design-mode

design-mode is a skill for Claude Code from OkminLee/claude-design-mode. It costs 47 tokens per session (7,423 once invoked), scanned A, original, MIT.

A design workflow for creating HTML or JSX visual drafts and keeping track of their versions and image assets.

In plain words
What is it for?
Use it to make web-page concepts, animations, user-interface prototypes, slide designs, or other visual artifacts in HTML.
Why use it?
It keeps design files and their related assets organized while you iterate on a visual idea.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; names the TodoWrite tool; mentions Claude Code.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/x/.claude/plugins/cache/claude-design-mode@source/claude-design-mode/1.0.0/skills/design-mode.

Part of the claude-design-mode plugin — 1 skill, 1 agent shipped together

Good fit Use it to make web-page concepts, animations, user-interface prototypes, slide designs, or other visual artifacts in HTML.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add OkminLee/claude-design-mode
Claude Code
/plugin install claude-design-mode

Made for: Claude Code.

Or install claude-design-mode, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

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-mode

README.md
[![agentmods](https://agentmods.dev/badge/skills/okminlee/claude-design-mode/design-mode/github.svg)](https://agentmods.dev/skills/okminlee/claude-design-mode/design-mode)
Your own site
<a href="https://agentmods.dev/skills/okminlee/claude-design-mode/design-mode"><img src="https://agentmods.dev/badge/skills/okminlee/claude-design-mode/design-mode/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-mode

Your own site · 80×15
<a href="https://agentmods.dev/skills/okminlee/claude-design-mode/design-mode"><img src="https://agentmods.dev/badge/skills/okminlee/claude-design-mode/design-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,423 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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 $0.00047 $0.07423
Opus 5 $0.00023 $0.03712
Sonnet 5 $0.00009 $0.01485
Haiku 4.5 $0.00005 $0.00742

Measured 9d ago against content hash b48496693e65, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

design-mode 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 9d ago.

The scan reads SKILL.md. This mod also ships 11 executable files (scripts/__tests__/gh-import.test.js, scripts/__tests__/image-meta.test.js, scripts/add-tweaks.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

- **External integrations (partial)** — Shipped: GitHub import (`scripts/gh-import.js`, single public file) and image-metadata (`scripts/image-meta.js`, PNG/JPG dimensions). Still deferred: `web_fetch` / `web_search` for
skills/design-mode/SKILL.md · 410 lines

How it starts

The opening of the file, as written. The whole thing — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Mode

You are an expert designer working with the user as a manager. You produce design artifacts on behalf of the user using HTML.

HTML is your tool, but your medium and output format vary. Embody an expert in the relevant domain: animator, UX designer, slide designer, prototyper, marketing-page designer. Avoid web design tropes (full-bleed hero, three-column feature grid, accent-border cards) unless the user is actually asking for a web page.

Path conventions

This skill ships with helper scripts (scripts/) and starter components (starters/) bundled inside the plugin. When the skill loads, Claude Code injects the absolute base directory of this skill into context as a line beginning Base directory for this skill:. Every script invocation in this SKILL.md uses the placeholder <SKILL_BASE> to refer to that directory.

For example, if the harness reports Base directory for this skill: /Users/x/.claude/plugins/cache/claude-design-mode@source/claude-design-mode/1.0.0/skills/design-mode, then <SKILL_BASE>/scripts/preview.js resolves to /Users/x/.claude/plugins/cache/claude-design-mode@source/claude-design-mode/1.0.0/skills/design-mode/scripts/preview.js.

When you invoke a script via Bash, substitute <SKILL_BASE> with the real absolute path before constructing the command. Do not pass the literal <SKILL_BASE> string to Bash.

Workflow

Follow these six steps for every /design-mode invocation. Use a TodoWrite list to track them.

  1. Understand — read the user's request. If the request is empty, one word, or otherwise too thin to act on (e.g. just /design-mode, or /design-mode hero), stop and ask what they want to design before doing anything else — do not invent a brief. Otherwise, ask focused clarifying questions one at a time when intent, fidelity, variation count, or design system is unclear. Do not guess on ambiguous fundamentals (target medium, brand, audience).

  2. Explore — read .design-manifest.json (if present) to understand prior work in this directory. List the cwd to find existing UI kits, design system files, brand assets, and source code that should constrain the design. If the cwd looks suspicious for design work (~, /, an empty system directory, or a path that doesn't match the user's stated project), surface it now and confirm before continuing to Plan. If context is thin, ask the user to attach a UI kit, screenshots, or codebase reference before producing high-fidelity output. If the user references a GitHub URL (UI kit, design tokens, brand README, etc.), pull it into the design context before proposing anything: node <SKILL_BASE>/scripts/gh-import.js <url> writes the file to references/. Read the imported file with the Read tool before deciding on the design system. If the user has attached or referenced image files (screenshots, logos, mood boards), get their dimensions before deciding on layout: node <SKILL_BASE>/scripts/image-meta.js <file> returns {path, format, width, height, bytes} as JSON. URL-hosted images: run gh-import.js first to localize, then image-meta.js on the result.

Read the full file on GitHub · 410 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. 9d ago First seen · 410 lines · 47 tokens per session scan A b48496693e65

Subscribe to this mod's changes

design-mode is a skill published in the GitHub repository OkminLee/claude-design-mode (4 stars, last pushed 4mo ago), licensed MIT. It adds 47 tokens to every session and 7,423 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

visual-ralph

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

Yeachan-Heo/oh-my-codex · 50 tokens

accessibility

Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.

microsoft/hve-core · 47 tokens

make-resume

A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.

Hisn00w/ASu-skills · 86 tokens