This video walks through a homemade 'AgentOS' where a single chat agent (the author runs Fable) acts as a chief-of-staff that never writes code itself, delegating all implementation to Codex app server while cron-triggered watcher agents, Notion task tracking, and hooks keep work moving and flag blockers automatically.
Nath Aston32 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 Nath Aston; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to design a multi-agent orchestration layer that separates planning/communication (a chief-of-staff agent) from implementation (a delegate agent), using watchers, hooks, and a lightweight task/decision log to keep autonomous work unblocked without constant supervision.
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.
5,745 cleaned transcript words reviewed across 1,711 timed caption segments.
Thesis
Building my own AgentOS Workspace teaches a practical coding-agent workflow move: This video walks through a homemade 'AgentOS' where a single chat agent (the author runs Fable) acts as a chief-of-staff that never writes code itself, delegating all implementation to Codex app server while cron-triggered watcher agents, Notion task tracking, and hooks keep work moving and flag blockers automatically.
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.
0:22
Chief of staff, not builder
“the the agent that I use is like the central orchestration agent. It is Fable and I'm managing all of my tasks from within notion but you could do it from you know, I previously worked from linear.”
The main chat agent (Fable) never does implementation work itself; it only plans, clarifies scope, and offloads every task to Codex app server, because the author finds it easier to communicate with Fable than to work directly with GPT 5.6 Sol despite Sol doing the actual coding. Write down one recurring task where you currently mix planning and doing in the same chat, and sketch how you'd split it into a planning agent and a separate implementation agent.
9:57
Watchers, hooks, decisions log
“open source this um system just for for you to go and like build on top of. It may not even need to be open source, but and you can just like I don't know, copy this video...”
A cron-triggered worker checks Codex chats every 20 minutes for blocked or stalled work and reports back to the orchestrator; turn-end and session-start hooks update Notion task status automatically; and a lean decisions.md folder captures any preference or architecture call that isn't obvious from the code, so agents can check it before escalating. Create a single small decisions.md (or equivalent) file in one active project and log the next non-obvious architecture or preference decision you make there instead of only saying it out loud.
21:09
Adversarial audit + proactive push
“agents could default into using superpowers. And on some of the work that I do and so it would try to like build everything and superpowers is in itself a bit of a like I love it. It's...”
A 'build' skill wraps a brainstorming/spec workflow with an adversarial audit loop where a GPT 5.6 Sol agent and an Opus 5 agent independently critique the plan for gaps and risky behavior before the orchestrator brings findings back to the human, and in live use the system proactively finds and unblocks the highest-priority Notion task without being prompted. Pick one plan you're about to implement and have two independent agents (or reviewers) separately critique it for gaps before you execute, then compare their findings.
01
Inspect context
Start with this video's job: This video walks through a homemade 'AgentOS' where a single chat agent (the author runs Fable) acts as a chief-of-staff that never writes code itself, delegating all implementation to Codex app server while cron-triggered watcher agents, Notion task tracking, and hooks keep work moving and flag blockers automatically. Treat "Inspect context" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:22, where the video says: “the the agent that I use is like the central orchestration agent. It is Fable and I'm managing all of my tasks from within notion but you could do it from you know, I previously worked from linear.”
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 9:57, where the video says: “open source this um system just for for you to go and like build on top of. It may not even need to be open source, but and you can just like I don't know, copy this video...”
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: This video walks through a homemade 'AgentOS' where a single chat agent (the author runs Fable) acts as a chief-of-staff that never writes code itself, delegating all implementation to Codex app server while cron-triggered watcher agents, Notion task tracking, and hooks keep work moving and flag blockers automatically.
02
Explain the practical stakes without hype: New playlist item from Nath Aston; 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: Building my own AgentOS Workspace
- URL: https://www.youtube.com/watch?v=wMUkg2Yng6I
- Topic: Interfaces + Open Design
- My current learning frame: Set up a minimal version of this system: one planning agent, one implementation agent, a task tracker with a status field, and a single decisions log file, then run one real task through the full loop from plan to delegated implementation to status update.
- Why this matters: New playlist item from Nath Aston; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:22 / Evidence 1: "the the agent that I use is like the central orchestration agent. It is Fable and I'm managing all of my tasks from within notion but you could do it from you know, I previously worked from linear."
- 2:18 / Evidence 2: "to Codex app server. The reason I built this system is I really hate speaking to 5.6 soul. I in all honesty just find it really difficult to work with. The outcomes are good, but the just the..."
- 3:50 / Evidence 3: "that triggers a Claude agent. It's not using Fable. I think it was either Sonnet or maybe Haiku, actually. And it lists our recent chats in in Codex, and it just makes sure that nothing's blocked, that nothing..."
- 9:57 / Evidence 4: "open source this um system just for for you to go and like build on top of. It may not even need to be open source, but and you can just like I don't know, copy this video..."
- 13:30 / Evidence 5: "you know, drinking coffee, like what whatever I'm doing. The work isn't blocked. This is just acting as like a watcher, as a manager of all of my Codex chats, of all of my Codex sessions. Um or..."
- 16:01 / Evidence 6: "that like just little tools that I kind of build for myself. So, projects.json just contains every project. It It tells Claude if it's local only, as in doesn't need to deploy on GitHub, doesn't need to use..."
- 21:09 / Evidence 7: "agents could default into using superpowers. And on some of the work that I do and so it would try to like build everything and superpowers is in itself a bit of a like I love it. It's..."
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 "Building my own AgentOS Workspace", 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 — without rewatching.
Why does the author route all implementation work to Codex app server instead of having Fable do it directly?
What is decisions.md used for and why does the author keep it small?
How does the adversarial audit loop in the build skill work?
Source shelf
Use the video as a doorway, then verify with primary sources.
