Codex: Build Your Full AI Marketing Team (Agents + Skills)
Riley Brown demonstrates how he runs nearly all his content-marketing work inside OpenAI's Codex super app by layering reusable skills (YouTube Researcher, Readwise CLI, Excalidraw diagrams, paper MCP) and turning them into daily automations.
Riley BrownWatchTranscript found
Quick learning frame
Read this before watching.
Coding-agent workflow is the loop of inspect, plan, edit, verify, summarize, and route the next task to the right tool.
New playlist item from Riley Brown; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: Building and chaining reusable Codex/Claude Code skills that ground an AI agent in real reference data, then converting working prompts into scheduled automations.
Watch for the shift from claim to mechanism. The learning value is the point where the transcript reveals a repeatable action, tool boundary, context move, review habit, or artifact.
Concept diagram
Where this video fits.
01Inspect
02Plan
03Edit
04Verify
05Review
06Route
Deep lesson
Turn this video into working knowledge.
9,300 cleaned transcript words reviewed across 2,473 timed caption segments.
Thesis
Codex: Build Your Full AI Marketing Team (Agents + Skills) teaches a practical codex + claude workflows move: Riley Brown demonstrates how he runs nearly all his content-marketing work inside OpenAI's Codex super app by layering reusable skills (YouTube Researcher, Readwise CLI, Excalidraw diagrams, paper MCP) and turning them into daily automations.
The goal is not to remember the video. The goal is to extract the operating principle, tie it to timestamped evidence, test how far the claim transfers, and make something reusable.
0:00
Skills vs plugins
“Yesterday I was working on my laptop and I realized that 95% of the tasks that I do on my computer for content and marketing is inside Codeex. And Codeex is OpenAI's brand new super app. And the...”
Codex is a super app whose preview pane morphs to the task (app, browser, spreadsheet, deck); skills are instruction files for an agent invoked with slash, and plugins are bundles of skills invoked with the at sign. Open Codex (or Claude Code), click Plugins top-left, and inspect one plugin like Vercel to see the multiple skills bundled inside it.
18:34
Ground in references
“video and as we go along I'm going to use these skills together. Right? So I I wanted to create an excalad diagrams. Please do it in my voice and you can use the YouTube researcher skill to...”
Instead of relying on a model's generic trained taste, 'grounding' points the agent at a high-quality reference: the YouTube Researcher skill pulls real transcripts (via a SupaData API key) and the Readwise CLI skill taps your own bookmarked tweets as a second brain. Get a SupaData API key, then run /youtube-researcher to pull a creator's last 10 transcripts and generate hooks grounded in their actual style.
43:35
Diagram then automate
“that work done just with an AI agent. And then this is how you kind of like skill stack here. And we're able to just like schedule all the meetings. I can say, "Okay, I want to schedule...”
Chained skills (Excalidraw, paper MCP) build visual diagrams while sub-agents run grounding tasks in parallel for speed; once a prompt produces output you like, you tell the agent to save it as a skill and schedule it as a daily automation. Take one prompt that worked, say 'turn this into a skill called X,' then 'run this every morning at 8am,' and confirm it appears under Automations.
01
Inspect
Start with this video's job: Riley Brown demonstrates how he runs nearly all his content-marketing work inside OpenAI's Codex super app by layering reusable skills (YouTube Researcher, Readwise CLI, Excalidraw diagrams, paper MCP) and turning them into daily automations. Treat "Inspect" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:00, where the video says: “Yesterday I was working on my laptop and I realized that 95% of the tasks that I do on my computer for content and marketing is inside Codeex. And Codeex is OpenAI's brand new super app. And the...”
02
Plan
Use "Plan" to locate the part of the codex + claude workflows workflow the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 18:34, where the video says: “video and as we go along I'm going to use these skills together. Right? So I I wanted to create an excalad diagrams. Please do it in my voice and you can use the YouTube researcher skill to...”
03
Edit
Turn "Edit" into the reusable artifact for this lesson: A routing matrix for when to use Codex, Claude, browser checks, or manual review. This is where watching becomes something you can inspect and reuse.
04
Verify
Use "Verify" as the application surface. Decide whether the idea touches a browser flow, a local file, a model choice, a source document, a UI, or a review step.
05
Review
Use "Review" to prove the lesson. The evidence should connect back to the video title, transcript anchors, and a concrete output, not a generic best-practice claim.
06
Route
Use "Route" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.
Example
Source-backed work packet
Convert the video into a scoped task that includes the transcript claim, target workflow, acceptance criteria, and proof. The output should be a routing matrix for when to use codex, claude, browser checks, or manual review..
Example
Claim vs. demo brief
Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the workflow.
Example
Teach-back module
Transform the lesson into a definition, a mechanism diagram, one misconception, one practice exercise, and a check-for-understanding question.
Do not learn it wrong
Treating the title as the lesson without checking what the transcript actually says.
Letting the prompt drift into generic advice that could apply to any video in the playlist.
Copying the tool setup without identifying the operating principle that transfers to your own stack.
Skipping the artifact, which means the learning never becomes operational or inspectable.
Do not count this as learned until these are true.
01
State the transcript-backed claim in your own words: Riley Brown demonstrates how he runs nearly all his content-marketing work inside OpenAI's Codex super app by layering reusable skills (YouTube Researcher, Readwise CLI, Excalidraw diagrams, paper MCP) and turning them into daily automations.
02
Explain the practical stakes without hype: New playlist item from Riley Brown; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Inspect -> Plan -> Edit -> Verify -> Review -> Route sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A routing matrix for when to use Codex, Claude, browser checks, or manual review.
Put it into practice
Give this grounded prompt to Codex or Claude after watching.
You are helping me turn one specific YouTube video into real, durable learning.
Source video:
- Title: Codex: Build Your Full AI Marketing Team (Agents + Skills)
- URL: https://www.youtube.com/watch?v=sL_KBnYB17I
- Topic: Codex + Claude Workflows
- My current learning frame: Pick one recurring marketing task you do, build a grounded Codex/Claude Code skill for it using a real YouTube transcript or your Readwise bookmarks, then convert the working prompt into a scheduled daily automation.
- Why this matters: New playlist item from Riley Brown; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:00 / Evidence 1: "Yesterday I was working on my laptop and I realized that 95% of the tasks that I do on my computer for content and marketing is inside Codeex. And Codeex is OpenAI's brand new super app. And the..."
- 1:55 / Evidence 2: "page. When you use codeex, you're basically prompting an AI agent and you can select your model. And this AI model has full control over your computer. It can edit, delete, and create files on your computer. Basic..."
- 6:54 / Evidence 3: "depending on your niche or depending on who you are, you might have a specific taste that you like. And so what you want to do is you want to actually ground the model or point your AI..."
- 10:07 / Evidence 4: "karpathy style for skills. And this sounds exactly like him. Think of Codex as a little operating system around a language model. At the center there is the model. The model can read text, write text, reason, and..."
- 18:34 / Evidence 5: "video and as we go along I'm going to use these skills together. Right? So I I wanted to create an excalad diagrams. Please do it in my voice and you can use the YouTube researcher skill to..."
- 43:35 / Evidence 6: "that work done just with an AI agent. And then this is how you kind of like skill stack here. And we're able to just like schedule all the meetings. I can say, "Okay, I want to schedule..."
- 47:33 / Evidence 7: "I will have all of those skills updated and you can try them in codeex or claude code. If you want to test them out for free, you can test them in our new experimental AI agent product..."
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 routing matrix for when to use Codex, Claude, browser checks, or manual review.
5. Include:
- a plain-English definition of the core idea
- a diagram or structured model using this sequence: Inspect -> Plan -> Edit -> Verify -> Review -> Route
- 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 "Codex: Build Your Full AI Marketing Team (Agents + Skills)", not a generic Codex + Claude Workflows 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.
Misconceptions
What to stop believing.
One agent should do every task.
Different tools have different strengths. Routing is part of the workflow.
More context is always better.
Relevant context helps; stale context causes drift and cost.
Practice studio
Learning only counts when you make something.
01
Transcript evidence map
Separate what the video actually says from what you already believe about the topic.
3 source-backed takeaways with timestamps, confidence, and a transfer note.02
One useful artifact
Apply the video to a real workflow and produce a routing matrix for when to use codex, claude, browser checks, or manual review..
A reusable artifact with a done signal and one verification step.03
Teach-back card
Explain the lesson to someone who has not watched the video yet.
A 90-second explanation, one diagram, one example, and one misconception to avoid.
Recall check
Answer first, then reveal — without rewatching.
In Codex, what is the difference between a skill and a plugin, and how is each invoked?
What does 'grounding' mean in this workflow, and how does the YouTube Researcher skill ground content (including what external tool it needs)?
Once a prompt produces output you like, what two steps turn it into a recurring automation in Codex?
Source shelf
Use the video as a doorway, then verify with primary sources.
