Omnigent: The New Meta-Harness for EVERY Coding Agent - Claude Code, Codex, Pi, More
Cole Medin walks through Omni Agent, Databricks' open-source meta-harness that orchestrates Claude Code, Codex, and Pi from one session — demoing the Poly orchestrator (Claude implements, Codex reviews), custom agents with Python policy guardrails and human-in-the-loop approvals, the Debbie debate agent, and cross-device session sharing.
Cole MedinWatchTranscript found
Quick learning frame
Read this before watching.
Coding-agent workflow is the loop of inspect, plan, edit, verify, summarize, and route the next task to the right tool.
New playlist item from Cole Medin; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to run multi-assistant AI coding workflows through a meta-harness — delegating implementation and review to different harnesses and configuring custom orchestrators with executors, skills, and guardrails.
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
02Plan
03Edit
04Verify
05Review
06Route
Deep lesson
Turn this video into working knowledge.
3,141 cleaned transcript words reviewed across 866 timed caption segments.
Thesis
Omnigent: The New Meta-Harness for EVERY Coding Agent - Claude Code, Codex, Pi, More teaches a practical codex + claude workflows move: Cole Medin walks through Omni Agent, Databricks' open-source meta-harness that orchestrates Claude Code, Codex, and Pi from one session — demoing the Poly orchestrator (Claude implements, Codex reviews), custom agents with Python policy guardrails and human-in-the-loop approvals, the Debbie debate agent, and cross-device session sharing.
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.
0:44
Why meta-harnesses now
“which is more important than ever right now. An Omni agent is the layer above the AI coding assistance that makes this orchestration really straightforward. Because if we don't have a tool like this, just one session to...”
A meta-harness is the layer above AI coding assistants that lets you run longer workflows mixing tools — the classic pattern being Claude Code for implementation and Codex for review — because top engineers no longer rely on one model or harness, both to lean on different strengths and to keep separate sessions for context and token optimization; without it you juggle terminals and handoff documents. Write down your current multi-tool coding workflow, marking every point where you manually copy context or create a handoff document between assistants.
6:59
Separate implementer and reviewer
“so easily. And I know this is a pretty simple example of orchestrating a larger AI coding workflow, but it is very important, at least at a very fundamental level, to do your code review in a separate...”
With Poly as orchestrator you can say 'delegate implementation to Claude Code and review to Codex' in one request — it loads its cross-review skill, runs Claude Code as a subprocess, then hands the diff to Codex, reusing your existing CLI credentials with no re-authentication; reviewing in a separate session matters because an LLM reviewing its own implementation builds up too much bias. On your next feature, run the review in a completely separate coding-agent session (ideally a different vendor) from the one that wrote the code, and note what the fresh reviewer catches.
9:39
Anatomy of an orchestrator
“these are like just the classic skills that we have with claude codeex every AI coding assistant. This is the workflow that it can walk itself through. And then each of the individual agents has the exact same...”
Every Omni Agent orchestrator has three parts — configuration, skills, and the agents it can call — where the config sets the executor model, system prompt, sandboxing (none, Docker, or E2B), tools, and guardrails, including human-in-the-loop policies written as Python that live next to the config, e.g. requiring approval for any git push using the force flag. Have your coding assistant draft a custom agent config modeled on Poly with one guardrail policy that forces human approval on a dangerous command you care about.
01
Inspect
Start with this video's job: Cole Medin walks through Omni Agent, Databricks' open-source meta-harness that orchestrates Claude Code, Codex, and Pi from one session — demoing the Poly orchestrator (Claude implements, Codex reviews), custom agents with Python policy guardrails and human-in-the-loop approvals, the Debbie debate agent, and cross-device session sharing. Treat "Inspect" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:44, where the video says: “which is more important than ever right now. An Omni agent is the layer above the AI coding assistance that makes this orchestration really straightforward. Because if we don't have a tool like this, just one session to...”
02
Plan
Use "Plan" to locate the part of the codex + claude workflows workflow the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 6:59, where the video says: “so easily. And I know this is a pretty simple example of orchestrating a larger AI coding workflow, but it is very important, at least at a very fundamental level, to do your code review in a separate...”
03
Edit
Turn "Edit" into the reusable artifact for this lesson: A routing matrix for when to use Codex, Claude, browser checks, or manual review. This is where watching becomes something you can inspect and reuse.
04
Verify
Use "Verify" 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
Review
Use "Review" 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
Route
Use "Route" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.
Example
Source-backed work packet
Convert the video into a scoped task that includes the transcript claim, target workflow, acceptance criteria, and proof. The output should be a routing matrix for when to use codex, claude, browser checks, or manual review..
Example
Claim vs. demo brief
Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the workflow.
Example
Teach-back module
Transform the lesson into a definition, a mechanism 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.
Letting the prompt drift into generic advice that could apply to any video in the playlist.
Copying the tool setup without identifying the operating principle that transfers to your own stack.
Skipping the artifact, which means the learning never becomes operational or inspectable.
Do not count this as learned until these are true.
01
State the transcript-backed claim in your own words: Cole Medin walks through Omni Agent, Databricks' open-source meta-harness that orchestrates Claude Code, Codex, and Pi from one session — demoing the Poly orchestrator (Claude implements, Codex reviews), custom agents with Python policy guardrails and human-in-the-loop approvals, the Debbie debate agent, and cross-device session sharing.
02
Explain the practical stakes without hype: New playlist item from Cole Medin; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Inspect -> Plan -> Edit -> Verify -> Review -> Route sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A routing matrix for when to use Codex, Claude, browser checks, or manual review.
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: Omnigent: The New Meta-Harness for EVERY Coding Agent - Claude Code, Codex, Pi, More
- URL: https://www.youtube.com/watch?v=oGE_Dwz-rMk
- Topic: Codex + Claude Workflows
- My current learning frame: Set up Omni Agent with the one-command install, run Poly on a small real task with implementation delegated to Claude Code and review to Codex, then add a custom Python guardrail that makes force-pushes require your approval.
- Why this matters: New playlist item from Cole Medin; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:44 / Evidence 1: "which is more important than ever right now. An Omni agent is the layer above the AI coding assistance that makes this orchestration really straightforward. Because if we don't have a tool like this, just one session to..."
- 2:19 / Evidence 2: "orchestrates many AI coding assistants working together on larger tasks? That's exactly what a metah harness is. I'm building something kind of around meta harness engineering with archon. And there's actually a lot of ideas from Omni Agent..."
- 5:11 / Evidence 3: "you'll have a web UI that looks like this. It's nice, simple, and elegant. It reminds me a lot of the codeex app. So it's just agent first. You have your chat session here and you tell it..."
- 6:59 / Evidence 4: "so easily. And I know this is a pretty simple example of orchestrating a larger AI coding workflow, but it is very important, at least at a very fundamental level, to do your code review in a separate..."
- 9:39 / Evidence 5: "these are like just the classic skills that we have with claude codeex every AI coding assistant. This is the workflow that it can walk itself through. And then each of the individual agents has the exact same..."
- 11:25 / Evidence 6: "workspace. We can see the agents that we're using if we're orchestrating many of them. It's really neat the the UX and the UI that we have here in the platform. And here you can see that I..."
- 13:00 / Evidence 7: "the kinds of ways that you can build these larger workflows, combining coding agents when it becomes so incredibly easy to do so, even setting up your own custom orchestrators like I showed earlier. All right. So, at..."
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, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable claims from the video. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A routing matrix for when to use Codex, Claude, browser checks, or manual review.
5. Include:
- a plain-English definition of the core idea
- a diagram or structured model using this sequence: Inspect -> Plan -> Edit -> Verify -> Review -> Route
- 3 concrete examples that apply the video idea to real agentic work
- 2 failure modes the video helps prevent
- a checklist I can use the next time I run Codex or Claude
- one practical exercise with a clear done signal
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 "Omnigent: The New Meta-Harness for EVERY Coding Agent - Claude Code, Codex, Pi, More", not a generic Codex + Claude Workflows essay.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- If evidence is weak, 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.
One agent should do every task.
Different tools have different strengths. Routing is part of the workflow.
More context is always better.
Relevant context helps; stale context causes drift and cost.
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 routing matrix for when to use codex, claude, browser checks, or manual review..
A reusable artifact with a done signal and one verification step.03
Teach-back card
Explain the lesson 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 problem does a meta-harness solve that using multiple coding assistants directly does not?
In the Poly demo, why does the video argue code review should happen in a separate coding-agent session from implementation?
What are the three parts of an Omni Agent orchestrator, and how are guardrail policies implemented?
Source shelf
Use the video as a doorway, then verify with primary sources.
