designer

designer is a skill for Claude Code from Pierry/harness-kit. It costs 81 tokens per session (5,612 once invoked), scanned A, original, MIT.

A set of visual and user-experience rules for building new interfaces. It uses Material Design 3, a system of reusable guidelines for layout, colors, typography, components, and interaction states.

In plain words
What is it for?
Use it when creating a new app, page, feature, or landing page. It is intended for greenfield UI work and should follow an existing project design system when one is already present.
Why use it?
It gives new user interfaces a consistent structure and appearance, while accounting for themes, language support, icons, and project conventions.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the harness-kit plugin — 14 skills, 18 commands, 4 agents, 4 hooks shipped together

Good fit Use it when creating a new app, page, feature, or landing page. It is intended for greenfield UI work and should follow an existing project design system when one is already present.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pierry/harness-kit/designer
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 Pierry/harness-kit --skill designer
Clone the repo
git clone --depth 1 https://github.com/Pierry/harness-kit

Made for: Claude Code.

Or install harness-kit, the plugin that ships this one along with the rest of its 14 skills, 18 commands, 4 agents, 4 hooks.

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 designer

README.md
[![agentmods](https://agentmods.dev/badge/skills/pierry/harness-kit/designer/github.svg)](https://agentmods.dev/skills/pierry/harness-kit/designer)
Your own site
<a href="https://agentmods.dev/skills/pierry/harness-kit/designer"><img src="https://agentmods.dev/badge/skills/pierry/harness-kit/designer/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 designer

Your own site · 80×15
<a href="https://agentmods.dev/skills/pierry/harness-kit/designer"><img src="https://agentmods.dev/badge/skills/pierry/harness-kit/designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,612 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00081 $0.05612
Opus 5.5 $0.00032 $0.02245
Sonnet 5.5 $0.00016 $0.01122
Haiku 4.5 $0.00008 $0.00561

Measured 1mo ago against content hash 709814b6df51, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

designer 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 1mo 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.

.claude/agents/staff-software-engineer/skills/designer/SKILL.md · 357 lines

How it starts

The opening of the file, as written. The whole thing — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Designer conventions. Apply when SSE builds something new with a UI (new app, page, feature, landing). Layers on top of the area skill (web/mobile), does not replace it. Project override: {repo}/.claude/conventions/web.md wins. Match existing design system if repo already has one; only green-field gets these defaults.

READ FIRST: Material Design 3 is non-negotiable

Every visual surface this skill touches must be Material Design 3. Not "M3-inspired", not "close enough". M3 is the system: token-driven color roles, the shape scale, tonal elevation, state layers, and motion. If you are about to write a color, a border, a radius, or a callout, it comes from M3, not from instinct or a CMS habit. This rule has been broken before; do not break it again.

Before you ship any surface, self-check against these top offenders. Each one is a hard rule with its own section below; this is the unmissable summary, not the exception list.

  • No colored left-border accent bars. A border-left: 3px/4px solid var(--primary) on a card, hint, callout, banner, or "supporting" box is forbidden. It collides with the shape-scale radius and leaves a colored sliver in the rounded corner (the classic "corzinha no canto"). Color the surface with a tonal container (secondary-container / surface-container-high), never one edge. See "Info, help, and supporting surfaces".
  • Tonal containers, not ad-hoc borders, carry meaning. Reach for a *-container role + its on-* text + a real shape radius + an MD3 info icon. A stripe is not a design system.
  • Tokens only, never raw hex in component CSS. Define roles once for light and dark.
  • No emoji, ever. Use Material Symbols or a single modern open set. Draw brand marks original.
  • No em-dashes or en-dashes anywhere: copy, headings, comments, commits, PRs, docs, all locales.
  • Both themes, always. Light and dark, system-preference first, choice persisted.
  • Vivid, on-trend color, never a timid grey wash. Saturated modern seed + a second accent + purposeful gradients. A washed-out palette is a build blocker. See "Vivid, on-trend color".
  • A real, beautiful typeface, never the raw system stack. Load/embed a current variable face (Geist, Instrument Sans, Bricolage Grotesque, etc.); system-ui as the final look is forbidden.
  • Depth and motion on every surface. Layered + tinted shadows, accent glow, highlights/glass, and animation are always on (with prefers-reduced-motion). Flat and shadowless is a defect.

When in doubt, open the matching section below and follow it literally. The detailed rules win over any quick instinct, and the "Forbidden" list at the end is exhaustive. Treat a violation of any of these as a build blocker, the same as a failing test.

Read the full file on GitHub · 357 lines

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. 1mo ago First seen · 357 lines · 81 tokens per session scan A 709814b6df51

Subscribe to this mod's changes

designer is a skill published in the GitHub repository Pierry/harness-kit (4 stars, last pushed 19d ago), licensed MIT. It adds 81 tokens to every session and 5,612 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

frontend-enhancer

Enhance the visual design of web apps: modern UI components, layout, responsive design, color palettes, animations. Use for styling and UI polish; pair with ui-research first for new design directions.

travisjneuman/.claude · 45 tokens

generic-design-system

Complete design system reference for any project - colors, typography, spacing, components, animations. Adapts to project theme and tech stack. Use when implementing UI, choosing colors, creating animations, or ensuring brand consistency. For new design systems, use ui-research skill first.

travisjneuman/.claude · 60 tokens

generic-react-design-system

Complete design system reference for React applications. Covers colors, typography, spacing, component patterns, glassmorphism effects, GPU-accelerated animations, and WCAG AA accessibility. Use when implementing UI, choosing colors, applying spacing, creating components, or ensuring brand consistency.

travisjneuman/.claude · 59 tokens

generic-static-design-system

Complete design system reference for static HTML/CSS/JS sites. Covers colors, typography, component patterns, animations, and accessibility. Use when implementing UI, choosing colors, or ensuring brand consistency.

travisjneuman/.claude · 44 tokens

generic-static-ux-designer

Professional UI/UX design expertise for static HTML/CSS/JS sites. Covers design thinking, user psychology, visual hierarchy, minimalist interaction patterns, accessibility, and performance-driven design. Use when designing features, improving UX, or conducting design reviews.

travisjneuman/.claude · 56 tokens

agent-accessibility-expert

Specialist subagent: WCAG compliance, screen reader compatibility, and inclusive design patterns. Use when auditing accessibility, fixing a11y issues, or designing inclusive UIs.

travisjneuman/.claude · 41 tokens