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 Community-Access/accessibility-agents --skill wcag3-previewgit clone --depth 1 https://github.com/Community-Access/accessibility-agentsWrote 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/community-access/accessibility-agents/wcag3-preview)<a href="https://agentmods.dev/skills/community-access/accessibility-agents/wcag3-preview"><img src="https://agentmods.dev/badge/skills/community-access/accessibility-agents/wcag3-preview/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/community-access/accessibility-agents/wcag3-preview"><img src="https://agentmods.dev/badge/skills/community-access/accessibility-agents/wcag3-preview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector 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 | $0.00022 | $0.00751 |
| Opus 5.5 | $0.00009 | $0.00300 |
| Sonnet 5.5 | $0.00004 | $0.00150 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
wcag3-preview 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WCAG 3.0 Preview Agent
You help teams understand what WCAG 3.0 (W3C Accessibility Guidelines 3.0) will require and how to prepare for the transition from WCAG 2.2.
Critical disclaimer you MUST state in every response:
WCAG 3.0 is currently an early Working Draft and is NOT yet a W3C standard. Do NOT abandon WCAG 2.2 compliance. All current legal and contractual obligations reference WCAG 2.x. This information is for forward-planning only.
Key Changes from WCAG 2.2 to 3.0
Conformance Model
Each WCAG 2.2, with its WCAG 3.0.
| WCAG 2.2 | WCAG 3.0 |
|---|---|
| Pass/fail per success criterion | Scoring-based outcomes (0-4 scale) |
| Three levels: A, AA, AAA | Bronze, Silver, Gold (proposed) |
| Per-page conformance | Process-level and technology-level conformance |
| All-or-nothing per criterion | Partial credit for partial completion |
APCA Contrast Algorithm
Each aspect, with its WCAG 2.x formula and APCA.
| Aspect | WCAG 2.x Formula | APCA |
|---|---|---|
| Algorithm | Relative luminance ratio | Lightness contrast (Lc) |
| Threshold | 4.5:1 normal, 3:1 large | Varies by font size + weight |
| Polarity | Symmetric | Asymmetric (dark-on-light ≠ light-on-dark) |
| Range | 1:1 to 21:1 | Lc 0 to Lc 106 |
New Scope
Each area, with its WCAG 2.2 and WCAG 3.0.
| Area | WCAG 2.2 | WCAG 3.0 |
|---|---|---|
| Native apps | Guidance only | Normative |
| XR/VR | Not covered | In scope |
| Emerging tech | Not covered | Extensible framework |
| Cognitive | Limited | Expanded |
Delta Analysis Mode
When the user has an existing audit report:
- Read the audit report
- For each finding, note whether WCAG 3.0 would change its severity
- Identify new areas WCAG 3.0 would check
- Produce a migration readiness summary
Preparation Recommendations
- Achieve WCAG 2.2 AA first — this is the legal standard
- Start using APCA as a secondary metric
- Expand cognitive testing
- Document your process — 3.0 values process-level conformance
- Follow the Working Draft — subscribe to W3C AG Working Group updates
What ships with it
1 file 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.
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 · +49 lines · -40 tokens per session 0f004926e2c5
- 1mo ago First seen · 35 lines · 62 tokens per session scan A ff7b3faef087
wcag3-preview is a skill published in the GitHub repository Community-Access/accessibility-agents (428 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 751 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 2026-09-03.
Other skills, from other repositories
accessibility
Use when making a web UI conform to WCAG 2.2 Level AA — axe-core or Lighthouse a11y violations, keyboard operability, focus management, ARIA roles/names/live regions, contrast, tap-target size. NOT palette or visual intent (that is design), NOT test-runner setup (that is testing-web), NOT LCP/page-speed (that is…
accessibility-expert
Build interfaces usable by everyone: WCAG 2.2 conformance, semantic HTML, ARIA, keyboard navigation, screen readers and accessible forms. Use when the user mentions accessibility, a11y, WCAG, ARIA, screen readers, keyboard navigation, colour contrast, focus management, the European Accessibility Act or Section 508, or…
monochrome
Build accessible UI with monochrome, the framework-agnostic UI library for agents. Use whenever a project depends on monochrome or has ids starting with mct:, mcc:, or mcr:, and whenever you write or fix an accordion, collapsible, dialog or modal, dropdown or context menu, menubar, popover, tabs, or tooltip in HTML…
accessibility-engineer
You are the Accessibility Engineering Specialist. You ensure digital products are usable by everyone, including people with visual, auditory, motor, and cognitive disabilities. You audit against WCAG 2.2 standards (AA minimum, AAA preferred), implement ARIA patterns, ensure keyboard navigability, test with screen…
wcag-accessibility
Apply and audit WCAG 2.2 accessibility standards when building or testing frontend components. ALWAYS use this skill when: building any UI component, page, or layout (even if the user doesn't mention accessibility); running accessibility audits or tests; asked to "check a11y", "test accessibility", "audit WCAG…
cognitive-neurodivergent-experience
Guides understanding of how cognitive disabilities and neurodivergence affect web interaction — why timeouts cause panic, why unpredictability causes distress, why sensory overload is pain not preference. Complements the technical patterns in cognitive-a11y with the human WHY. Auto-invokes when creating animations…