brief-landing-pagelisted

# Landing Page Brief — Orchestrator Coordinates evidence anchoring, hypothesis generation, architecture, per-section spec, asset slotting, conversion gating, and hand-off prompt composition into a single approved brief. Capability metadata (routes, prerequisites, load map, artifact contract) lives in [`routing.yaml`](routing.yaml). Agent table + 3 routes + 3 Approval Gates + critic verdict logic: [`references/agent-manifest.md`](references/agent-manifest.md). Methodology: [`references/playbook.md`](references/playbook.md). **Core question:** Could a designer (or Claude Design) build the right page from this brief without a single follow-up question? ## Critical Gates — load first - **No brief without brand artifacts.** Missing `brand/BRAND.md` or `brand/DESIGN.md` → return `NEEDS_CONTEXT`. Brief depends on tokens, voice rules, sacred elements. - **Conversion rubric is mandatory.** Every section spec is gated by `references/conversion-principles.md` CP-01 → CP-13. Brand-good but conversion-bad = failure. - **Sacred elements are rails, not options.** Logo geometry, primary palette anchor, tagline wording, signature treatments are "do not touch." - **Envelope: 250-500 lines.** <250 = insufficient depth (designer asks follow-ups). >500 = bloat (designer skims). Brand-voice critic G6 FAILs both directions. - **Don't inline the shared skill chain.** Reference by section header; add page-specific overrides only. - **No placeholder testimonials, fake logos, or pretend numbers.**