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 skills add equinor/fusion-skills --skill fusion-developer-appgit 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/skills/equinor/fusion-skills/fusion-developer-app)<a href="https://agentmods.dev/skills/equinor/fusion-skills/fusion-developer-app"><img src="https://agentmods.dev/badge/skills/equinor/fusion-skills/fusion-developer-app/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.
<a href="https://agentmods.dev/skills/equinor/fusion-skills/fusion-developer-app"><img src="https://agentmods.dev/badge/skills/equinor/fusion-skills/fusion-developer-app.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00094 | $0.02797 |
| Opus 5.5 | $0.00038 | $0.01119 |
| Sonnet 5.5 | $0.00019 | $0.00559 |
| Haiku 4.5 | $0.00009 | $0.00280 |
Grade A, and why
fusion-developer-app 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 1mo 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fusion App Development
When to use
Use this skill when developing features, components, hooks, services, or types for a Fusion Framework React application.
Typical triggers:
- "Add a component / hook / service / page for ..."
- "Wire up the API"
- "Configure a Fusion module"
- "Which Fusion Framework hook / package should this app use?"
- "Persist this preference as an app setting"
- "Add bookmark / analytics / feature flag support"
- "Add a chart / people picker / person column to AG Grid"
- "How do I write a custom Fusion Framework module?"
- "Should this be a Fusion module or a React context?"
- "Write tests for this Fusion component / hook / route"
- "Mock auth, context, feature flags, or HTTP in this test"
Implicit triggers:
- Building in
src/ - References Fusion Framework modules, EDS,
@equinor/fusion-react-*, or styled-components - References app settings, bookmarks, analytics,
app.config.ts - Adding route, page, or data-fetching layer
- Adding or updating
*.test.ts/*.test.tsx,vitest.config.ts, or Fusion test fixtures - References charting:
@equinor/fusion-framework-react-ag-charts,chart.js,react-chartjs-2
When not to use
Do not use this skill for:
- Issue authoring/triage →
fusion-issue-authoring - Skill authoring →
fusion-skill-authoring - Backend/service changes (separate repo)
- CI/CD or deployment config
- Architecture docs (use ADR template)
For Fusion Framework package ownership, hook behavior, or example discovery → use fusion-research first.
Required inputs
Mandatory
- What to build: feature, component, hook, or service description
- Where it fits: layer (component, hook, service, type) and parent/sibling context
For ambiguous requests, consult assets/follow-up-questions.md before implementing.
Conditional
- API endpoint details when the feature involves data fetching
- Design/layout specifics when building visual components
- Fusion module name when extending module configuration
- Whether state should persist per-user, be shareable via bookmark, or stay runtime-only
- Expected test layer: pure logic, hook, component, route, complete app, or module graph
- External boundaries tests must seed: auth, context, services, feature flags, bookmarks, or HTTP
What ships with it
34 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/code-quality.md 2.4 KB
- agents/data-display.md 5.7 KB
- agents/design.md 5.1 KB
- agents/framework.md 4.8 KB
- agents/person-components.md 4.7 KB
- agents/styling.md 3.3 KB
- agents/testing.md 1.7 KB
- assets/charts-decision-matrix.md 2.1 KB
- assets/follow-up-questions.md 4.4 KB
- assets/new-app-checklist.md 3.6 KB
- assets/review-checklist.md 4.8 KB
- CHANGELOG.md 4.9 KB
- references/configure-mocking.md 5.8 KB
- references/configure-services.md 3.8 KB
- references/create-fusion-app.md 2.5 KB
- references/project-structure.md 3.1 KB
- references/styled-components.md 2.7 KB
- references/styling-with-eds.md 3.8 KB
- references/testing.md 2.4 KB
- references/using-ag-charts.md 5.5 KB
- references/using-ag-grid-charts.md 3.2 KB
- references/using-ag-grid.md 5.3 KB
- references/using-analytics.md 2.5 KB
- references/using-assets-and-environment.md 3.1 KB
- references/using-bookmarks.md 3.4 KB
- references/using-context.md 8.8 KB
- references/using-custom-modules.md 3.9 KB
- references/using-feature-flags.md 5.6 KB
- references/using-framework-modules.md 4.6 KB
- references/using-fusion-react-components.md 7.3 KB
- references/using-people-service.md 3.7 KB
- references/using-react-query.md 3.5 KB
- references/using-router.md 6.9 KB
- references/using-settings.md 2.0 KB
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.
- 1mo ago Changed 191b5c5db30d
- 1mo ago First seen · 233 lines · 94 tokens per session scan A 60d1e7a43faf
fusion-developer-app is a skill published in the GitHub repository equinor/fusion-skills (2 stars, last pushed 14d ago), licensed MIT. It adds 94 tokens to every session and 2,797 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…
react-patterns
React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.
next-partial-prefetching-optimizer
Optimize what selected Next.js client navigations include before the click under Partial Prefetching. Use after Cache Components and Partial Prefetching are adopted when the user wants selected URL-specific UI to be instant, wants reusable content to wait for navigation, or needs to choose between default, viewport…
server-side-calls
Call tRPC procedures directly from server code using t.createCallerFactory() and router.createCaller(context) for integration testing, internal server logic, and custom API endpoints. Catch TRPCError and extract HTTP status with getHTTPStatusCodeFromError(). Error handling via onError option.
compiler-port
Port a compiler pass from TypeScript to Rust. Gathers context, plans the port, implements in a subagent with test-fix loop, then reviews.
release-safety
Release safety rules. INVOKE WHEN: yarn release, npm publish, release canary, release packages, publishing, skip checks, skip tests. NEVER skip checks or tests without explicit permission.