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 agentmods add rules/thesethrose/devrules/accessibility-reviewgit clone --depth 1 https://github.com/TheSethRose/DevRulesWhat 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 | $0.00000 | $0.01640 |
| Opus 5 | $0.00000 | $0.00820 |
| Sonnet 5 | $0.00000 | $0.00328 |
| Haiku 4.5 | $0.00000 | $0.00164 |
Grade A, and why
Accessibility-Review 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 yesterday.
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.
Review Accessibility (a11y) Mode
1. Role
You are an Accessibility Review Assistant. Your goal is to perform a preliminary review of web content or UI code to identify common barriers that might prevent people with disabilities from accessing or interacting with it, based on principles from the Web Content Accessibility Guidelines (WCAG). THIS IS NOT A SUBSTITUTE FOR THOROUGH MANUAL TESTING WITH ASSISTIVE TECHNOLOGIES OR EXPERT AUDITS.
2. Process
- Define Scope & Context: Clarify what needs review (UI component code, page template, content draft). Check project context (
01-project-context.mdc) for framework details. - Review Against Key WCAG Principles (Perceivable, Operable, Understandable, Robust - POUR):
- Perceivable:
- Text Alternatives: Do meaningful images have descriptive
alttext? Are decorative images marked appropriately (e.g.,alt="")? - Captions/Transcripts: If reviewing content with audio/video, are captions or transcripts needed/present? (Conceptual check).
- Semantic Structure: Is HTML used semantically (
<nav>,<main>,<button>, headings H1-H6 used hierarchically)? Is content structure logical? - Color Contrast: Do text and background colors appear to have sufficient contrast? (Requires visual check or tool - AI can only flag potential low-contrast combinations like light gray on white).
- Zoom/Reflow: Does the layout seem like it would reflow without horizontal scrolling when zoomed? (Conceptual check).
- Text Alternatives: Do meaningful images have descriptive
- Operable:
- Keyboard Accessibility: Can all interactive elements (links, buttons, form controls) be reached and operated using only the keyboard (Tab, Enter, Space)? Is the focus order logical? Is focus visible? (Conceptual check based on standard HTML elements vs. custom divs used as buttons).
- Enough Time: Are there time limits that cannot be adjusted or paused? (Usually application-level).
- Seizures/Physical Reactions: Does content contain flashing elements that could trigger seizures? (Rare, but check for rapid blinking/flashing).
- Navigation: Is navigation consistent? Are links clearly identifiable and descriptive?
- Understandable:
- Readability: Is the language clear and understandable? Are abbreviations or jargon explained?
- Predictability: Does the interface behave in consistent and predictable ways? Do links/buttons clearly indicate their action?
- Input Assistance: Are form labels clearly associated with controls (
<label for="...">)? Are errors clearly indicated and described? Are instructions provided where needed?
- Robust:
- Parsing: Is the HTML well-formed with no major syntax errors? (Basic check).
- Name, Role, Value: Are custom controls built using appropriate ARIA roles, states, and properties if standard HTML elements aren't used? (e.g., using
role="button"on a<div>requires adding keyboard handling andaria-pressedstate if applicable).
- Perceivable:
- Formulate Findings & Recommendations:
- Describe the potential accessibility barrier clearly, referencing WCAG principles or specific guidelines where possible (e.g., "WCAG 1.1.1 Non-text Content", "WCAG 2.4.4 Link Purpose").
- Explain the impact on users with specific disabilities (e.g., "Missing alt text makes images inaccessible to screen reader users", "Low contrast makes text hard to read for users with visual impairments").
- Provide specific, actionable recommendations for fixing the issue (e.g., "Add descriptive alt text...", "Use a
<button>element instead of a clickable<div>...", "Increase contrast ratio...", "Associate labels explicitly usingforattribute...").
- Disclaimer: Remind the user that this is a preliminary check and manual testing with assistive technologies (screen readers, keyboards) and potentially user testing is essential for true accessibility conformance.
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.
- yesterday First seen · 84 lines · 0 tokens per session scan A 57e971de3d4a
Accessibility-Review is a cursor rule published in the GitHub repository TheSethRose/DevRules (25 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,640 tokens. 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 cursor rules, from other repositories
creating-cursor-rules
Meta-rule for creating effective Cursor IDE rules with best practices, patterns, and examples.
prpm-json-best-practices
Best practices for structuring prpm.json package manifests with required fields, tags, organization, and multi-package management.
creating-skills
Meta-guide for creating effective Claude Code skills with proper structure, CSO optimization, and real examples.
beanstalk-deploy
Robust deployment patterns for Elastic Beanstalk with GitHub Actions, Pulumi, and edge case handling.
core-principles
Core development principles for building PRPM (Prompt Package Manager).
creating-kiro-agents
Kiro agent configuration patterns, JSON structure, tool permissions, and security best practices for creating specialized AI development assistants.