Introducing /visual-plan - rich plans for Claude Code + Codex
Steve from Builder.io introduces /visual-plan, an open-source skill for Claude Code and Codex that replaces walls of markdown plans with MDX documents built from reusable components — interactive diagrams, API specs, schema changes, annotated code, and pan-and-zoomable wireframes — plus a companion /visual-recap skill and a GitHub Action that attaches a visual snapshot to every pull request.
Steve (Builder.io)4 minTranscript 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 Steve (Builder.io); queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to review and steer coding agents at the plan level — using visual, interactive MDX plans and recaps to catch mis-specified UI, APIs, and schemas before and after the agent implements them, instead of hand-reading long markdown or line-by-line diffs.
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.
1,065 cleaned transcript words reviewed across 300 timed caption segments.
Thesis
Introducing /visual-plan - rich plans for Claude Code + Codex teaches a practical codex + claude workflows move: Steve from Builder.io introduces /visual-plan, an open-source skill for Claude Code and Codex that replaces walls of markdown plans with MDX documents built from reusable components — interactive diagrams, API specs, schema changes, annotated code, and pan-and-zoomable wireframes — plus a companion /visual-recap skill and a GitHub Action that attaches a visual snapshot to every pull request.
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
Plans you can see
“Plan mode in Claude code is incredible, but I always find my eyes glazing over this huge markdown essay in my terminal. And I've realized after I implement things that I totally miss some important small details that...”
Plan mode's giant markdown essays cause reviewers' eyes to glaze over and important small details get missed; visual-plan instead generates MDX plans with interactive components — diagrams, API specs, schema changes, annotated code, and wireframes you can comment on and iterate before the agent works. Raw HTML was rejected because it is slow and verbose to generate, looks bad checked into a repo, and lacks reusable components. Take the last long markdown plan an agent gave you and list three concrete details you would have caught faster with a wireframe or an interactive API spec instead of prose.
1:17
Plan as abstraction layer
“reverse of this. I call it visual recap. What it can do is after the agent works, give you a recap of everything it did. The same idea. Wireframes, interactive API specs and diffs, schemas, annotated code, etc.”
Steve argues engineering is entering a new abstraction phase where the plan is the real reasoning level — like trusting the C compiler to emit assembly, if the plan is clear and correct we increasingly trust agents to implement it; the companion visual-recap skill applies the same idea after the work, replacing terse summaries or granular line-by-line diffs with wireframes, interactive specs, and annotated code so mistakes are caught before production. Write a one-paragraph 'plan-level contract' for a small feature — what a reviewer must be able to verify from the plan alone — then note which parts need a visual (wireframe, schema, API shape) versus text.
2:49
MDX, open source, CI
“so much more you can do with reusable components than generating honestly kind of HTML slop every time, different every time. It also means when you change agents or models, you get consistency as well. I open-sourced all...”
MDX is pitched as the full-circle format: nicer than raw HTML to check into a repo, more consistent than 'HTML slop' regenerated differently every time, and consistent across agents and models thanks to reusable, customizable components; everything is free and open source on GitHub with a CLI installer and a GitHub Action that posts an interactive visual plan snapshot on every pull request. Install the visual-plan CLI from Steve's GitHub, run it on one repo, and customize or add one MDX component to match a review artifact your team actually needs.
01
Inspect
Start with this video's job: Steve from Builder.io introduces /visual-plan, an open-source skill for Claude Code and Codex that replaces walls of markdown plans with MDX documents built from reusable components — interactive diagrams, API specs, schema changes, annotated code, and pan-and-zoomable wireframes — plus a companion /visual-recap skill and a GitHub Action that attaches a visual snapshot to every pull request. Treat "Inspect" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:00, where the video says: “Plan mode in Claude code is incredible, but I always find my eyes glazing over this huge markdown essay in my terminal. And I've realized after I implement things that I totally miss some important small details that...”
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 1:17, where the video says: “reverse of this. I call it visual recap. What it can do is after the agent works, give you a recap of everything it did. The same idea. Wireframes, interactive API specs and diffs, schemas, annotated code, etc.”
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: Steve from Builder.io introduces /visual-plan, an open-source skill for Claude Code and Codex that replaces walls of markdown plans with MDX documents built from reusable components — interactive diagrams, API specs, schema changes, annotated code, and pan-and-zoomable wireframes — plus a companion /visual-recap skill and a GitHub Action that attaches a visual snapshot to every pull request.
02
Explain the practical stakes without hype: New playlist item from Steve (Builder.io); 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: Introducing /visual-plan - rich plans for Claude Code + Codex
- URL: https://www.youtube.com/watch?v=NE0aBuQF0HA
- Topic: Codex + Claude Workflows
- My current learning frame: Pick one upcoming feature, generate a visual plan for it with the /visual-plan skill, mark up the wireframe and API spec with corrections before letting the agent implement, then compare the visual recap against your plan to see what the visual layer caught that markdown would have hidden.
- Why this matters: New playlist item from Steve (Builder.io); queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:00 / Evidence 1: "Plan mode in Claude code is incredible, but I always find my eyes glazing over this huge markdown essay in my terminal. And I've realized after I implement things that I totally miss some important small details that..."
- 1:17 / Evidence 2: "reverse of this. I call it visual recap. What it can do is after the agent works, give you a recap of everything it did. The same idea. Wireframes, interactive API specs and diffs, schemas, annotated code, etc."
- 2:49 / Evidence 3: "so much more you can do with reusable components than generating honestly kind of HTML slop every time, different every time. It also means when you change agents or models, you get consistency as well. I open-sourced all..."
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 "Introducing /visual-plan - rich plans for Claude Code + Codex", 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.
Why did Steve build visual-plan on MDX instead of plain HTML or markdown?
What analogy does Steve use to describe reasoning at the plan level rather than the code level?
What kinds of interactive components does a visual plan include, and what problem do they solve?
Source shelf
Use the video as a doorway, then verify with primary sources.
