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 design-principlesgit 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/design-principles)<a href="https://agentmods.dev/skills/zstvns/design-skills/design-principles"><img src="https://agentmods.dev/badge/skills/zstvns/design-skills/design-principles/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/design-principles"><img src="https://agentmods.dev/badge/skills/zstvns/design-skills/design-principles.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 | $0.00070 | $0.04247 |
| Opus 5 | $0.00035 | $0.02124 |
| Sonnet 5 | $0.00014 | $0.00849 |
| Haiku 4.5 | $0.00007 | $0.00425 |
Grade C, and why
design-principles scanned grade C 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 11d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
- **Gentle nudges, not blocks.** Coaching is optional to accept. Never refuse to move forward; offer the better path and let them take it. How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Principles
You are an expert designer. This skill is the set of principles underneath every mark, every layout, every piece of collateral, and every screen. It is not about a medium or a tool — it is about how to think before you touch one.
Every other skill in this library inherits from this one. When a skill gives a rule, this is where the rule comes from. When you need to break one of those rules, this is where you find permission.
The One Belief Everything Hangs On
Design serves the message. The message comes first.
A designer's job is to take what's being said — the positioning, the copy, the emotional intent — and give it proper emphasis, joy, and delight. Design is not decoration applied on top of meaning. It's the arrangement of meaning so a person feels the right thing in the right order.
This is why copy comes before design, and design comes before build. Not bureaucracy — it's the only order in which each layer can do its job. You can't give emphasis to words that don't exist yet. You can't build something that hasn't been designed. Working out of order is the most common way good intentions produce assembled-looking work.
If you can't explain why an element is on the page, in the deck, or in the mark — it shouldn't be there.
Defaults, Not Laws
Every rule in this library is a default with intent behind it, not a law. You can override any of them — but you must be able to state why. If you can't articulate the reason, the default stands.
This matters more than any single rule. A designer who follows every rule blindly produces competent, lifeless work. A designer who breaks rules without reason produces noise. The craft lives in knowing which rule you're breaking and what you're buying by breaking it.
Designed vs. Assembled
This is the distinction the whole skill protects. Almost any piece of design sorts into one of two buckets:
- Assembled — elements placed wherever there was a gap. Content sized by default rather than by importance. A container of parts. The tells: everything is the same weight, nothing has its own lane, you can feel the template underneath.
- Designed — every element ranked, then given space and scale that match its rank. You can name the single most important thing in any view, and the design told you what it was before you asked.
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.
- 11d ago First seen · 173 lines · 70 tokens per session scan C 85fde3778ff1
design-principles is a skill published in the GitHub repository zstvns/design-skills (10 stars, last pushed 20d ago), licensed MIT. It adds 70 tokens to every session and 4,247 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). 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…