I Cut My OpenCode Token Usage by 96% - Here's How

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

Source video:
- Title: I Cut My OpenCode Token Usage by 96%  - Here's How
- URL: https://www.youtube.com/watch?v=FX7jcd3GYtI
- Topic: Creative Automation
- My current learning frame: Instrument your coding agent with a proxy to capture one real request, tally tokens across system prompt, tool definitions, and your actual message, then build a minimal custom agent and measure the reduction on identical prompts.
- Why this matters: New playlist item from Adam Gardner; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 0:00 / Evidence 1: "8,000 tokens. That's what it cost me to say hello to an AI coding agent. Not write me a website or build this project, not write me a function, not refactor this code base, just hello. I'm going..."
- 3:04 / Evidence 2: "thing I typed in. Hello, that's it, two messages. But, look at the system message. It's 9 and 1/2 thousand characters. That's about 114 lines. It tells the LLM what Open Code is, how to how it should..."
- 5:42 / Evidence 3: "Come on, Adam. Open Code Chips with two default agents out of the box, build and plan. Build has everything. It all has all 11 tools. It's the all singing, all dancing. Plan does restrict some. Basically, it's..."
- 6:32 / Evidence 4: "tools, etc., etc. It's very basic. That's it. It's a description. Now, I have set the agent to primary because in open code, when you hit the tab key on your keyboard, you can tab between different agents."
- 8:56 / Evidence 5: "box agents, plan and build? Or should I just yolo it and use the build agent for everything? Or should I define a lot of smaller scoped agents, like the front-end design agent, you know, an expert at..."

Video-aware target:
- Prompt lane: Creative automation
- Mechanism to extract: Extract the creative production loop, especially where the human keeps taste, selection, and final judgment.
- Artifact to produce: A creative production board with source inputs, prompt recipe, selection criteria, edit pass, and taste-review checkpoints.
- Artifact must include: brief; source inputs; generation recipe; selection criteria; edit/review checkpoint

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: Extract the creative production loop, especially where the human keeps taste, selection, and final judgment. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A creative production board with source inputs, prompt recipe, selection criteria, edit pass, and taste-review checkpoints.
5. Include:
   - a plain-English definition of the core idea
   - a diagram or structured model using this sequence: Brief -> Source material -> Generation -> Selection -> Edit -> Taste review -> Reusable recipe
   - answers to these source questions: What asset is being produced? | What inputs and tools drive it? | Where does human taste intervene?
   - 3 concrete examples that apply the video idea to real agentic work, such as Claude-generated video campaign; image-to-site workflow; voice or video editing loop
   - 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: mistaking novelty for quality; no source/brief discipline; shipping generated media without taste review
   - a checklist for the next real workflow, focused on: brief, inputs, generation, selection, critique
   - one practical exercise with a clear done signal: Build one reusable creative recipe and define what would make the result rejectable.
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 Cut My OpenCode Token Usage by 96%  - Here's How", not a generic Creative Automation essay.
- Anchor each creative step to transcript evidence about inputs, model/tool choices, iteration, editing, or critique.
- 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 content advice; tool hype; creative output without selection criteria.
- 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.