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/nedcodes-ok/cursor-doctorWrote 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/nedcodes-ok/cursor-doctor/accessibility)<a href="https://agentmods.dev/rules/nedcodes-ok/cursor-doctor/accessibility"><img src="https://agentmods.dev/badge/rules/nedcodes-ok/cursor-doctor/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/rules/nedcodes-ok/cursor-doctor/accessibility"><img src="https://agentmods.dev/badge/rules/nedcodes-ok/cursor-doctor/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 | $0.01145 | $0.01145 |
| Opus 5.5 | $0.00458 | $0.00458 |
| Sonnet 5.5 | $0.00229 | $0.00229 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
accessibility 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.
This is a copy
100% identical to accessibility — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Rules
Semantic HTML (the foundation)
- Heading hierarchy:
h1→h2→h3, never skip levels. Screen readers use headings to navigate — a page that goes h1 → h3 → h2 is like a book with shuffled chapters - Semantic elements:
<nav>for navigation,<main>for primary content,<article>for standalone content,<aside>for related info,<footer>for footer. These create landmarks that screen readers use for quick navigation — a<div>with a class name does nothing <button>for actions (submit, toggle, delete),<a>for navigation (go to another page/section). Never<div onClick>— it has no keyboard support, no focus, no role announcement. If you must use a div, you needrole="button",tabIndex={0},onKeyDownfor Enter+Space — or just use<button>- Every
<input>needs a visible<label>withhtmlFor/formatching the input'sid. Placeholder text is NOT a label — it disappears on focus, isn't announced by all screen readers, and has poor contrast <table>for tabular data, not layout. With<caption>,<thead>,<th scope="col">— screen readers announce "row 3, column 2: $45.00" which is useless without headers
ARIA (last resort, not first)
- ARIA is a repair tool — use it when HTML semantics can't express the pattern.
<nav aria-label="Main">is correct (distinguishes multiple navs).<div role="navigation">instead of<nav>is wrong — use the HTML element - Icon-only buttons MUST have accessible text:
<button aria-label="Close"><CloseIcon /></button>. Without it, screen readers announce "button" with no indication of what it does aria-live="polite"for dynamic content updates (toast notifications, form validation messages, loading states). Without it, screen readers don't announce content that changes after page loadaria-expanded="true/false"on toggles (accordion headers, dropdown triggers) — tells users whether the controlled content is visiblearia-hidden="true"on decorative elements (icons next to text labels, background SVGs) — removes them from the accessibility tree so screen readers don't announce noise
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 First seen · 40 lines · 1,145 tokens per session scan A d6436141e01f
accessibility is a cursor rule published in the GitHub repository nedcodes-ok/cursor-doctor (9 stars, last pushed 7mo ago), licensed MIT. It adds 1,145 tokens to every session, about $0.0046 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to accessibility, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
test-patterns
Selenium pytest test patterns — data-driven tests, fixtures, error handling, and performance checks.
testing-fundamentals
Core Cypress testing principles — selector strategy, smart waiting, and spec organization. Apply when writing or reviewing Cypress E2E tests.
web
Web build conventions (separate from native and RN JS).
components
Component patterns and UI conventions.
git
Git workflow and commit conventions.
minimax-m3-self-evolution
MiniMax M3 self-evolution harness: iterative refinement loops, compress-before-iterate, autonomous debugging, and recursive improvement patterns.