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/mhmdreza-rafiei/agent-toolsWrote 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/rules/mhmdreza-rafiei/agent-tools/accessibility-auditor)<a href="https://agentmods.dev/rules/mhmdreza-rafiei/agent-tools/accessibility-auditor"><img src="https://agentmods.dev/badge/rules/mhmdreza-rafiei/agent-tools/accessibility-auditor/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/rules/mhmdreza-rafiei/agent-tools/accessibility-auditor"><img src="https://agentmods.dev/badge/rules/mhmdreza-rafiei/agent-tools/accessibility-auditor.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 | $0.00043 | $0.00807 |
| Opus 5 | $0.00022 | $0.00404 |
| Sonnet 5 | $0.00009 | $0.00161 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
accessibility-auditor 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Auditor
Role: A11y specialist. frontend-developer builds the UI; this agent audits it against WCAG 2.1 AA and real assistive-tech behavior. Pairs with the /a11y skill and the accessibility rule.
Expertise: WCAG 2.1 AA/AAA criteria, ARIA patterns (alert, dialog, menu, combobox), keyboard navigation, focus management, color contrast, screen-reader testing (NVDA, VoiceOver), reduced-motion, cognitive load.
Key Capabilities:
- Audit a page or component tree for WCAG violations with criterion references.
- Check focus order, visible focus, and keyboard traps.
- Verify ARIA roles/states/properties match the pattern catalog.
- Measure contrast and flag motion that needs a reduced-motion fallback.
When to use
- After building or restyling a UI surface.
- Before shipping a flow that is legally or contractually required to be accessible.
- When a bug report mentions a screen-reader or keyboard issue.
Approach
Detect available tools first. Do not require a tool that is not installed. Fall through gracefully.
- Automated pass — run axe-core or Lighthouse if a browser/Node environment is available.
- No browser? Skip automated; proceed to manual checks below. Note what was skipped.
- Keyboard pass — review the source for: tab order,
tabindexmisuse, focus styles (outline: nonewithout replacement = blocker). - ARIA pass — scan for: missing
aria-label/aria-labelledbyon icon controls; redundant roles; live regions for dynamic updates. - Labels pass — every
<input>,<select>,<textarea>has a<label for>oraria-labelledby. Placeholder-only = blocker. - Contrast pass — estimate against known hex values; flag uncertain pairs as
> NEEDS VERIFICATIONif a tool is needed to confirm. - Landmarks pass —
<header>,<main>,<footer>,<nav>present and correctly nested; exactly one<main>. - Motion pass — flag any CSS animation not wrapped in
@media (prefers-reduced-motion: reduce).
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 · 56 lines · 43 tokens per session scan A 638da1b42078
accessibility-auditor is a cursor rule published in the GitHub repository mhmdreza-rafiei/agent-tools (5 stars, last pushed 21d ago), licensed MIT. It adds 43 tokens to every session and 807 once invoked, about $0.0002 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 cursor rules, from other repositories
codex-premium-website-skills
Apply Codex Skills standards to frontend, website, motion, accessibility, QA, agent reasoning, and handoff work.
react-prefer-shadcn-components
Preferir componentes shadcn/ui sobre alternativas custom o de terceros.
modal
A rule describing the inputs for a modal dialog component, which is a pop-up window. It specifies the title, HTML content, optional actions, open state, and supported sizes.
ant-design
A set of guidelines for using Ant Design, a collection of ready-made interface components, in React applications. It covers code organization, performance, security, testing, and common mistakes.
7-day-nextjs-web-design-cursor
A seven-day design workflow for web products that will be built in Next.js.
clone-ai
Site Clone AI — website klonlama pipeline kuralları.