Why I stopped using Codex and started using T3 Code instead.

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

Source video:
- Title: Why I stopped using Codex and started using T3 Code instead.
- URL: https://www.youtube.com/watch?v=LgshG0_cxtw
- Topic: Codex + Claude Workflows
- My current learning frame: Run the same small repository task through your current coding-agent client and T3 Code, then compare task triage, project defaults, pull-request handling, provider visibility, and the listed missing features.
- Why this matters: New playlist item from AI in C# (Rasmus Wulff Jensen); queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 0:27 / Evidence 1: "T3 Code. It's a annoying name to say, so that's definitely not one of the reasons why I've switched. But why did I switch and what is T3 Code? Well T3 Code is an open source coding agent..."
- 2:02 / Evidence 2: "sidebar with projects. They have the chat and then they often have right sidebar with an integrated browser, a diff editor and so on and so forth. And this one has the same just on the surface, but..."
- 8:12 / Evidence 3: "Second part is the per project settings. So you have projects like the others, but there's all these small niceties in for example, you can set up icons. onto a project. You can go in and set that..."
- 10:43 / Evidence 4: "ChatGPT have put out. Then there's stats and limits. It's built into the system that you can actually see how many tokens you use either in real tokens or in API costs despite not still using a sub,..."
- 14:33 / Evidence 5: "T3 Code or had an even better schedule system. But because I use Hermes Agent I don't really need to use the schedules in that regard other than for a few things code related. There's also no MCP..."
- 16:11 / Evidence 6: "I've heard that's something about Codex encrypting their sub-agents so they can only decrypt them by themselves. I think that's the reason why we don't see them. So we can only see a list of them. We can't..."
- 17:46 / Evidence 7: "give it a couple of days at least. But this is why I switched. This is why whenever I do the coding agent videos you see something from T3 Code and not from Codex anymore. So with that..."

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 "Why I stopped using Codex and started using T3 Code instead.", not a generic Codex + Claude Workflows 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.