PLANS For Fable 5: Rebuilding My /Plan Skill for Mythos Class Models
A deep agentic-engineering vlog rebuilding a reusable /plan 'meta skill' (a prompt that outputs plans) for state-of-the-art Mythos-class models, arguing that great planning is great engineering and upgrading the plan template to an HTML format with generated images so agents get more valuable tokens to work with.
IndyDevDan63 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 IndyDevDan; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to write and iterate your own reusable planning meta skill with an explicit plan template so agents produce the exact outcomes you specify instead of guessing.
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.
12,575 cleaned transcript words reviewed across 3,791 timed caption segments.
Thesis
PLANS For Fable 5: Rebuilding My /Plan Skill for Mythos Class Models teaches a practical coding-agent workflow move: A deep agentic-engineering vlog rebuilding a reusable /plan 'meta skill' (a prompt that outputs plans) for state-of-the-art Mythos-class models, arguing that great planning is great engineering and upgrading the plan template to an HTML format with generated images so agents get more valuable tokens to work with.
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.
0:18
Own your planning
“cares about the plan skill? Why is planning so important? Your planning skill is one of the most important tools you and your agent have. Most engineers hand this off to the model, they hand it off to...”
Most engineers hand planning off to the model's built-in /plan, which forces the model to guess what you want; the argument is you should write your own planning skill, prompt, and template because great planning is great engineering, more upfront planning investment means less reviewing, and this only compounds as model capability rises. Open a raw.md and just write out, in your own words, why and what you're planning for a real task before letting any agent touch it, to serve as context for both you and the agent.
29:31
Property-based engineering
“variable here. This is looking pretty good. I will pull the workflow just to give our agent a starting place here. Analyze the requirements, parse the user prompt to understand the core problem, desired outcome, explore the code...”
He does 'property-based engineering', starting from priorities (the trade-off trifecta of performance > speed >= cost, sacrificing speed and cost to win) and building a plan format the model must fill in while leaving non-templated sections untouched, with phases each containing a problem/solution, relevant files, tasks, and specific validation commands to prove the phase is complete. Draft a reusable plan template with named phases where each phase lists the problem, the files touched, and the exact commands that validate it's done, and reuse it on your next task.
51:04
HTML and image specs
“use PyCroco for research. It is pulling in the Py versus Claude code base, and this is publicly available, of course, on my GitHub repository. This is a public code base available to anyone, and it contains several...”
The key Mythos-class upgrade is outputting the plan in HTML rather than plain text because, per an Anthropic write-up he cites, more valuable tokens give agents a slight edge on producing the result you want; he also generates images (via a GPT image model script) so both humans and multimodal agents ingest the plan deeper, accepting the higher token cost knowingly, run on Opus 4.8 at high effort. Convert one of your plan templates into an HTML format and add a generated diagram or image, then compare whether the agent's output tracks your intent better than the plain-text version.
01
Inspect context
Start with this video's job: A deep agentic-engineering vlog rebuilding a reusable /plan 'meta skill' (a prompt that outputs plans) for state-of-the-art Mythos-class models, arguing that great planning is great engineering and upgrading the plan template to an HTML format with generated images so agents get more valuable tokens to work with. Treat "Inspect context" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:18, where the video says: “cares about the plan skill? Why is planning so important? Your planning skill is one of the most important tools you and your agent have. Most engineers hand this off to the model, they hand it off to...”
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 29:31, where the video says: “variable here. This is looking pretty good. I will pull the workflow just to give our agent a starting place here. Analyze the requirements, parse the user prompt to understand the core problem, desired outcome, explore the code...”
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: A deep agentic-engineering vlog rebuilding a reusable /plan 'meta skill' (a prompt that outputs plans) for state-of-the-art Mythos-class models, arguing that great planning is great engineering and upgrading the plan template to an HTML format with generated images so agents get more valuable tokens to work with.
02
Explain the practical stakes without hype: New playlist item from IndyDevDan; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Brief -> Source material -> Generation -> Selection -> Edit -> Taste review -> Reusable recipe sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A creative production board with source inputs, prompt recipe, selection criteria, edit pass, and taste-review checkpoints.
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: PLANS For Fable 5: Rebuilding My /Plan Skill for Mythos Class Models
- URL: https://www.youtube.com/watch?v=DzbqeO_diOQ
- Topic: Creative Automation
- My current learning frame: Write a raw.md rationale and priorities, build a reusable HTML plan-template meta skill with phased problem/solution/validation-command sections, then run it against a real feature spec on a capable model and judge whether the output matches your intended outcome.
- Why this matters: New playlist item from IndyDevDan; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:18 / Evidence 1: "cares about the plan skill? Why is planning so important? Your planning skill is one of the most important tools you and your agent have. Most engineers hand this off to the model, they hand it off to..."
- 6:34 / Evidence 2: "when you ask them the right way, only when you present them with the right information. So this is our API. We're going to run any coding agent. I like to use the PyCoding agent, and I like..."
- 20:14 / Evidence 3: "With these powerful models, this is unnecessary, but I'm doing this not just for the agents, I'm doing it for my team and myself. So, that's the purpose of this. Create a detailed implementation plan based on the..."
- 29:31 / Evidence 4: "variable here. This is looking pretty good. I will pull the workflow just to give our agent a starting place here. Analyze the requirements, parse the user prompt to understand the core problem, desired outcome, explore the code..."
- 31:33 / Evidence 5: "right? That's the whole idea. So, we're just using some really basic agent of coding. We could pretty much throw any model we want to at but for now, we're just going to keep it simple. We're going..."
- 51:04 / Evidence 6: "use PyCroco for research. It is pulling in the Py versus Claude code base, and this is publicly available, of course, on my GitHub repository. This is a public code base available to anyone, and it contains several..."
- 61:56 / Evidence 7: "places to spend time to increase our ability to move at the agentic speed while building out very, very valuable, very hand-picked, hand-structured, heavily engineered foundations and fabrics and meta skills and meta prompts for our agents to..."
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 "PLANS For Fable 5: Rebuilding My /Plan Skill for Mythos Class Models", 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.
Why does the presenter argue you should write your own planning skill instead of using the model's built-in /plan?
What is the trade-off trifecta and how does the new plan template prioritize it?
Why does he switch the plan format to HTML and add generated images?
Source shelf
Use the video as a doorway, then verify with primary sources.
