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 mysleekdesigns/crawlforge-mcp --skill crawlforge-brand-style-guidegit clone --depth 1 https://github.com/mysleekdesigns/crawlforge-mcpWrote 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/mysleekdesigns/crawlforge-mcp/crawlforge-brand-style-guide)<a href="https://agentmods.dev/skills/mysleekdesigns/crawlforge-mcp/crawlforge-brand-style-guide"><img src="https://agentmods.dev/badge/skills/mysleekdesigns/crawlforge-mcp/crawlforge-brand-style-guide/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/mysleekdesigns/crawlforge-mcp/crawlforge-brand-style-guide"><img src="https://agentmods.dev/badge/skills/mysleekdesigns/crawlforge-mcp/crawlforge-brand-style-guide.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 | $0.00145 | $0.01373 |
| Opus 5.5 | $0.00058 | $0.00549 |
| Sonnet 5.5 | $0.00029 | $0.00275 |
| Haiku 4.5 | $0.00015 | $0.00137 |
Grade A, and why
crawlforge-brand-style-guide 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 8d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CrawlForge Brand Style Guide
Turn a website into a style guide or a design-token file. CrawlForge collects
the brand data in one scrape call; you write the guide from it.
When to use
- "Make a style guide from stripe.com" / "build a brand kit for this site"
- "What colours and fonts does this company use?"
- "Grab this site's logo and button styles"
- "Match the look of this website"
- "Export this site's design tokens for Figma / Style Dictionary"
The one call
{
"tool": "scrape",
"params": {
"url": "https://stripe.com",
"formats": ["branding", "screenshot"],
"brandingOptions": { "dtcg": true }
}
}
Cost: 2 credits. branding and screenshot share one browser render. Add
"metadata" if you need the site name and description too. Leave out dtcg
unless the user wants a token file: it can double the size of the result.
If the result is truncated: true, do not scrape again. Read the parts with
read_result and a json_path, such as content.branding.roles or
content.branding.dtcg.
What comes back in content.branding
| Key | What it holds |
|---|---|
colorScheme |
light or dark, from the page background |
roles |
background, text, heading, link, primary, onPrimary: each { value, source, evidence } |
components |
buttonPrimary and buttonSecondary: fill, label colour, border, radius, padding, font, size and weight |
typography |
body, h1, h2: family, stack, size, weight, line height, letter spacing, colour |
logo |
inlineHeaderSvg (the header logo as SVG), favicons, ogImage, image candidates |
fonts, fontFaces |
font families ranked by use, and their @font-face sources |
tokens |
the site's CSS custom properties, grouped: colors.ramps, colors.semantic, typography, spacing, radius, shadow, plus stats on what was dropped |
colors |
every colour found, ranked by frequency |
dtcg |
with dtcg: true, the tokens and roles as W3C Design Tokens (2025.10) JSON |
provenance |
what each source value means |
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.
- 8d ago First seen · 108 lines · 145 tokens per session scan A b9620e61de21
crawlforge-brand-style-guide is a skill published in the GitHub repository mysleekdesigns/crawlforge-mcp (6 stars, last pushed 5d ago), licensed MIT. It adds 145 tokens to every session and 1,373 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-29.
crawlforge-brand-style-guide compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| crawlforge-brand-style-guidemysleekdesigns/crawlforge-mcp | Skill | 6 | 5d ago | MIT | A | 145 | Claude Code, Codex |
| figma-code-connect-componentsulises-jeremias/agent-toolkit | Skill | 19 | yesterday | MIT | A | 92 | Claude Code |
| figma-create-design-system-rulesulises-jeremias/agent-toolkit | Skill | 19 | yesterday | MIT | A | 71 | Claude Code |
| design-improvementulises-jeremias/agent-toolkit | Skill | 19 | yesterday | MIT | A | 60 | Claude Code |
| reviewulises-jeremias/agent-toolkit | Skill | 19 | yesterday | MIT | A | 48 | Claude Code |
| design-assessmentulises-jeremias/agent-toolkit | Skill | 19 | yesterday | MIT | A | 61 | Claude Code |
| architecture-diagramulises-jeremias/agent-toolkit | Skill | 19 | yesterday | MIT | A | 61 | Claude Code |