design-principles

design-principles is a skill for Claude Code from zstvns/design-skills. It costs 70 tokens per session (4,247 once invoked), scanned C, original, MIT.

A general guide to making visual designs clear, coherent, and purposeful across logos, brand identities, printed materials, websites, and other screens. It explains how to decide what people should notice and understand first.

In plain words
What is it for?
Use it before design work, or when judging layouts, marks, brand systems, printed pieces, and interfaces whose visual choices need a clear reason.
Why use it?
It gives a way to diagnose why a design feels wrong and to make choices based on the message instead of decoration.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the designskills plugin — 8 skills shipped together

Good fit Use it before design work, or when judging layouts, marks, brand systems, printed pieces, and interfaces whose visual choices need a clear reason.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zstvns/design-skills/design-principles
Install

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.

Any agent
npx skills add zstvns/design-skills --skill design-principles
Clone the repo
git clone --depth 1 https://github.com/zstvns/design-skills

Made for: Claude Code.

Or install designskills, the plugin that ships this one along with the rest of its 8 skills.

Wrote 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.

agentmods badge for design-principles

README.md
[![agentmods](https://agentmods.dev/badge/skills/zstvns/design-skills/design-principles/github.svg)](https://agentmods.dev/skills/zstvns/design-skills/design-principles)
Your own site
<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.

agentmods 80×15 button for design-principles

Your own site · 80×15
<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>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,247 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 11d ago against content hash 85fde3778ff1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.
skills/design-principles/SKILL.md · 173 lines

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.

Read the full file on GitHub · 173 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 173 lines · 70 tokens per session scan C 85fde3778ff1

Subscribe to this mod's changes

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.

Related

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.

roslove44/brand-artisan · 78 tokens

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…

roslove44/brand-artisan · 110 tokens

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)…

roslove44/brand-artisan · 110 tokens

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.

roslove44/brand-artisan · 76 tokens

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…

danpeg/visual-research · 116 tokens

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…

DTM-repo/skills · 235 tokens