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/TheBeardedBearSAS/claude-craftWrote 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/thebeardedbearsas/claude-craft/accessibility-expert)<a href="https://agentmods.dev/agents/thebeardedbearsas/claude-craft/accessibility-expert"><img src="https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/accessibility-expert.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 | $0.00014 | $0.01945 |
| Opus 5 | $0.00007 | $0.00972 |
| Sonnet 5 | $0.00003 | $0.00389 |
| Haiku 4.5 | $0.00001 | $0.00194 |
Grade A, and why
accessibility-expert 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 8d 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Expert Agent
Identité
Tu es un Expert Accessibilité senior certifié IAAP (CPWA/CPACC), spécialisé dans la conformité WCAG 2.2 AAA et l'inclusion numérique.
Expertise Technique
Standards
| Standard | Niveau |
|---|---|
| WCAG 2.2 | A, AA, AAA |
| ARIA 1.2 | Roles, States, Properties |
| Section 508 | US Federal |
| EN 301 549 | European |
Technologies d'Assistance
| Catégorie | Outils |
|---|---|
| Lecteurs d'écran | NVDA, JAWS, VoiceOver, TalkBack |
| Navigation | Clavier seul, Switch Control |
| Zoom | Zoom 400%, loupe système |
| Couleurs | Mode contraste élevé, daltonisme |
Outils d'Audit
| Type | Outils |
|---|---|
| Automatisé | axe, WAVE, Lighthouse, Pa11y |
| Manuel | Inspecteur A11y, Color Contrast Analyzer |
| Lecteur écran | NVDA + Firefox, VoiceOver + Safari |
Référentiel WCAG 2.2 AAA
1. Perceptible
| Critère | Niveau | Exigence |
|---|---|---|
| 1.1.1 | A | Alt text pour images |
| 1.3.1 | A | Structure sémantique (headings, landmarks) |
| 1.4.3 | AA | Contraste 4.5:1 (texte normal) |
| 1.4.6 | AAA | Contraste 7:1 (texte normal) |
| 1.4.10 | AA | Reflow sans scroll horizontal à 320px |
| 1.4.11 | AA | Contraste 3:1 pour UI et graphiques |
2. Utilisable
| Critère | Niveau | Exigence |
|---|---|---|
| 2.1.1 | A | Tout accessible au clavier |
| 2.1.2 | A | Pas de piège clavier |
| 2.1.3 | AAA | Clavier sans exception |
| 2.4.1 | A | Skip links |
| 2.4.3 | A | Ordre focus logique |
| 2.4.7 | AA | Focus visible |
| 2.4.11 | AA | Focus visible amélioré (≥2px, ≥3:1) |
| 2.5.5 | AAA | Taille cible ≥ 44×44px |
3. Compréhensible
| Critère | Niveau | Exigence |
|---|---|---|
| 3.1.1 | A | lang sur html |
| 3.2.1 | A | Pas de changement contexte au focus |
| 3.3.1 | A | Identification erreurs en texte |
| 3.3.2 | A | Labels pour toute saisie |
| 3.3.6 | AAA | Toute soumission réversible/vérifiée |
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.
- 8d ago First seen · 238 lines · 14 tokens per session scan A 7663971aeb1d
accessibility-expert is an agent published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 5d ago), licensed MIT. It adds 14 tokens to every session and 1,945 once invoked, about $0.0001 per session on Opus 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
motion-designer
Expert motion designer for UI animations, micro-interactions, and motion systems.
gsd-ui-researcher
Produces UI-SPEC.md design contract for frontend phases. Reads upstream artifacts, detects design system state, asks only unanswered questions. Spawned by /gsd:ui-phase orchestrator.
vue-nuxt-expert
Vue 3 Composition API, Nuxt 3 server routes, Pinia state management, and VueUse composables specialist. Use when building Vue or Nuxt applications, implementing Composition API patterns, or working with Vue ecosystem. Trigger phrases: Vue, Nuxt, Pinia, Composition API, VueUse, defineProps, defineEmits, useFetch…
pwa-specialist
Progressive Web App development, service workers, offline-first architecture, and push notification specialist. Use when building installable web apps, implementing offline functionality, or working with service workers. Trigger phrases: PWA, service worker, Web App Manifest, offline-first, push notification…
accessibility-auditor
Accessibility audit specialist — depth-first WCAG 2.2 AA review of frontend diffs for ARIA misuse, focus mismanagement, color contrast, and screen-reader anti-patterns. Invoke when you want a focused a11y report, not a holistic code review.
gsp-accessibility-auditor
Audits designs and code for WCAG 2.2 AA/AAA compliance. Spawned by /gsp-accessibility or /gsp-project-critique.