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.
npx skills add thatrebeccarae/claude-marketing --skill brand-dnagit clone --depth 1 https://github.com/thatrebeccarae/claude-marketingWrote 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.
[](https://agentmods.dev/skills/thatrebeccarae/claude-marketing/brand-dna)<a href="https://agentmods.dev/skills/thatrebeccarae/claude-marketing/brand-dna"><img src="https://agentmods.dev/badge/skills/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.
<a href="https://agentmods.dev/skills/thatrebeccarae/claude-marketing/brand-dna"><img src="https://agentmods.dev/badge/skills/thatrebeccarae/claude-marketing/brand-dna.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00098 | $0.01684 |
| Opus 5 | $0.00049 | $0.00842 |
| Sonnet 5 | $0.00020 | $0.00337 |
| Haiku 4.5 | $0.00010 | $0.00168 |
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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 161 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.
Install
git clone https://github.com/thatrebeccarae/claude-marketing.git && cp -r claude-marketing/skills/brand-dna ~/.claude/skills/
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 (especiallyog:image,description)- Google Fonts
@importURLs - Any
<link>tags referencing external stylesheets
Fetch order:
- Homepage (
<url>) - About page — try
<url>/about, then/about-us, then/our-story - 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-coloron.hero,.btn-primary,header, orog:imagedominant color - Secondary colors: Supporting palette from CTAs, accents, borders
- Background/text:
bodybackground-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
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 161 lines · 98 tokens per session scan A a273bfa6217b
brand-dna is a skill published in the GitHub repository thatrebeccarae/claude-marketing (137 stars, last pushed 4mo ago), licensed MIT. It adds 98 tokens to every session and 1,684 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.
Other skills, from other repositories
a11y-validate
Accessibility validator: WCAG 2.1 AA, EN 301 549, EAA. Triggers: a11y, accessibility, WCAG, EAA, ARIA, contrast, keyboard, screen reader.
design-engineering
UI craftsmanship: animation rules, easing, micro-interactions, state polish. Triggers: animation, transition, ease-out, motion, micro-interaction, hover, loading state, UI polish.
accessibility-checker
Vérifie et améliore l'accessibilité web (WCAG 2.1/2.2). Se déclenche avec "accessibilité", "a11y", "WCAG", "screen reader", "ARIA", "contraste", "accessible", "handicap", "lecteur d'écran". Also triggers on "accessibility audit", "WCAG compliance", "screen reader issues".
design-critique
Critique constructive d'interfaces et suggestions d'amélioration UX/UI. Se déclenche avec "critique mon design", "avis sur mon UI", "améliorer mon interface", "feedback design", "review UX", "est-ce que mon design est bon", "UI review". Also triggers on "critique my UI", "design feedback", "review this interface".
software-in-worten
Übersetzt zwischen Benutzeroberfläche und Text — in beide Richtungen. Aus einer beschriebenen Oberfläche wird ein Skill; aus einem Skill wird eine Oberfläche. Nutzen, wenn eine Anwendung entworfen wird und der Ablauf noch unklar ist, wenn ein bestehendes Werkzeug als Skill verfügbar gemacht werden soll, wenn…
build-for-good-ux
Use when building, reviewing, or improving user-facing UI, frontend components, pages, forms, flows, loading states, error handling, empty states, success feedback, graceful degradation, familiar layouts, or choice-heavy interfaces.