brand-dna

brand-dna is a cursor rule for Cursor from thatrebeccarae/claude-marketing. It costs 94 tokens per session (3,121 once invoked), scanned A, original, MIT.

A website analysis guide that extracts a brand’s writing style, colors, fonts, images, values, and audience into a structured brand profile file. It can analyze a full website or just its homepage.

In plain words
What is it for?
Use it to create a brand profile from a website that can guide SEO writing, emails, frontend design, presentations, and cross-platform reviews.
Why use it?
It gives other content and design work a shared description of the brand to follow. This reduces the need to rediscover the same identity details for every new task.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc). Also seen: mentions Claude Code.

Good fit Use it to create a brand profile from a website that can guide SEO writing, emails, frontend design, presentations, and cross-platform reviews.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/thatrebeccarae/claude-marketing/brand-dna
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/thatrebeccarae/claude-marketing

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for brand-dna

README.md
[![agentmods](https://agentmods.dev/badge/rules/thatrebeccarae/claude-marketing/brand-dna/github.svg)](https://agentmods.dev/rules/thatrebeccarae/claude-marketing/brand-dna)
Your own site
<a href="https://agentmods.dev/rules/thatrebeccarae/claude-marketing/brand-dna"><img src="https://agentmods.dev/badge/rules/thatrebeccarae/claude-marketing/brand-dna/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for brand-dna

Your own site · 80×15
<a href="https://agentmods.dev/rules/thatrebeccarae/claude-marketing/brand-dna"><img src="https://agentmods.dev/badge/rules/thatrebeccarae/claude-marketing/brand-dna.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,121 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00094 $0.03121
Opus 5 $0.00047 $0.01561
Sonnet 5 $0.00019 $0.00624
Haiku 4.5 $0.00009 $0.00312

Measured 10d ago against content hash 91653a3443b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

brand-dna scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

integrations/cursor/brand-dna.mdc · 309 lines

How it starts

The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brand DNA — Brand Identity Extractor

Extracts brand identity from a website and produces a structured brand-profile.json that other skills can consume for brand-consistent output.

Quick Reference

Command What It Does
"Extract brand DNA from https://example.com" Full extraction → brand-profile.json
"Quick brand profile for https://example.com" Homepage-only extraction (faster, lower confidence)

Zero Dependencies

This skill uses only the WebFetch tool — no Python scripts, no Playwright, no external APIs. It works anywhere Claude Code runs.

Extraction Process

Step 1: Collect URL

If the user hasn't provided a URL, ask:

"What website URL should I analyze? (e.g., https://yoursite.com)"

Step 2: Fetch Pages

Use the WebFetch tool to retrieve page content. For each URL, request:

  • All visible text content
  • Full contents of <style> blocks
  • Inline style= attributes
  • <meta> tags (especially og:image, description)
  • Google Fonts @import URLs
  • Any <link> tags referencing external stylesheets

Fetch order:

  1. Homepage (<url>)
  2. About page — try <url>/about, then /about-us, then /our-story
  3. Product/Services page — try <url>/products, then /product, then /services

Quick mode: If the user requests a quick extraction, fetch homepage only — skip pages 2 and 3.

If a secondary page returns 404 or redirects to homepage, continue with fewer pages and note reduced confidence.

Step 3: Extract Brand Elements

Colors
  • Primary color: Most prominent brand color from CSS background-color on .hero, .btn-primary, header, or og:image dominant color
  • Secondary colors: Supporting palette from CTAs, accents, borders
  • Background/text: body background-color and color
  • Forbidden: Infer from brand positioning (e.g., competitor colors if identifiable)
  • Dark mode detection: If body background is #333 or darker, swap background/text values

Read the full file on GitHub · 309 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 309 lines · 94 tokens per session scan A 91653a3443b4

Subscribe to this mod's changes

brand-dna is a cursor rule published in the GitHub repository thatrebeccarae/claude-marketing (134 stars, last pushed 3mo ago), licensed MIT. It adds 94 tokens to every session and 3,121 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.