Herdr: Why Developers Are Replacing Tmux with AI Agents

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

Source video:
- Title: Herdr: Why Developers Are Replacing Tmux with AI Agents
- URL: https://www.youtube.com/watch?v=7W_H9313DHQ
- Topic: Interfaces + Open Design
- My current learning frame: Install Herder, wire up one coding-agent integration, spin up a git worktree, and spawn an agent inside it to complete a small real task.
- Why this matters: New playlist item from Damian Galarza; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 0:00 / Evidence 1: "Today, I want to walk you through a new tool that I've been using called Herder. Herder is a terminal multiplexer designed specifically for use with coding agents. It's available on Mac OS and Linux and also has..."
- 1:38 / Evidence 2: "them. And one of the other nice things about Herder is that it's mouse native. So, you can see here I'm moving my mouse. I can actually scroll inside of this window inside of the Herder UI and..."
- 4:13 / Evidence 3: "universal will be installed in agent skills in your home directory, and then also Claude code cuz I'm using this in the global configuration so that any session has it. So, I'll go ahead and choose Simlink and..."
- 6:25 / Evidence 4: "of there. Start a new Pi agent inside of WB work tree to scan the past 10 commits and verify that we have proper documentation up-to-date. So, that should then now cause the Pi agent here to spin..."
- 8:19 / Evidence 5: "to the projects configuration there. So, this is a nice way to be able to go ahead and actually interface with different projects and different agents at the same time. And we can see that we monitor and..."
- 10:36 / Evidence 6: "such plugin that I've been looking to start working with is one for scheduling things. So, I do like the Codex automations or cloud code routines, and I want to have something in the command line that I..."
- 13:36 / Evidence 7: "kind of um a built-in browser you can use and all sorts of things. And again, the docs list everything that you can do so you can make your own plug-ins if you want um as well, which..."

Video-aware target:
- Prompt lane: Coding-agent workflow
- Mechanism to extract: Find the workflow rule that explains when and how to use Codex, Claude Code, browser control, dashboards, or manual review.
- Artifact to produce: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
- Artifact must include: task class; agent/tool choice; context packet; verification step; handoff/recovery rule

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, transcript support, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable mechanism from the video: Find the workflow rule that explains when and how to use Codex, Claude Code, browser control, dashboards, or manual review. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
5. Include:
   - a plain-English definition of the core idea
   - a diagram or structured model using this sequence: Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step
   - answers to these source questions: What workflow pain is being solved? | What exact coordination mechanism is shown? | What evidence proves it changes the work?
   - 3 concrete examples that apply the video idea to real agentic work, such as rate-limit routing; browser verification after a UI edit; long-running /goal session review
   - 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: choosing tools by hype; losing context across agents; letting parallel sessions become invisible
   - a checklist for the next real workflow, focused on: routing decision, context portability, verification, handoff summary
   - one practical exercise with a clear done signal: Route three recent tasks across Codex, Claude, browser checks, and manual review with a reason for each.
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 "Herdr: Why Developers Are Replacing Tmux with AI Agents", not a generic Interfaces + Open Design essay.
- Each workflow rule must point to a timestamped claim or demo moment, then state what remains unproven.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- Avoid these generic drifts: generic Codex vs Claude comparison; feature lists without task routing; claims that ignore limits or recovery.
- If evidence is weak or missing, stop and say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.