Pi replaced every other coding agent harness for me

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

Source video:
- Title: Pi replaced every other coding agent harness for me
- URL: https://www.youtube.com/watch?v=jPuN4ilZLdU
- Topic: Interfaces + Open Design
- My current learning frame: Install Pi from pi.dev, scope it to the three models you actually use, work through one real coding question using /tree to branch and summarize instead of restarting the chat, then ask Pi to write you a small extension that transforms messages before they reach the agent.
- Why this matters: New playlist item from Jilles; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 0:21 / Evidence 1: "test and I don't want it to. Same with Claude code. It has all these instructions and I'm not saying anything of this is bad and for a lot of people, this is probably what you want, but..."
- 1:39 / Evidence 2: "{slash} scope models, you'll see I have these three. Why is this important? Because now I can cycle with control P. Okay? So, Claude Fable 5, Opus 4.8, GPT 5.5. You can also control L to switch through..."
- 3:51 / Evidence 3: "context. So, you could see you could be going back and forth at a glance for a long time. Go back a bit, branch, summarize, >> >> and work your way through a problem. So, instead of you..."
- 5:24 / Evidence 4: "input transforms. Here's another one before agent start. I'm not writing any of this. Pi, the coding agent, is writing this. We can hot reload. Let's reload. Boom, now it's hot reloaded. It will load the extension. I..."

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 "Pi replaced every other coding agent harness for me", 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.