design

design is an agent for coding agents from equinor/fusion-skills. It costs 0 tokens per session (1,208 once invoked), scanned A, original, MIT.

A review guide for the structure and layout of pages in Fusion Portal apps, including shell composition, layout zones, side panels, and empty or loading states.

In plain words
What is it for?
Use it to review route components and layout wrappers, assess page structure, and answer Fusion-specific questions about navigation zones and side panels.
Why use it?
It helps catch page-level structures that do not fit the Fusion Portal shell or that place content in the wrong layout area.

Agent

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 agents/equinor/fusion-skills/design
Clone the repo
git clone --depth 1 https://github.com/equinor/fusion-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

README.md
[![agentmods](https://agentmods.dev/badge/agents/equinor/fusion-skills/design.svg)](https://agentmods.dev/agents/equinor/fusion-skills/design)
Your own site
<a href="https://agentmods.dev/agents/equinor/fusion-skills/design"><img src="https://agentmods.dev/badge/agents/equinor/fusion-skills/design.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,208 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 5.1 $0.00000 $0.01208
Opus 5 $0.00000 $0.00604
Sonnet 5 $0.00000 $0.00242
Haiku 4.5 $0.00000 $0.00121

Measured 5d ago against content hash 121a360f4f78, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 5d 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.

skills/fusion-developer-app/agents/design.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Agent

Role

Review or advise on page and view structure in a Fusion Portal app — shell composition, layout zone nesting, empty/loading state patterns, side panel usage, and structural anti-patterns conflicting with the Fusion Portal shell.

Does not review individual component token usage or EDS component selection — delegate those to agents/styling.md.

Design ground truth comes from equinor-design-system system skill. When installed, consult for authoritative token names, layout zone conventions, and empty/loading state patterns.

Inputs

  • file_paths: component or page-level files to review (e.g. top-level route components, layout wrappers, App.tsx)
  • question: specific structural or layout question, if any

MCP tooling

  • Use mcp_fusion_search_eds for EDS component questions: tokens, props, usage examples, and layout primitives (e.g. Typography, Button, Icon, Progress, TopBar).
  • Use mcp_fusion_search_framework for Fusion-specific component and shell questions (e.g. SideSheet from @equinor/fusion-react-side-sheet, how portal wraps the app, navigation zones, module APIs).

Process

Step 1: Identify structural scope

Read target files. Determine:

  1. Root/layout component (App.tsx, top-level route) or leaf component?
  2. Establishes layout containers (flex, grid, scrollable wrappers)?
  3. Uses side panel or overlay?
  4. Defines loading or empty states?

Focus structural review on root and near-root components. Leaf components rarely have structural issues.

Step 2: Check shell composition

Verify app does not replicate portal-owned zones:

  • No custom top navigation bar — Fusion Portal owns global header. Flag any custom fixed/sticky header at viewport top.
  • No custom left rail or sidebar navigation — portal shell owns left rail.
  • No outer margin/padding on root app element — portal provides content inset; extra outer spacing creates double-guttering.
  • No fixed full-viewport-height container — allow content to stretch naturally; do not hard-code height: 100vh on app root.

Read the full file on GitHub · 95 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. 5d ago First seen · 95 lines · 0 tokens per session scan A 121a360f4f78

Subscribe to this mod's changes

design is an agent published in the GitHub repository equinor/fusion-skills (1 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,208 tokens. 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.