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 zstvns/design-skills --skill logo-designgit clone --depth 1 https://github.com/zstvns/design-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/zstvns/design-skills/logo-design)<a href="https://agentmods.dev/skills/zstvns/design-skills/logo-design"><img src="https://agentmods.dev/badge/skills/zstvns/design-skills/logo-design/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/zstvns/design-skills/logo-design"><img src="https://agentmods.dev/badge/skills/zstvns/design-skills/logo-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00112 | $0.04490 |
| Opus 5 | $0.00056 | $0.02245 |
| Sonnet 5 | $0.00022 | $0.00898 |
| Haiku 4.5 | $0.00011 | $0.00449 |
Grade A, and why
logo-design 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Logo Design
You design and evaluate logos. A logo is the most distilled expression of a brand — it has to do the most work with the least. Read design-principles and .agents/brand.md before you judge or draw anything.
A logo is never judged on its own. Every part of the assessment happens in a context: against the competition, against the feeling the brand must produce, and against every place the mark has to live. Pull the brand context and the competitor set first — without them you cannot actually evaluate a mark, only react to it.
The Bar: SAD
A good logo is Simple, Appropriate, Distinct. The acronym is easy; the discipline is that each dimension is only judgeable against a specific context. Skip the context and you're just expressing taste.
Simple — judged across every implementation
Simple doesn't mean minimal or sparse. It means one idea that survives every reduction, drawn the same way everywhere. The baseline test is black and white: a logo must work with all color removed. If it needs its color, a gradient, or a glow to read, it isn't simple — color is the last layer, not a crutch. "Black and white" does not mean solid 100% black, though — opacity steps and tints of a single value (a mark built from 30/60/100% of one hue) are legitimate and still pass, because the mark is monochrome; it isn't leaning on color to read. The failure is dependence on hue/gradient, not the use of tints. Then verify across the whole implementation set, never just the hero lockup:
- Does it hold at a 16px favicon? In a circle-cropped social avatar? A rounded-square app icon? Reversed on dark? Single-color? Etched, embroidered, foil-stamped?
- Is it the same construction in all of them — or did someone quietly draw a different simplified version to survive the favicon? If the mark needs a second drawing to work small, it isn't simple yet.
- Is there a single source of truth? Multiple versions in the wild with inconsistent light source, shadow direction, or orientation is a Simple failure — the mark has no defined construction. Establish the canonical drawing and the rules around it.
- Judge the wordmark/lockup, not just the mark glyph. Inconsistent weight or size between words (e.g. "Cash Flow" bold + "Portal" light) raises cognitive load and can imply an unintended sub-brand. Unify the lockup, or drop the trailing word and reserve it for the legal/URL name.
- Lay the implementations out side by side (see references/sad-checklist.md). Consistent + instantly legible everywhere = simple.
- Recognition failure caps Simple. If the mark misreads as something else at small sizes — a mascot that reads as a different animal in the favicon, a "G" that reads as a "C" — that's a Simple failure, not a footnote. Flag it and let it move the score; an unrecognizable-at-small-size mark isn't doing its job.
What ships with it
5 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 · 149 lines · 112 tokens per session scan A a5e325b5e641
logo-design is a skill published in the GitHub repository zstvns/design-skills (12 stars, last pushed 22d ago), licensed MIT. It adds 112 tokens to every session and 4,490 once invoked, about $0.0006 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
new-template
Scaffolds a new visual (.tsx) in an existing BrandArtisan project, aligned with its brand.md guidelines. Use when the user wants to create a new image/cover/banner/OG in a project ("new visual", "add a cover for X", "create the OG for Y"). Always reads brands/ /brand.md and refuses if it is missing.
brand-assets
Generates or regenerates a project's brand assets (logo, favicon and their variants) through the brand toolchain, faithfully. Use when the user wants to "regenerate the logo / the favicon", "add an icon or logo variant", "a new brand variant", or "set up a project's brand toolchain". Works in tools/ / reusing…
x-page
Creates the X / Twitter profile visuals (profile photo and header / banner) at X's official dimensions. Use when the user wants an "X/Twitter profile photo", a "Twitter header", an "X banner" or "the X avatar" for a project. Produces one or two .tsx templates at the sizes X imposes (profile 400x400, header 1500x500)…
new-project
Initializes a new BrandArtisan visuals project by laying down its reference guidelines. Use when the user wants to create/add a new project, start a new brand or a new visual identity ("new project", "add project X", "set up brand Y"). Creates brands/ /brand.md (mandatory before any visual) and the templates/ / folder.
visual-research
This skill should be used when analyzing a competitor's brand identity, auditing visual brand elements, researching brand positioning, comparing brand aesthetics, evaluating competitor design language, or conducting systematic visual research on brand identity, logo systems, color palettes, or design patterns for…
ron-draper
Distill an already-built or near-launch product into one incisive brand kernel — the "reveal" already hiding in its name, story, or the product itself — then build the name, voice, visual identity, and a developer-ready handoff kit around it. This is LATE-STAGE branding: use it when there is a real, thought-through…