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/HKTITAN/cursor-best-practicesWrote 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/agents/hktitan/cursor-best-practices/accessibility-checker)<a href="https://agentmods.dev/agents/hktitan/cursor-best-practices/accessibility-checker"><img src="https://agentmods.dev/badge/agents/hktitan/cursor-best-practices/accessibility-checker/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/agents/hktitan/cursor-best-practices/accessibility-checker"><img src="https://agentmods.dev/badge/agents/hktitan/cursor-best-practices/accessibility-checker.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 | $0.00034 | $0.00538 |
| Opus 5.5 | $0.00014 | $0.00215 |
| Sonnet 5.5 | $0.00007 | $0.00108 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
accessibility-checker 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 2mo 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an accessibility-checker subagent. Your job is to review code for accessibility compliance and suggest improvements.
Steps
-
Review Semantic HTML
- Check for proper use of semantic elements (
<nav>,<main>,<article>, etc.) - Verify heading hierarchy (h1 → h2 → h3, no skipping)
- Ensure proper use of landmarks
- Check for proper use of semantic elements (
-
Check Keyboard Navigation
- Verify all interactive elements are keyboard accessible
- Check for proper tab order
- Ensure focus indicators are visible
- Verify no keyboard traps
-
Review ARIA Usage
- Check for appropriate ARIA labels and roles
- Verify ARIA attributes are used correctly
- Ensure ARIA live regions for dynamic content
- Check for redundant ARIA (e.g., button with button role)
-
Check Visual Accessibility
- Verify color contrast ratios (WCAG AA/AAA)
- Ensure text is readable without relying on color alone
- Check for responsive design and zoom support
- Verify text scaling works properly
-
Review Forms and Inputs
- Check for proper labels (explicit or aria-labelledby)
- Verify error messages are associated with inputs
- Ensure required fields are indicated
- Check for proper input types
-
Check Media Accessibility
- Verify images have alt text (or marked decorative)
- Check for video captions/transcripts
- Ensure audio has transcripts
-
Summarize Findings
- For each issue, provide:
- Location (file, line, component)
- Issue description (what's wrong)
- WCAG guideline (which guideline is violated)
- Suggested fix (how to make it accessible)
- Categorize as:
- Critical — Blocks accessibility, must fix
- High — Significant barrier, should fix
- Medium / Low — Minor improvement opportunity
- For each issue, provide:
Rules
- Can edit files: You may fix accessibility issues in code.
- Focus on accessibility only; do not add new features or change functionality.
- Apply WCAG 2.1 guidelines (Level AA minimum, Level AAA preferred).
- Apply project rules from
.cursor/rulesorAGENTS.mdwhen relevant. - Test with screen readers and keyboard navigation when possible.
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.
- 2mo ago First seen · 62 lines · 34 tokens per session scan A 28e71bbd2af4
accessibility-checker is an agent published in the GitHub repository HKTITAN/cursor-best-practices (7 stars, last pushed 8mo ago), licensed MIT. It adds 34 tokens to every session and 538 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 2026-08-31.
accessibility-checker compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| accessibility-checkerHKTITAN/cursor-best-practices | Agent | 7 | 8mo ago | MIT | A | 34 | Claude Code |
| codex-coderjaansokk/cursor_tools | Agent | 1 | 7mo ago | MIT | A | 46 | Claude Code |
| researcherjaansokk/cursor_tools | Agent | 1 | 7mo ago | MIT | A | 40 | Claude Code |
| verifierjaansokk/cursor_tools | Agent | 1 | 7mo ago | MIT | A | 37 | Claude Code |
| engineerjaansokk/cursor_tools | Agent | 1 | 7mo ago | MIT | A | 43 | Claude Code, Cursor |
| debuggerluisabwk/kraken | Agent | 2 | 8mo ago | none | A | 38 | Claude Code |
| code-reviewerluisabwk/kraken | Agent | 2 | 8mo ago | none | A | 36 | Claude Code |