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 boparaiamrit/skills-by-amrit --skill accessibility-auditgit clone --depth 1 https://github.com/boparaiamrit/skills-by-amritWrote 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/boparaiamrit/skills-by-amrit/accessibility-audit)<a href="https://agentmods.dev/skills/boparaiamrit/skills-by-amrit/accessibility-audit"><img src="https://agentmods.dev/badge/skills/boparaiamrit/skills-by-amrit/accessibility-audit/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/boparaiamrit/skills-by-amrit/accessibility-audit"><img src="https://agentmods.dev/badge/skills/boparaiamrit/skills-by-amrit/accessibility-audit.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 | $0.00029 | $0.03011 |
| Opus 5 | $0.00015 | $0.01505 |
| Sonnet 5 | $0.00006 | $0.00602 |
| Haiku 4.5 | $0.00003 | $0.00301 |
Grade A, and why
accessibility-audit 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 11d 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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Audit
Overview
Accessibility is not an afterthought — it's a legal requirement and an ethical obligation. 15% of the world's population has a disability. Accessible design is better design for everyone.
Core principle: If it doesn't work with a keyboard and a screen reader, it's broken for millions of users.
The Iron Law
NO INTERACTIVE ELEMENT WITHOUT KEYBOARD ACCESS. NO IMAGE WITHOUT ALT TEXT. NO FORM INPUT WITHOUT LABEL. NO COLOR AS SOLE INDICATOR.
When to Use
- Building any user interface
- Auditing existing UI for compliance
- Before launch or major release
- When accessibility complaints arise
- During frontend audit
- When targeting government or enterprise clients (legal compliance)
When NOT to Use
- CLI tools or backend services (no UI)
- API-only projects (use
api-design-audit) - If the
frontend-auditquick accessibility check found no issues AND the app is simple (< 5 pages)
Anti-Shortcut Rules
YOU CANNOT:
- Say "accessibility looks fine" — test every interactive element with keyboard only
- Say "alt text is present" — verify it's DESCRIPTIVE, not "image" or "photo" or the filename
- Say "forms are accessible" — verify every input has a VISIBLE label (placeholder is NOT a label)
- Say "contrast is fine" — measure actual contrast ratios (4.5:1 text, 3:1 components)
- Skip screen reader testing — use NVDA, VoiceOver, or at minimum, test with browser accessibility tree
- Say "we use semantic HTML" — check for div-as-button, span-as-link, div-as-list patterns
- Accept "it works with a mouse" as sufficient — mouse users are NOT the accessibility bar
- Say "ARIA will fix it" — ARIA is a last resort; native HTML is always preferred
Common Rationalizations (Don't Accept These)
| Rationalization | Reality |
|---|---|
| "Our users don't have disabilities" | You don't know that. 15% of all people do. Plus situational disabilities (broken arm, bright sunlight). |
| "We'll add accessibility later" | Retrofitting accessibility is 10x harder than building it in. |
| "Screen readers aren't our target" | Screen readers are used by blind, low-vision, dyslexic, and cognitively impaired users. Plus SEO benefits. |
| "Placeholder text is fine as a label" | Placeholders disappear on input — users forget what the field is for mid-typing. |
| "We removed focus outlines because they're ugly" | You just broke keyboard navigation. Style them, don't remove them. |
| "Only sighted users use our app" | Temporary impairments, aging, situational contexts (screen glare, one hand busy) affect everyone. |
| "ARIA will make it accessible" | Wrong ARIA is worse than no ARIA. Use native HTML elements first, always. |
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.
- 11d ago First seen · 288 lines · 29 tokens per session scan A adea6e3f739d
accessibility-audit is a skill published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 3,011 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.