Interfaces + Open Design / Foundation

I Turned Claude Code Into JARVIS (FULL WALKTHROUGH)

This walkthrough builds a Claude Code assistant in three testable stages: voice, hands-free listening and vision, then access to real work through files, skills, connectors, and subagents. It also shows how secret storage, permission ownership, read-only data access, and reversible-action guards keep those expanding capabilities controlled.

Shabbir Noor AI18 minTranscript found

Quick learning frame

Read this before watching.

Coding-agent workflow is the loop of inspect, route, plan, edit, verify, summarize, and decide what should be automated next.

New playlist item from Shabbir Noor AI; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Skill you build: The ability to stage a multimodal assistant from conversation to real work while defining tests, process permissions, data boundaries, and guards at each capability layer.

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 context
02Route tool
03Plan work
04Edit safely
05Verify behavior
06Report next step

Deep lesson

Turn this video into working knowledge.

2,957 cleaned transcript words reviewed across 916 timed caption segments.

Thesis

I Turned Claude Code Into JARVIS (FULL WALKTHROUGH) teaches a practical coding-agent workflow move: This walkthrough builds a Claude Code assistant in three testable stages: voice, hands-free listening and vision, then access to real work through files, skills, connectors, and subagents. It also shows how secret storage, permission ownership, read-only data access, and reversible-action guards keep those expanding capabilities controlled.

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.

1:08

Voice Needs Context

β€œto do real, meaningful work. It'll read my files, run my save routines, and even send out a team of helper agents for large jobs. Even if you've never opened Claude code, you can do this because all...”

Voice makes the assistant quicker and more natural to use, but it also needs access to existing work so every session does not start from scratch. Building Jarvis as a Claude Code mod removes the extra relay app and places it inside the tool that already holds the user's work context. For one assistant idea, name the host tool where the work already happens, the existing files it should access, and the interaction that voice would make faster.

9:02

Local Ears, Separate Eyes

β€œClaude without needing to press a button. Eyes, the ability to do something, and integrating the existing skills. And this was the longest build of the whole project. It took about 12 minutes. And remember those earlier instructions...”

Open Wake Word listens for "Hey Jarvis" on the Mac, so nothing leaves the machine before activation. Screen capture worked, but the camera hung because its request came from Claude Code's helper, which only asked for microphone access; a separate Jarvis Eyes app fixed the problem by requesting camera permission directly. Draw two flows: local wake-word detection through activation, and the failed camera request through Jarvis Eyes receiving camera permission. Mark where data or permission changes in each flow.

13:05

Connect Work Safely

β€œanything Claude Code can already do, Jarvis can do by voice. And that's the beauty of building it inside Claude Code as a mod. Next, let's have Jarvis spin up a team of three sub agents. >> >>...”

Because Jarvis is a Claude Code mod, it inherits installed skills, connectors, and subagents instead of requiring a separate integration layer. The vault starts read-only, results are tied to real files, and a guard redirects risky requests such as deletion toward reversible actions like moving items to the trash. Choose one notes collection or installed skill, define a read-only first task, and write the approval rule for any irreversible action.

01

Inspect context

Start with this video's job: This walkthrough builds a Claude Code assistant in three testable stages: voice, hands-free listening and vision, then access to real work through files, skills, connectors, and subagents. It also shows how secret storage, permission ownership, read-only data access, and reversible-action guards keep those expanding capabilities controlled. Treat "Inspect context" as the outcome you are trying to make visible, not a topic label. Anchor it to 1:08, where the video says: β€œto do real, meaningful work. It'll read my files, run my save routines, and even send out a team of helper agents for large jobs. Even if you've never opened Claude code, you can do this because all...”

02

Route tool

Use "Route tool" to locate the part of the coding-agent workflow mechanism the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 9:02, where the video says: β€œClaude without needing to press a button. Eyes, the ability to do something, and integrating the existing skills. And this was the longest build of the whole project. It took about 12 minutes. And remember those earlier instructions...”

03

Plan work

Turn "Plan work" into the reusable artifact for this lesson: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal. This is where watching becomes something you can inspect and reuse.

04

Edit safely

Use "Edit safely" 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

Verify behavior

Use "Verify behavior" 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

Report next step

Use "Report next step" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.

Example

Source-backed artifact packet

Convert the video into a scoped artifact request that includes the transcript claim, mechanism, acceptance criteria, and proof. The output should be a coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal..

Example

Coding-agent workflow proof brief

Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the coding-agent workflow pattern.

Example

Teach-back module

Transform the lesson into a definition, a Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step 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.
  • choosing tools by hype
  • losing context across agents
  • letting parallel sessions become invisible
  • Letting the lesson drift into generic Codex vs Claude comparison.
  • Letting the lesson drift into feature lists without task routing.
  • Letting the lesson drift into claims that ignore limits or recovery.

Transcript-derived moments

Use timestamps to study the actual video.

Quality check

Do not count this as learned until these are true.

01

State the transcript-backed claim in your own words: This walkthrough builds a Claude Code assistant in three testable stages: voice, hands-free listening and vision, then access to real work through files, skills, connectors, and subagents. It also shows how secret storage, permission ownership, read-only data access, and reversible-action guards keep those expanding capabilities controlled.

02

Explain the practical stakes without hype: New playlist item from Shabbir Noor AI; queued for transcript-backed review, topic mapping, and a practical learning artifact.

03

Map the idea onto the Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step sequence and name the weakest link.

04

Produce the artifact and include the evidence that proves it: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.

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: I Turned Claude Code Into JARVIS (FULL WALKTHROUGH)
- URL: https://www.youtube.com/watch?v=MtW9bnWvEfI
- Topic: Interfaces + Open Design
- My current learning frame: Plan three increments for conversation, perception, and real work, then give each a functional test, keep wake-word detection local until activation, grant camera access through the requesting helper, start data access read-only, and make risky actions reversible.
- Why this matters: New playlist item from Shabbir Noor AI; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 1:08 / Evidence 1: "to do real, meaningful work. It'll read my files, run my save routines, and even send out a team of helper agents for large jobs. Even if you've never opened Claude code, you can do this because all..."
- 2:54 / Evidence 2: "else that you get because of this one change that I've made. So let's start by setting it up and making Jarvis talk. So now for level one, making it talk, you need the Claude desktop app installed."
- 4:32 / Evidence 3: "then we'll build the whole thing. And it writes the plan. Click talk, speak, click stop. Your words get transcribed and they go into Claude code as a prompt. So that was the ears. And for the mouth,..."
- 6:29 / Evidence 4: "off by default, so it fixed it Second try, it replied on screen, but I heard nothing. So I typed two words, I can't hear. And Claude found it. My voice prompt was being treated like a typed..."
- 9:02 / Evidence 5: "Claude without needing to press a button. Eyes, the ability to do something, and integrating the existing skills. And this was the longest build of the whole project. It took about 12 minutes. And remember those earlier instructions..."
- 13:05 / Evidence 6: "anything Claude Code can already do, Jarvis can do by voice. And that's the beauty of building it inside Claude Code as a mod. Next, let's have Jarvis spin up a team of three sub agents. >> >>..."
- 16:16 / Evidence 7: "Claude code, about 1,000 lines, 29 files, 10 features from a single prompt. The link to grab the prompt is in the description. And now for the honest limits. The voice does need a separate engine. I'm using..."

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 "I Turned Claude Code Into JARVIS (FULL WALKTHROUGH)", 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.

Misconceptions

What to stop believing.

A beautiful page is automatically a good learning tool.

Learning requires sequence, active recall, feedback, and application.

Generated UI should be accepted as-is.

Generated UI needs critique, revision, and browser verification.

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 coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal..

A reusable artifact with a done signal and one verification step.
03

Coding-agent workflow teach-back card

Explain the coding-agent workflow mechanism 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 β€” without rewatching.

Why does the presenter build Jarvis inside Claude Code rather than as a separate app?

Why was a separate Jarvis Eyes helper needed for camera access?

Why does the content-vault interface start as read-only?

Source shelf

Use the video as a doorway, then verify with primary sources.

ReadingOpen Design Repogithub.com/open-design-dev/open-designReadingReact Docsreact.dev/