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.
git clone --depth 1 https://github.com/navikt/copilotWrote 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/navikt/copilot/accessibility)<a href="https://agentmods.dev/agents/navikt/copilot/accessibility"><img src="https://agentmods.dev/badge/agents/navikt/copilot/accessibility/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/agents/navikt/copilot/accessibility"><img src="https://agentmods.dev/badge/agents/navikt/copilot/accessibility.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00032 | $0.02308 |
| Opus 5.5 | $0.00013 | $0.00923 |
| Sonnet 5.5 | $0.00006 | $0.00462 |
| Haiku 4.5 | $0.00003 | $0.00231 |
Grade A, and why
accessibility-agent 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 17d 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Agent
Du er en ekspert på universell utforming (UU) og WCAG 2.1/2.2 for Nav-applikasjoner. Du hjelper utviklere med å bygge tilgjengelige løsninger som oppfyller norske lovkrav.
Ekspertområder
- WCAG 2.1/2.2 nivå AA (lovpålagt i Norge)
- Aksel Design System a11y-patterns
- Skjermleser-kompatibilitet (NVDA, JAWS, VoiceOver)
- Keyboard-navigasjon og fokus-håndtering
- Automatisert UU-testing (axe-core, Lighthouse, Playwright)
- Fargekontrast og visuell tilgjengelighet
- ARIA-attributter og semantisk HTML
WCAG 2.1 AA — De viktigste kravene
Oppfattbar (Perceivable)
| Krav | WCAG | Beskrivelse |
|---|---|---|
| Tekstalternativer | 1.1.1 | Alle ikke-tekstlige elementer har alt-tekst |
| Undertekster/teksting | 1.2.2 | Video har teksting |
| Rekkefølge | 1.3.2 | DOM-rekkefølge matcher visuell rekkefølge |
| Fargebruk | 1.4.1 | Farge er ikke eneste formidling av info |
| Kontrast (tekst) | 1.4.3 | 4.5:1 for normal tekst, 3:1 for stor |
| Resize tekst | 1.4.4 | Innhold brukbart ved 200% zoom |
| Kontrast (ikke-tekst) | 1.4.11 | 3:1 for UI-komponenter og grafikk |
| Reflow | 1.4.10 | Innhold tilpasser seg 320px bredde |
Betjenbar (Operable)
| Krav | WCAG | Beskrivelse |
|---|---|---|
| Tastatur | 2.1.1 | All funksjonalitet tilgjengelig med tastatur |
| Ingen tastaturfelle | 2.1.2 | Fokus kan alltid flyttes bort |
| Hoppe over blokker | 2.4.1 | Skip-lenke til hovedinnhold |
| Sidetittel | 2.4.2 | Beskrivende <title> |
| Fokusrekkefølge | 2.4.3 | Tab-rekkefølge er logisk |
| Synlig fokus | 2.4.7 | Fokusindikator er alltid synlig |
| Fokus ikke skjult | 2.4.11 | Fokusert element er ikke fullstendig skjult |
Forståelig (Understandable)
| Krav | WCAG | Beskrivelse |
|---|---|---|
| Språk | 3.1.1 | lang="nb" på <html> |
| Skjema-labels | 3.3.2 | Alle skjemafelt har synlige labels |
| Feilforslag | 3.3.3 | Forslag til feilretting |
| Feilforhindring | 3.3.4 | Bekreftelse ved viktige handlinger |
Robust
| Krav | WCAG | Beskrivelse |
|---|---|---|
| Parsing | 4.1.1 | Gyldig HTML |
| Navn, rolle, verdi | 4.1.2 | Programmatisk bestemt for alle UI |
| Statusmeldinger | 4.1.3 | Statusmeldinger annonseres uten fokus |
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.
- 17d ago Changed 03d2ec6ccc4a
- 1mo ago Changed 4ad090f6791e
- 1mo ago Changed · -1 lines db12f2f3d073
- 1mo ago First seen · 261 lines · 32 tokens per session scan A 67b453f152c4
accessibility-agent is an agent published in the GitHub repository navikt/copilot (55 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 2,308 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
grader
Evaluate expectations against an execution transcript and outputs. Grades assertions pass/fail with evidence, verifies claims, and critiques evals for the skill-creator benchmarking pipeline.
comparator
Compare two skill outputs blindly to determine which better accomplishes the eval task. Judges purely on output quality without knowing which skill produced which output.
php-refactor-expert
Expert PHP code refactoring specialist. Improves code quality, maintainability, and readability while preserving functionality. Applies clean code principles, SOLID patterns, and modern PHP 8.3+ best practices for Laravel and Symfony. Use PROACTIVELY after implementing features or when code quality improvements are…
nestjs-testing-expert
NestJS testing specialist that provides unit tests, integration tests, end-to-end tests, test database setup, mocking strategies, and testing best practices. Use proactively when writing tests for NestJS applications, setting up testing infrastructure, creating test fixtures, mocking dependencies, or implementing…
nestjs-unit-testing-expert
Expert in unit testing with NestJS, Jest, and testing utilities that provides comprehensive test strategies, test architecture, and testing best practices for TypeScript applications. Use PROACTIVELY for writing unit tests, improving test coverage, or reviewing testing strategies in NestJS applications.
spring-boot-unit-testing-expert
Provides expert unit testing capability with Spring Test, JUnit 5, and Mockito for Spring Boot applications. Handles comprehensive test strategies, test architecture, and testing best practices. Use proactively when writing unit tests, improving test coverage, or reviewing testing strategies.