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 marchatton/agent-skills --skill brand-dna-extractorgit clone --depth 1 https://github.com/marchatton/agent-skillsWrote 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/marchatton/agent-skills/brand-dna-extractor)<a href="https://agentmods.dev/skills/marchatton/agent-skills/brand-dna-extractor"><img src="https://agentmods.dev/badge/skills/marchatton/agent-skills/brand-dna-extractor/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/marchatton/agent-skills/brand-dna-extractor"><img src="https://agentmods.dev/badge/skills/marchatton/agent-skills/brand-dna-extractor.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 | $0.00074 | $0.02860 |
| Opus 5 | $0.00037 | $0.01430 |
| Sonnet 5 | $0.00015 | $0.00572 |
| Haiku 4.5 | $0.00007 | $0.00286 |
Grade A, and why
brand-dna-extractor 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.
How it starts
The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brand-dna-extractor
Purpose
Extract brand signals from multiple sites, ground every claim in evidence, and blend sources into a single composite direction.
When to use
Use when asked to:
- scrape or crawl multiple sites for brand signals
- create brand guidelines, prompt packs, or design tokens from real websites
- compare and blend multiple brands into a “composite DNA”
- capture “CSS etc” (CSS variables, computed styles, hover/focus states)
Outputs
Produce exactly three artefacts:
brand_guidelines.mdprompt_library.jsondesign_tokens.json
Do not output additional artefacts. Do not claim scraping or probing happened unless tool calls were actually executed in the current run.
Inputs
Accept a configuration object (see assets/sample_config.json for a working example). Support:
- optional run metadata:
run_id(recommended) to name artefact folders / receipts - scraping lane provider: Firecrawl / Parallel / hybrid
- browser-probe lane: agent-browser (recommended) or equivalent Playwright-class tooling
- limits: max_pages, max_depth, pages_per_site for probing
- evidence limits: quote_limit_words
The 3-Pronged Approach (Scrape + Extract + Probe)
This skill works best as three parallel “lanes”, each producing different kinds of evidence:
Pick a run_folder for each run (where the three required outputs live). When brand docs are the source of truth,
it often makes sense to use something like docs/02-guidelines/inspiration/<run_id>/ so the outputs and receipts
live together.
Prong 1: Firecrawl (crawl/map + scrape)
Use Firecrawl for breadth and structured web scraping, especially within a domain:
- Best for: mapping/crawling a site, getting broad page coverage, and pulling “main content” markdown.
- Branding Format v2: Retrieve via
POST https://api.firecrawl.dev/v2/scrapewithformats: ["branding"]. This can yield structured hints for colours, typography, logo/icon, layout, and personality (treat as hints, not truth). - Evidence produced:
excerpt(from scraped markdown), plus provider metadata (scrapeId, status, etc.). - Common failure modes: JS-heavy pages, auth walls, noisy nav/footer content, rate limits.
What ships with it
15 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.
- assets/examples/brand_guidelines.md 4.8 KB
- assets/examples/design_tokens.json 4.1 KB
- assets/examples/prompt_library.json 2.7 KB
- assets/sample_config.json 2.4 KB
- LICENSE.txt 651 B
- references/brand_dna_run.schema.json 5.0 KB
- references/brand_guidelines_template.md 2.2 KB
- references/design_tokens.schema.json 5.6 KB
- references/prompt_library.schema.json 2.3 KB
- references/worked_example_minimal.md 1.2 KB
- scripts/blend_signals.py 11 KB runs code
- scripts/firecrawl_branding_v2.ts 8.9 KB runs code
- scripts/normalise_tokens.py 1.5 KB runs code
- scripts/probe_css.js 3.6 KB runs code
- scripts/validate_outputs.py 3.8 KB runs code
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.
- 10d ago First seen · 316 lines · 74 tokens per session scan A 6974bafb9045
brand-dna-extractor is a skill published in the GitHub repository marchatton/agent-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 74 tokens to every session and 2,860 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.