OpenCode Full Tutorial: Free Models, Skills & MCPs

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

Source video:
- Title: OpenCode Full Tutorial: Free Models, Skills & MCPs
- URL: https://www.youtube.com/watch?v=0xKE1UHpSfk
- Topic: Codex + Claude Workflows
- My current learning frame: In a real project, install OpenCode, connect a free and a subscription model, run /init to build an agents.md, install one skill from skills.sh, and use plan mode plus a shared session link to scaffold and refactor a small app end to end.
- Why this matters: New playlist item from Eric Tech; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 0:09 / Evidence 1: "tool called open code which should solve exactly this problem. And with just only one AI agents, you can now be able to use any models you want with your existing subscriptions or with the free models or..."
- 2:29 / Evidence 2: "the terminal session and now I'm already inside of that project. So if I were to do Ctrl C, you can see I'm in the app directory, right? So now if I were to type in like for..."
- 4:31 / Evidence 3: "flash free. So if you want to use the free model simply just going to click on enter and now you have access to deepcv4 flash free from the open code zen and if I were to say..."
- 6:05 / Evidence 4: "full AI builder road map where you're going to start with AI automations. Then later on moving into AI agents, research systems, SAS buildings, and eventually how to productize and market your AI skills. You're going to get..."
- 14:11 / Evidence 5: "have our coding agent here now switch from plan mode to execution mode. Okay, so finally what I want to talk about is how you can be able to integrate your skills MCPS into your open code. So..."
- 17:03 / Evidence 6: "sup power inside of open code here right off the bat. Now lastly, what I want to cover here is also the ability here to initialize your agents.mdv. That's kind of like your system prompt for your entire..."
- 19:39 / Evidence 7: "should respond with emojis because I have already mentioned this right inside of the agents file. So here you can see it has mentioned with emojis, which is pretty good, right? So that's exactly how you can be..."

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 "OpenCode Full Tutorial: Free Models, Skills & MCPs", 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.