One Folder Runs Claude, Gemini, Codex, and even Obsidian (Free on GitHub)
Use a plain-markdown personal knowledge architecture as the handoff layer between Claude, Gemini, Codex, Obsidian, and other tools so project memory stays portable.
ICOR with Tom | AI Productivity35 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.
This reinforces the atlas pattern of durable artifacts: folders, notes, and conventions that survive tool switching.
Skill you build: The ability to run a single LLM-agnostic local folder as your knowledge assistant, using an index-driven agent team and session logs instead of vendor auto-memory to control persistent context.
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.
6,503 cleaned transcript words reviewed across 1,802 timed caption segments.
Thesis
One Folder Runs Claude, Gemini, Codex, and even Obsidian (Free on GitHub) teaches a practical coding-agent workflow move: Use a plain-markdown personal knowledge architecture as the handoff layer between Claude, Gemini, Codex, Obsidian, and other tools so project memory stays portable.
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.
0:28
LLM-independent folder
“video, I show you proof that no matter if you're using Claude, Codeex, or Gemini, or any other local LLM, if you might need it, as some have some security worries, they rather want to use a local...”
The folder is built from the ground up independent of any LLM, using markdown that Obsidian can visualize; three core agents live in it, Larry the orchestrator who reads the agent index and routes work, Nolan who hires new agents when expertise is missing, and Pax the researcher who finds the best profile to build. Sketch a folder with an agent index and the three roles (orchestrator, hirer, researcher) and write one sentence describing what each routes or produces.
17:28
One folder, any agent
“of the box. So here you see how things are connected. The different agents agents index that just visualizes the context in this folder. But here we go. There's Dr. Schmidt and he's connected with the clinic which...”
The same folder works when opened with Claude Cowork, Claude in the terminal, Codex (which reads agents.md so needs no big init), or Gemini (which creates a Gemini.md); each just says 'who are you?' or 'init' and initializes as Larry by reading the interconnected files, and you can point all of them at one folder. Open one prepared folder in two different agents (e.g., Claude and one other) and confirm both initialize from the same files without custom prompts.
25:29
Session logs beat auto-memory
“what was going on. And this is much better than the automemory that is just random and never so comprehensive and context connected than building it this way. Now you see for the other two agents they launched.”
Turn off auto-memory (via /memory) because it randomly grabs what the AI thinks is useful and locks you into one vendor; instead, saying 'close the session' or 'keep this in mind' writes markdown session logs into team knowledge, giving comprehensive, context-connected, reviewable permanent memory you can look back through in time. Disable auto-memory in your agent, then end a working session with 'close the session' and read the generated session-log markdown to see what was captured.
01
Inspect context
Start with this video's job: Use a plain-markdown personal knowledge architecture as the handoff layer between Claude, Gemini, Codex, Obsidian, and other tools so project memory stays portable. Treat "Inspect context" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:28, where the video says: “video, I show you proof that no matter if you're using Claude, Codeex, or Gemini, or any other local LLM, if you might need it, as some have some security worries, they rather want to use a local...”
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 17:28, where the video says: “of the box. So here you see how things are connected. The different agents agents index that just visualizes the context in this folder. But here we go. There's Dr. Schmidt and he's connected with the clinic which...”
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: Use a plain-markdown personal knowledge architecture as the handoff layer between Claude, Gemini, Codex, Obsidian, and other tools so project memory stays portable.
02
Explain the practical stakes without hype: This reinforces the atlas pattern of durable artifacts: folders, notes, and conventions that survive tool switching.
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: One Folder Runs Claude, Gemini, Codex, and even Obsidian (Free on GitHub)
- URL: https://www.youtube.com/watch?v=4C2w8eIG48A
- Topic: AI Strategy
- My current learning frame: Download the free folder scaffold, open it in your chosen agent and say 'init', hand it a screenshot or note to auto-file and cross-link via wiki links, then close the session to generate a session log and confirm it works across a second agent.
- Why this matters: This reinforces the atlas pattern of durable artifacts: folders, notes, and conventions that survive tool switching.
Transcript anchors from this exact video:
- 0:28 / Evidence 1: "video, I show you proof that no matter if you're using Claude, Codeex, or Gemini, or any other local LLM, if you might need it, as some have some security worries, they rather want to use a local..."
- 3:09 / Evidence 2: "somebody. And Pax, the third agent in this constellation is the researcher. So Nolan will ask Pax to go online and research about the best front-end developer to build this or the best journal writer or the best..."
- 8:55 / Evidence 3: "information. This is not task management or project management. We say here there are projects habits that sounds like action but in the end it's the information about these action items. And yet you need to organize these..."
- 11:57 / Evidence 4: "does it just tells any LLM to initiate itself inside this folder but keep things very simplistic and rather forward and reference these agent MD files instead of creating custom skills. So you might have seen endless videos..."
- 17:28 / Evidence 5: "of the box. So here you see how things are connected. The different agents agents index that just visualizes the context in this folder. But here we go. There's Dr. Schmidt and he's connected with the clinic which..."
- 19:15 / Evidence 6: "describing the process map how the agents work. So do you need to create these files? No, because this is what Larry will do and the combination of Nolan who is hiring the agents and creates this skill..."
- 25:29 / Evidence 7: "what was going on. And this is much better than the automemory that is just random and never so comprehensive and context connected than building it this way. Now you see for the other two agents they launched."
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 "One Folder Runs Claude, Gemini, Codex, and even Obsidian (Free on GitHub)", not a generic AI Strategy 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.
Every new AI tool deserves a trial.
Every tool has integration cost. Start from workflow pain, not novelty.
If an agent can do it once, it is automated.
Automation means repeatable, monitored, recoverable, and reviewable.
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.
What are the three core agents in the local folder and what does each do?
Why does the presenter say the folder is LLM-independent, and how do different agents initialize in it?
Why does the presenter turn off LLM auto-memory, and what does he use instead?
Source shelf
Use the video as a doorway, then verify with primary sources.
