you..."
- 9:50 / Evidence 4: "Skill visualizer, I five-coded it yesterday just to help me visualize my skills. Skill creator, I think it's built-in. And find skill, I also think it's built-in. I don't remember. I mean, built-in with cloud code, if I..."
- 17:24 / Evidence 5: "footer, for example, things to your editor right here, whatever you want. Okay. Now, let me give you another very quick example. Here I have another prompt that I have that I think that is a good extension..."
- 21:05 / Evidence 6: "So here are some of the common functionalities that you already know from other coding agents that you can add with a single command to your PyAgent. So for example, there is PySubagents, there is context mode, MCPAdapter..."
- 24:37 / Evidence 7: "agent to compact your conversation in case you're close to reaching your limit in your context window, and it will manually compact that session. And something nice is that you can add custom instructions right here, like for..."

Your task:
1. Use the transcript anchors above as the primary source packet. If you add outside context, label it clearly as outside context and keep it secondary.
2. Create a source-check table with columns: timestamp, claim, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable claims from the video. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A one-page agent harness map with tool boundaries and proof signals.
5. Include:
   - a plain-English definition of the core idea
   - a diagram or structured model using this sequence: Intent -> Model -> Harness -> Tools -> Verifier -> Artifact
   - 3 concrete examples that apply the video idea to real agentic work
   - 2 failure modes the video helps prevent
   - a checklist I can use the next time I run Codex or Claude
   - one practical exercise with a clear done signal
6. Add a "learning transfer" section: what changes in my workflow tomorrow if I actually learned this?
7. Add a "source check" section that cites which transcript anchor supports each major takeaway.

Quality bar:
- Make this specific to "Pi Agent - Crash Course | Minimal Coding Agent", not a generic Agent Architecture essay.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- If evidence is weak, say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.