design

design is a command for coding agents from fusengine/agents. It costs 35 tokens per session (391 once invoked), scanned A, original, MIT.

A complete workflow for designing a web page or web application from scratch. It covers the brief, shared visual rules, page creation, animation, and quality review.

In plain words
What is it for?
Use it to create landing pages, hero sections, dashboards, and other web or web-app designs from an initial request.
Why use it?
It organizes the decisions needed for a new design when no existing design system is available or a full redesign is required.

Command

Part of the fuse-design plugin — 9 skills, 5 commands, 1 agent shipped together

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.

agentmods
npx agentmods add commands/fusengine/agents/design
Clone the repo
git clone --depth 1 https://github.com/fusengine/agents

Or install fuse-design, the plugin that ships this one along with the rest of its 9 skills, 5 commands, 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

README.md
[![agentmods](https://agentmods.dev/badge/commands/fusengine/agents/design.svg)](https://agentmods.dev/commands/fusengine/agents/design)
Your own site
<a href="https://agentmods.dev/commands/fusengine/agents/design"><img src="https://agentmods.dev/badge/commands/fusengine/agents/design.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 391 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00035 $0.00391
Opus 5 $0.00017 $0.00196
Sonnet 5 $0.00007 $0.00078
Haiku 4.5 $0.00003 $0.00039

Measured yesterday against content hash 2db34dde1931, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

plugins/design-expert/commands/design.md · 33 lines

What it actually says

/design — Full Pipeline (FULL scope)

Generate a complete design from scratch — no design-system.md exists yet, or a full redesign was requested.

Complete documentation: skills/design-method/SKILL.md

Usage

/design hero section for fintech startup
/design landing page for physiotherapy clinic
/design dashboard for a project management SaaS

Workflow

  1. Read skills/design-method/SKILL.md — answer the 4-question brief, name the signature element, run the two-pass process.
  2. Read skills/design-system/SKILL.md — build design-system.md (OKLCH tokens, typography, spacing, motion profile) and run the Mechanical Contrast Check.
  3. Route per design-method's table: skills/design-web/SKILL.md (marketing/landing) or skills/design-webapp/SKILL.md (dashboard/app). Browse 4 inspiration sites if web/marketing.
  4. Read skills/design-motion/SKILL.md — gate every animation candidate; mandatory states (hover/focus/disabled) regardless of gate outcome.
  5. Read skills/design-review/SKILL.md — deterministic checks, then the bounded screenshot loop (light+dark, max 2 fix cycles), report.

Copy

If the brief needs dedicated UX copy work, read skills/ux-copy/SKILL.md at any point in the pipeline above — it isn't tied to a fixed step.

Forbidden

Skipping the design-method brief. Restating fonts/contrast/screenshot procedure instead of pointing to their canonical skill. Reporting a review as passed when design-review wasn't actually run.

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. yesterday First seen · 33 lines · 35 tokens per session scan A 2db34dde1931

Subscribe to this mod's changes

design is a command published in the GitHub repository fusengine/agents (25 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 391 once invoked, about $0.0002 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 2026-09-03.