This video walks through a complete AI-driven GitHub workflow where coding agents like Codex and Claude Code drive the GitHub CLI (gh) to create a repo, set up a Kanban project board, write a spec, break it into tickets, open and review pull requests, address automated code-review comments, merge, and finally build a GitHub Actions release pipeline that cross-compiles binaries and generates release notes.
Owain Lewis17 minTranscript found
Quick learning frame
Read this before watching.
Agent ops treats agents like services: observable state, queues, permissions, logs, recovery, and post-run review.
New playlist item from Owain Lewis; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to give AI coding agents the GitHub CLI as a tool and run a repeatable, auditable development workflow end to end — from repo and ticket creation through PR review and an automated release pipeline — instead of having the agent only write code.
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.
01Project state
02Session
03Queue/Kanban
04Tools
05Logs
06Recovery
07Post-run review
Deep lesson
Turn this video into working knowledge.
3,795 cleaned transcript words reviewed across 1,098 timed caption segments.
Thesis
My GitHub AI Workflow: Codex + Claude Code teaches a practical hermes operations move: This video walks through a complete AI-driven GitHub workflow where coding agents like Codex and Claude Code drive the GitHub CLI (gh) to create a repo, set up a Kanban project board, write a spec, break it into tickets, open and review pull requests, address automated code-review comments, merge, and finally build a GitHub Actions release pipeline that cross-compiles binaries and generates release notes.
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.
1:14
gh CLI as agent tool
“to collaborate with other people, to do code review, to do pretty much everything you need to do within your development workflow. So, the first thing we need to do in order to give our AI agents access...”
Installing and authenticating the GitHub CLI (brew install gh, gh auth login) gives agents a single tool to manage everything in GitHub; the agent figures out on its own that gh is available and uses it to create a public repo initialized with a README, a Go .gitignore, and a description — no manual setup. Install gh, run gh auth login, then prompt your agent to create a public repo initialized with a README and language-specific .gitignore without telling it which tool to use, and confirm it reaches for gh on its own.
7:18
Tickets over markdown
“any further issues. If you're using GitHub, there are a bunch of tools you can use for code review. For example, you can use Copilot, so we can go ahead and request a review, which might be nice.”
Rather than tracking work in local markdown files (which gets chaotic fast), the agent writes a spec by searching the target codebase's API, breaks it into ~10 tickets pushed to a linked GitHub project board, and updates each ticket's status as it works — giving a high-level overview and enabling multiple agents in parallel; an implementation skill also forces a self-review that catches a bug before the PR is opened. Have your agent create a GitHub project board, generate a spec from an existing API, and break it into linked tickets, then add a self-review step to your agent's instructions and watch whether it catches an issue before opening the PR.
12:12
Automated release pipeline
“archive. Okay, so now we're just going to go ahead and build out this task. So, what you'll notice here is we're not just using AI agents anymore for writing code. We're using AI agents to write the...”
The agent authors a GitHub Actions release.yaml that triggers on a version tag to check out code, build binaries for multiple operating systems, name them clearly, archive them (a .gz/archive design choice made mid-flow), generate release notes, and create a GitHub release — collapsing hours of tedious YAML and build configuration into minutes. Pick a small CLI of your own and prompt the agent to write a tag-triggered GitHub Actions workflow that cross-compiles binaries, archives them, generates release notes, and publishes a release, then tag a v1 and verify the release artifacts appear.
01
Project state
Start with this video's job: This video walks through a complete AI-driven GitHub workflow where coding agents like Codex and Claude Code drive the GitHub CLI (gh) to create a repo, set up a Kanban project board, write a spec, break it into tickets, open and review pull requests, address automated code-review comments, merge, and finally build a GitHub Actions release pipeline that cross-compiles binaries and generates release notes. Treat "Project state" as the outcome you are trying to make visible, not a topic label. Anchor it to 1:14, where the video says: “to collaborate with other people, to do code review, to do pretty much everything you need to do within your development workflow. So, the first thing we need to do in order to give our AI agents access...”
02
Session
Use "Session" to locate the part of the hermes operations mechanism the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 7:18, where the video says: “any further issues. If you're using GitHub, there are a bunch of tools you can use for code review. For example, you can use Copilot, so we can go ahead and request a review, which might be nice.”
03
Queue/Kanban
Turn "Queue/Kanban" into the reusable artifact for this lesson: A Hermes-style agent-ops runbook with health checks, state transitions, logs, recovery steps, and review criteria. This is where watching becomes something you can inspect and reuse.
04
Tools
Use "Tools" 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
Logs
Use "Logs" 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
Recovery
Use "Recovery" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.
07
Post-run review
Connect "Post-run review" to My GitHub AI Workflow: Codex + Claude Code by naming the claim, the evidence, and the artifact it should produce.
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 hermes-style agent-ops runbook with health checks, state transitions, logs, recovery steps, and review criteria..
Example
Hermes operations proof brief
Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the hermes operations pattern.
Example
Teach-back module
Transform the lesson into a definition, a Project state -> Session -> Queue/Kanban -> Tools -> Logs -> Recovery -> Post-run review 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.
treating UI features as reliability
missing logs
no stop/recover path
Letting the lesson drift into feature cheerleading.
Letting the lesson drift into ops advice without logs/state.
Letting the lesson drift into assuming reliability from a demo alone.
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 complete AI-driven GitHub workflow where coding agents like Codex and Claude Code drive the GitHub CLI (gh) to create a repo, set up a Kanban project board, write a spec, break it into tickets, open and review pull requests, address automated code-review comments, merge, and finally build a GitHub Actions release pipeline that cross-compiles binaries and generates release notes.
02
Explain the practical stakes without hype: New playlist item from Owain Lewis; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Project state -> Session -> Queue/Kanban -> Tools -> Logs -> Recovery -> Post-run review sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A Hermes-style agent-ops runbook with health checks, state transitions, logs, recovery steps, and review criteria.
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: My GitHub AI Workflow: Codex + Claude Code
- URL: https://www.youtube.com/watch?v=zdeZGePZMuE
- Topic: Creative Automation
- My current learning frame: Build a tiny CLI tool end to end with an agent driving the gh CLI: create the repo and a linked project board, generate and ticket a spec, ship the first ticket through a reviewed pull request, then add a tag-triggered GitHub Actions pipeline that builds binaries and publishes a release.
- Why this matters: New playlist item from Owain Lewis; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 1:14 / Evidence 1: "to collaborate with other people, to do code review, to do pretty much everything you need to do within your development workflow. So, the first thing we need to do in order to give our AI agents access..."
- 4:20 / Evidence 2: "tasks that we can then store on our project board. Can you go ahead and create a specification to help me build a Go lang CLI tool? This is going to be a single binary install that allows..."
- 7:18 / Evidence 3: "any further issues. If you're using GitHub, there are a bunch of tools you can use for code review. For example, you can use Copilot, so we can go ahead and request a review, which might be nice."
- 9:13 / Evidence 4: "the entire workflow. So, what you can see now is not only has the agent fixed the issues that were identified in the code review, it's also added a comment below. So, you can see here, this was..."
- 12:12 / Evidence 5: "archive. Okay, so now we're just going to go ahead and build out this task. So, what you'll notice here is we're not just using AI agents anymore for writing code. We're using AI agents to write the..."
- 14:41 / Evidence 6: ">> >> to addressing code review feedback to even building an end-to-end release pipeline that is fully automated. >> >> I've worked as a software engineer for a long time, but I'm still absolutely blown away by how..."
- 16:14 / Evidence 7: "give your AI agents the right tools, and let the AI agents run your pipeline. This is where the real leverage is going to come with these agents. It's not going to come from just writing code. It's..."
Video-aware target:
- Prompt lane: Hermes operations
- Mechanism to extract: Identify the operations control that makes long-running agent work visible, recoverable, or safer.
- Artifact to produce: A Hermes-style agent-ops runbook with health checks, state transitions, logs, recovery steps, and review criteria.
- Artifact must include: health check; state model; permission boundary; log source; recovery action
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: Identify the operations control that makes long-running agent work visible, recoverable, or safer. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A Hermes-style agent-ops runbook with health checks, state transitions, logs, recovery steps, and review criteria.
5. Include:
- a plain-English definition of the core idea
- a diagram or structured model using this sequence: Project state -> Session -> Queue/Kanban -> Tools -> Logs -> Recovery -> Post-run review
- answers to these source questions: What operational failure is prevented? | What state is visible? | What can be recovered or redirected?
- 3 concrete examples that apply the video idea to real agentic work, such as Hermes Kanban triage; local model endpoint check; agent swarm recovery review
- 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: treating UI features as reliability; missing logs; no stop/recover path
- a checklist for the next real workflow, focused on: status, model/backend, tools, logs, recovery
- one practical exercise with a clear done signal: Write a runbook for restarting one stuck Hermes-style agent session.
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 "My GitHub AI Workflow: Codex + Claude Code", not a generic Creative Automation essay.
- Ground each ops recommendation in transcript evidence about state, queues, models, tools, security, logs, or recovery.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- Avoid these generic drifts: feature cheerleading; ops advice without logs/state; assuming reliability from a demo alone.
- 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 hermes-style agent-ops runbook with health checks, state transitions, logs, recovery steps, and review criteria..
A reusable artifact with a done signal and one verification step.03
Hermes operations teach-back card
Explain the hermes operations 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 is the video asking you to understand?
What makes this lesson trustworthy?
What should you make after watching?
Source shelf
Use the video as a doorway, then verify with primary sources.
