Claude Code /goal Just Dropped and it Can Build Literally Anything
Chris explains Claude Code and Codex's /goal feature, which sets a completion condition and keeps the agent working turn after turn (a small fast model checks whether the condition holds) until done, then races both agents to build a full Next.js app from a PRD and a 62-task product roadmap in about 32 minutes each.
Build Great Products27 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 Build Great Products; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to write a strong, measurable /goal completion condition backed by spec docs (PRD, roadmap, design.md) so a coding agent can autonomously build and self-verify a large multi-task project.
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.
5,682 cleaned transcript words reviewed across 1,596 timed caption segments.
Thesis
Claude Code /goal Just Dropped and it Can Build Literally Anything teaches a practical coding-agent workflow move: Chris explains Claude Code and Codex's /goal feature, which sets a completion condition and keeps the agent working turn after turn (a small fast model checks whether the condition holds) until done, then races both agents to build a full Next.js app from a PRD and a 62-task product roadmap in about 32 minutes each.
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
How /goal loops
“Claude Co just released a feature that is going to change the way that everyone builds with AI. But the thing is they stole it directly from codecs. And the feature I'm talking about is for/goal. And what...”
The /goal command sets a completion condition and Claude keeps working without you prompting each step; after each turn a small fast model checks whether the condition holds and, if not, starts another turn, clearing the goal automatically once met, an evolution of the Ralph loop that pairs with auto mode. Write out, in plain English, one measurable end-state condition for a task you want an agent to finish without step-by-step prompting.
7:35
Spec docs drive it
“context to be able to work correctly. So, let's start building our app using for/goal include code and codeex. But before we start, I want to show you how I've set up the folders for these projects as...”
A good goal is bigger than one prompt but smaller than an open-ended backlog and must define what to change, how to validate, and when to stop; Chris feeds a PRD, a 62-task product roadmap, and a design.md (Google's open-source format) with Karpathy-style Claude.md/agents.md rules so the agent has a verifiable done condition. Draft a mini spec set (PRD outline, a task checklist, and a design.md direction) for a small app before writing any goal.
23:01
One-pass full build
“you're going to get around any like specific design direction from a a given model. Basically we've got our channel that is connected here. Jordan builds 10 posts ready to review now processing videos processing post generated niche...”
Both Claude Code and Codex ran /goal for about 32 minutes, flipping all 62 roadmap checkboxes and committing to a local git repo, producing offline-first apps with stubs and fallbacks (Convex, Clerk, Polar, YouTube/OpenAI) that needed only env vars wired up; the shared design.md kept both outputs visually close. Run a /goal build against your spec set, then prompt the agent to 'guide me step by step through setting up everything I need to deploy this app.'
01
Inspect context
Start with this video's job: Chris explains Claude Code and Codex's /goal feature, which sets a completion condition and keeps the agent working turn after turn (a small fast model checks whether the condition holds) until done, then races both agents to build a full Next.js app from a PRD and a 62-task product roadmap in about 32 minutes each. Treat "Inspect context" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:00, where the video says: “Claude Co just released a feature that is going to change the way that everyone builds with AI. But the thing is they stole it directly from codecs. And the feature I'm talking about is for/goal. And what...”
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 7:35, where the video says: “context to be able to work correctly. So, let's start building our app using for/goal include code and codeex. But before we start, I want to show you how I've set up the folders for these projects as...”
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.
Do not count this as learned until these are true.
01
State the transcript-backed claim in your own words: Chris explains Claude Code and Codex's /goal feature, which sets a completion condition and keeps the agent working turn after turn (a small fast model checks whether the condition holds) until done, then races both agents to build a full Next.js app from a PRD and a 62-task product roadmap in about 32 minutes each.
02
Explain the practical stakes without hype: New playlist item from Build Great Products; 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: Claude Code /goal Just Dropped and it Can Build Literally Anything
- URL: https://www.youtube.com/watch?v=0lw8KTx8KS8
- Topic: Creative Automation
- My current learning frame: Write a PRD, a task-checklist roadmap, and a design.md for a small app, then run /goal in Claude Code or Codex to build the whole thing in one pass and verify the roadmap tasks are checked off.
- Why this matters: New playlist item from Build Great Products; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:00 / Evidence 1: "Claude Co just released a feature that is going to change the way that everyone builds with AI. But the thing is they stole it directly from codecs. And the feature I'm talking about is for/goal. And what..."
- 2:53 / Evidence 2: "to understand here for non-technical people over at buildgreateproducts.com, which just covers off what is the codec cli, what for/goal actually does, the four subcomands, life cycle states, how to actually write a strong goal, and some of..."
- 7:35 / Evidence 3: "context to be able to work correctly. So, let's start building our app using for/goal include code and codeex. But before we start, I want to show you how I've set up the folders for these projects as..."
- 10:07 / Evidence 4: "context manageable. So it's now reading those files there. Codeex has saying the workspace is essentially fresh. Only agents.md and docs are present. There is no git metadata in this directory. The design file is design. MD. So..."
- 11:57 / Evidence 5: "design source. Let's do design.md wins everywhere. The scope is all 62 tasks as code. Get um in it with no remote. Let's do that. and then submit these answers to Claude Code. Codeex is just off to..."
- 23:01 / Evidence 6: "you're going to get around any like specific design direction from a a given model. Basically we've got our channel that is connected here. Jordan builds 10 posts ready to review now processing videos processing post generated niche..."
- 26:17 / Evidence 7: "really introducing an entirely new way of building with AI agents where instead of just prompting back and forth, we're allowing the AI agent to decide what all of these different tasks are based on a longer running..."
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 "Claude Code /goal Just Dropped and it Can Build Literally Anything", not a generic Creative Automation 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.
Creative AI removes the need for taste.
It increases the need for taste because output volume explodes.
The best prompt is enough.
References, critique, iteration, and post-production matter just as much.
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 — without rewatching.
How does the /goal feature keep an agent working, and what checks whether it should stop?
What must a good /goal define, and which spec documents does Chris feed the agents?
What was the outcome when Claude Code and Codex both ran the /goal build?
Source shelf
Use the video as a doorway, then verify with primary sources.
