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 roslove44/brand-artisan --skill new-projectgit clone --depth 1 https://github.com/roslove44/brand-artisanWrote 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/roslove44/brand-artisan/new-project)<a href="https://agentmods.dev/skills/roslove44/brand-artisan/new-project"><img src="https://agentmods.dev/badge/skills/roslove44/brand-artisan/new-project/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/roslove44/brand-artisan/new-project"><img src="https://agentmods.dev/badge/skills/roslove44/brand-artisan/new-project.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 | $0.00076 | $0.01462 |
| Opus 5 | $0.00038 | $0.00731 |
| Sonnet 5 | $0.00015 | $0.00292 |
| Haiku 4.5 | $0.00008 | $0.00146 |
Grade A, and why
new-project scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. **Download** to `fonts/<Family>-<weight>.ttf`, using `curl -L <url> -o ...` How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
new-project: bootstrapping a visuals project
Goal: lay down the two references of a new project in brands/<project>/:
brand.md (visual identity, blocking: no visual without it) and project.md
(substance and voice, for writing the text). A CLAUDE.md rule.
1. Determine the <project> slug
Take it from the arguments. Otherwise ask. It is a kebab-case slug (e.g.
calame, my-app). Check that it does not already exist: brands/<project>/ or
templates/<project>/. If it does -> stop, say so.
2. Collect the guidelines (invent nothing)
Interview the user. Never invent colors, type or logo: that is the heart of the project rule. Collect at least:
- Concept / meaning of the logo and the name.
- Typography: typeface, weight, source. Note: the available families and
weights are those present in
fonts/, discovered automatically by the engine. If the guidelines require another font absent fromfonts/, follow the Missing font procedure below: offer to pre-install it now, or let/new-templatefetch it for the first visual that needs it. - Palette: for each role, the hex (+ Tailwind landmark if known) and the usage.
- Logo / favicon variants available and when to use them.
- Usage rules and don'ts.
Collect the substance too (for project.md): a one-sentence pitch, what the
product does, audience and language, value proposition, editorial voice
(register, how it addresses the reader), vocabulary (exact name, URL) and
forbidden claims (don't invent figures).
If the user does not have everything yet, write down what is known and mark the
gaps with _(to be defined)_ rather than filling them at random.
3. Write brands/<project>/brand.md
Mirror the structure of brands/calame/brand.md (that is the reference):
- Title
# Brand guidelines: <Project>+ a short intro. ## 1. Concept and meaning(with Typography and Colors subsections).## 2. Variants(logotype, favicon/icons) if applicable.## 3. Usage rules(clear space, minimum size, backgrounds, Don't).## 4. Regenerationonly if some assets are generated by a script.
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 · 111 lines · 76 tokens per session scan A 63344c4a9dee
new-project is a skill published in the GitHub repository roslove44/brand-artisan (4 stars, last pushed 14d ago), licensed MIT. It adds 76 tokens to every session and 1,462 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
collateral-design
Apply a brand's defined visual system to any fixed-format piece that isn't a website — decks and presentations, one-pagers and sales sheets, social posts and graphics, blog/OG thumbnails, business cards, brochures, flyers, posters, banners, billboards, and paid ads. Use when the user mentions 'design a deck,' 'pitch…
desktop-brand-builder
Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo. Use when the user wants a custom, white-label, or rebranded desktop client, installer, DMG/EXE/AppImage/deb, or one-click brand build on top of packages/desktop-shell.
frame-logo-outro
Segmented logo assembly, glow bloom, and tagline reveal for video outros or brand closing frames.
ideate
Generate image-based alternatives, remixes, or new design directions from a Product Design brief. Use when the user asks for design variants, visual exploration, remixes, or image-generated approaches from provided context.
extract-design
Extract the full design language from any website URL. Produces 8 output files including AI-optimized markdown, visual HTML preview, Tailwind config, React theme, shadcn/ui theme, Figma variables, W3C design tokens, and CSS variables. Also runs WCAG accessibility scoring. Use when user says 'extract design', 'get…
design
Use when the user wants the visual/experiential design of a product done systematically — a design system, a screen, a landing page, or a visual identity — grounded in researched real-world prior art and free of AI slop. Establishes/extends the design system, invokes the matching local taste skill, dispatches the…