I Hit My Claude Code Limit and Tried Codex

You are helping me turn one specific YouTube video into real, durable learning.

Source video:
- Title: I Hit My Claude Code Limit and Tried Codex
- URL: https://www.youtube.com/watch?v=N0hLmUc3jUs
- Topic: Codex + Claude Workflows
- My current learning frame: Take a repo you currently drive with Claude Code, create an AGENTS.md symlinked to CLAUDE.md, install a skill with the Vercel `npx skills add` CLI for both agents, then run the same review-and-build task in Codex at two reasoning levels to document the behavioral differences yourself.
- Why this matters: This maps directly to a practical dual-agent operating model instead of forcing every task through one tool.

Transcript anchors from this exact video:
- 0:00 / Evidence 1: "A couple weeks ago I hit my weekly limit on my Cloud Code Max plan with 3 days left in the week. So, I decided to take this as an opportunity to try out Codex. And today I..."
- 3:54 / Evidence 2: "potentially move to something like Codex instead. Now, one of the first things that you need to think about is if you've already been using something like Claude Code instead, then getting some of the conventions over to..."
- 5:44 / Evidence 3: "it, um and things like that. One of the other common configuration points is going to be agent skills. So, with Claude Code, it looks for skills in the .claude/skills folder. In the case of something like Codex,..."
- 7:41 / Evidence 4: "And if we look inside of agent skills, now we have the TDD workflow. And then the other thing, if we look inside of Claude skills, that it is there as well. And so that Claude we take..."
- 10:45 / Evidence 5: "This is like a built-in Ralph Wiggum loop for using Codex. So, if you're not familiar with the Ralph Wiggum loop, it's essentially a way to autonomously let the Codex agent just work through a complicated problem on..."
- 12:26 / Evidence 6: "I feel like it's been a little bit limited in configuring how it operates and things like that. And it doesn't have all of the work streams that Codex has. So, there's linear, which has linear agents, where..."
- 13:56 / Evidence 7: "using Codex instead of Cloud Code. And if you have any questions, I'm curious if you started using Codex, or are you using any other tools, or are you primarily using Cloud Code? Leave a comment and let..."

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 "I Hit My Claude Code Limit and Tried Codex", not a generic Codex + Claude Workflows 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.