Reference Decode

• postplus-shared

  release-shell rules

• breaking a good reference into reusable logic
• separating what should be copied from what must not be copied
• turning vague ideas into promptable structure
• creating a stable handoff for storyboard or provider request work

Core Rule

1. hookEssence

2. viewerQuestion

3. mustCopyVisualGrammar

4. forbiddenDrift

Default Workflow

1. Load the smallest sufficient reference set

1. hook-first clip or first 0-5 seconds
2. hook-first contact sheet
3. supporting benchmark note
4. full-video style board only if hook-first material is insufficient

2. Decode the opening mechanism

• what is the first clear promise?
• what question enters the viewer's head?
• what exact visual structure makes that promise legible?

3. Separate structure from identity

• camera grammar
• shot order
• visible object logic
• timing logic
• relationship logic

• exact faces
• exact wardrobe
• creator identity
• exact text overlay
• exact location

4. Print the decode block before writing prompts

references/output-shape.md

5. Hand off cleanly

• if the target is a grid, hand off to

  storyboard-grid-writer

• if the target is a full render request, hand off to

  video-request-architect

• if references should be explicitly bounded, hand off to

  reference-contract-builder

No-Reference Rule

• start from the chosen segment pattern
• infer the likely viewer question
• write must-copy grammar as required scene anchors, not as imitation notes
• write forbidden drift as anti-generic safeguards

Failure Mode

• what the opening promise is
• what the viewer should notice first
• what the scene must visibly contain