I'm ditching tmux for herdr!

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

Source video:
- Title: I'm ditching tmux for herdr!
- URL: https://www.youtube.com/watch?v=yQDARWdrPeY
- Topic: Creative Automation
- My current learning frame: Install Herder locally, port over your tmux keybindings and a theme, run a coding agent inside a workspace, then stand up a remote box and reattach to a running agent session from a fresh SSH connection.
- Why this matters: New playlist item from typecraft; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 1:28 / Evidence 1: "the agent will keep working without my input on its own. And one of the coolest parts about Cursor's cloud agents is that they return so much information. I mean, they don't even just give you the results..."
- 3:22 / Evidence 2: "which is control B by default, just like Tmux, you'll see a little bar pop up at the bottom here. This gives you a little bit of a preview of some of the key bindings you can do..."
- 5:56 / Evidence 3: "see that they mention coding agents right off the gates. This is in the first sentence. And that's because Hurder treats coding agents like Claude, Cursor, tons of other agents as first-class citizens. And what does that mean?"
- 7:30 / Evidence 4: "agent in your workspace. But, if you like using your keyboard, there's actually a really, really great key binding that I found. Leader G opens up a fuzzy finding panel that will go through all of your agents..."
- 9:37 / Evidence 5: "is still here. The agent was still running, it was still doing its thing, nothing is lost. This is what I mean when I say Herder treats agents as first-class citizens. It works amazingly with any coding agent..."
- 11:16 / Evidence 6: "a scenario with you first. Let's say you're one of these cool agentic programmers. You're working on your loops, your graphs, and your agentic workflow, but you've got something to do. Let's say your wife calls, and one..."
- 12:47 / Evidence 7: "my Herder instances from wherever I may be. This is a workflow that I personally love, and I'm definitely going to set up and start using in the near-term future. So, stick around for that, because that's going..."

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 creative workflow board with critique criteria and review checkpoints.
5. Include:
   - a plain-English definition of the core idea
   - a diagram or structured model using this sequence: Brief -> Source -> Generation -> Selection -> Edit -> Taste Review
   - 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 "I'm ditching tmux for herdr!", not a generic Creative Automation 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.