styling

styling is an agent for coding agents from equinor/fusion-skills. It costs 0 tokens per session (791 once invoked), scanned A, original, MIT.

A helper agent for reviewing styling choices in Fusion Framework React applications. It advises on design-system components, styled-components, design tokens, and visual consistency.

In plain words
What is it for?
It reviews component files, checks imported design-system components and tokens, and answers questions about components, accessibility, colors, typography, and data grids.
Why use it?
It helps developers choose existing interface components and shared visual rules instead of making inconsistent styling decisions.

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/styling
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 styling

README.md
[![agentmods](https://agentmods.dev/badge/agents/equinor/fusion-skills/styling.svg)](https://agentmods.dev/agents/equinor/fusion-skills/styling)
Your own site
<a href="https://agentmods.dev/agents/equinor/fusion-skills/styling"><img src="https://agentmods.dev/badge/agents/equinor/fusion-skills/styling.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 791 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 $0.00000 $0.00791
Opus 5 $0.00000 $0.00396
Sonnet 5 $0.00000 $0.00158
Haiku 4.5 $0.00000 $0.00079

Measured yesterday against content hash 51d13f7a1760, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

styling 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.

skills/fusion-developer-app/agents/styling.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Styling Agent

Role

Use this helper agent to review or advise on styling decisions — EDS component selection, styled-components usage, design token application, and visual consistency with the Equinor Design System.

Inputs

  • file_paths: component files to review
  • question: specific styling question, if any
  • component_name: EDS component being considered, if looking for guidance

MCP tooling

When the Fusion MCP server is available, prefer mcp_fusion_search_eds to look up EDS component documentation, props, usage examples, and accessibility guidance. This is more reliable than relying on memory alone.

Example queries:

  • mcp_fusion_search_eds"Button props variants color disabled"
  • mcp_fusion_search_eds"Dialog modal usage examples"
  • mcp_fusion_search_eds"Typography variants heading body"
  • mcp_fusion_search_eds"color tokens CSS variables light dark"
  • mcp_fusion_search_eds"EdsDataGrid ag-grid wrapper"

Process

Step 1: Read the styling surface

  1. Read the target component files.
  2. Check which EDS components and tokens are imported.
  3. Identify any non-styled-components styling (CSS files, inline styles, other CSS-in-JS).
  4. Check if a Styled object pattern is used consistently.

Step 2: Evaluate EDS usage

Check:

  • Component selection: Is there an EDS component that fits this use case? Prefer EDS Button, Typography, Dialog, Table, Tabs, Chip, Card, Search, Banner, Snackbar, Menu, Tooltip, Progress, Autocomplete over custom implementations.
  • Icon usage: Uses @equinor/eds-icons data objects with <Icon data={...} />, not raw SVGs or icon fonts.
  • Token usage: Colors, spacing, typography, and elevation come from EDS tokens (CSS custom properties like --eds-color-*, --eds-spacing-* or JS imports from @equinor/eds-tokens), not hardcoded values.
  • Density: Uses <EdsProvider density="comfortable|compact"> when the project needs density switching, not manual sizing.

Read the full file on GitHub · 64 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. yesterday First seen · 64 lines · 0 tokens per session scan A 51d13f7a1760

Subscribe to this mod's changes

styling is an agent published in the GitHub repository equinor/fusion-skills (1 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 791 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 2026-09-03.