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.
npx agentmods add agents/equinor/fusion-skills/designgit clone --depth 1 https://github.com/equinor/fusion-skillsWrote 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.
[](https://agentmods.dev/agents/equinor/fusion-skills/design)<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>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.
| Model | Per session | Once 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 |
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.
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_edsfor EDS component questions: tokens, props, usage examples, and layout primitives (e.g.Typography,Button,Icon,Progress,TopBar). - Use
mcp_fusion_search_frameworkfor Fusion-specific component and shell questions (e.g.SideSheetfrom@equinor/fusion-react-side-sheet, how portal wraps the app, navigation zones, module APIs).
Process
Step 1: Identify structural scope
Read target files. Determine:
- Root/layout component (
App.tsx, top-level route) or leaf component? - Establishes layout containers (flex, grid, scrollable wrappers)?
- Uses side panel or overlay?
- 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: 100vhon app root.
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.
- 5d ago First seen · 95 lines · 0 tokens per session scan A 121a360f4f78
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.