# Agent Brief. build in the style of coverfairy.com

> Machine-extracted from a live on-demand funnel teardown (2026-07-27). 100% facts —
> measured tokens, detected patterns, harvested proof strings. No LLM interpretation.
> Single-page capture (MVP): homepage/landing page only, no funnel walk.
> Tokens: `tokens.json` / `tailwind.css`.

**Category (label):** —
**Funnel:** Homepage / Lander → Features → Pricing → Compare

## Palette (area-weighted from live CSS)
| Hex | Usage | Likely role |
|-----|------:|-------------|
| `#ffffff` | 37% | background |
| `#f4f5f3` | 15.3% | background |
| `#25211f` | 12.7% | support |
| `#171816` | 10.8% | support |
| `#e8ebe8` | 8% | background |
| `#e9ece9` | 4.6% | background |
| `#f6f5f1` | 4.2% | background |
| `#e2e6e2` | 1.8% | background |

Curated roles: `primary=#25211f` · `accent=#25211f` · `bg=#ffffff` · `surface=#f4f5f3` · `text=#171816`

## Type
- Display: `Newsreader`
- Body: `DM Sans`
- Size scale (px): 12, 13, 14, 15, 16, 18, 20, 27, 28, 29, 34, 38
- Radius (px): 6, 8, 9, 18, 50, 999

## Patterns detected (fact-based). 3/15
- **On-page review wall**. An embedded wall of customer reviews. _(home: 10 star glyphs)_
- **FAQ / objection handling**. An accordion / FAQ block answering objections. _(p2: Frequently asked questions Can I change the text after buying? Can I use my own fonts? Doe; pricing: Frequently asked questions Can I design before paying? Is Coverfairy a subscription? Do I )_
- **Proof above the fold**. Social proof rendered within the first viewport on at least one step. _(home: ★★★★★
4.9/5

from 100+ indie authors; p2: ★★★★★
4.9/5

from 100+ independent authors)_

## Proof language (harvested strings → templates)
- `{X}/5`. e.g. "4.9/5"

## Funnel facts
- Depth reached: 4 step(s) (single-page MVP capture)
- Proof points: 1 across 2 step(s)
- Discount/anchor pricing: no · Countdown: no · Subscription: yes

## To replicate
Match the palette + type tokens above and deploy the detected patterns. This is a single-page capture. no cart/checkout tactics were evaluated.