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/lacymorrow/paperclip-hubWrote 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/lacymorrow/paperclip-hub/accessibility)<a href="https://agentmods.dev/rules/lacymorrow/paperclip-hub/accessibility"><img src="https://agentmods.dev/badge/rules/lacymorrow/paperclip-hub/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/lacymorrow/paperclip-hub/accessibility"><img src="https://agentmods.dev/badge/rules/lacymorrow/paperclip-hub/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 | $0.00000 | $0.00454 |
| Opus 5.5 | $0.00000 | $0.00182 |
| Sonnet 5.5 | $0.00000 | $0.00091 |
| Haiku 4.5 | $0.00000 | $0.00045 |
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 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Best Practices
Semantic HTML
- Use proper heading hierarchy
- Use semantic elements (nav, main, article)
- Use proper list structures
- Use proper table markup
- Use proper form labels
- Use ARIA roles when needed
- Validate HTML structure
Keyboard Navigation
- Ensure keyboard focus visibility
- Implement logical tab order
- Provide skip links
- Handle keyboard shortcuts
- Test keyboard-only navigation
- Support focus management
- Document keyboard interactions
Screen Readers
- Provide alt text for images
- Use proper ARIA labels
- Implement proper headings
- Announce dynamic content
- Test with screen readers
- Support text-to-speech
- Document screen reader support
Visual Design
- Ensure sufficient color contrast
- Support high contrast modes
- Provide text alternatives
- Allow text resizing
- Support zoom functionality
- Avoid reliance on color alone
- Test with color blindness tools
Interactive Elements
- Make buttons keyboard accessible
- Make modals accessible
- Make dropdowns accessible
- Handle focus management
- Provide feedback on actions
- Support touch interfaces
- Test all interactions
Forms
- Use proper labels
- Provide clear error messages
- Support keyboard navigation
- Group related fields
- Validate input accessibly
- Support autocomplete
- Test form submissions
Media
- Provide captions for videos
- Provide transcripts for audio
- Support media controls
- Allow volume control
- Provide media alternatives
- Test media playback
- Document media features
Dynamic Content
- Announce updates
- Handle loading states
- Manage focus on updates
- Provide progress indicators
- Support pause/stop
- Test dynamic changes
- Document behavior
Testing
- Use accessibility checkers
- Test with screen readers
- Test keyboard navigation
- Test color contrast
- Test with users
- Regular audits
- Document findings
Documentation
- Document accessibility features
- Provide usage guidelines
- Document known issues
- Keep VPAT updated
- Document test results
- Regular reviews
- Maintain compliance docs
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 · 97 lines · 454 tokens per session scan A c9c41d451471
accessibility is a cursor rule published in the GitHub repository lacymorrow/paperclip-hub (15 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 454 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 2026-11-10.
accessibility compared with cursor rules from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| accessibilitylacymorrow/paperclip-hub | Cursor rule | 15 | yesterday | MIT | A | 0 | Cursor |
| design-tokens-guidefirst-fluke/fullstack-starter | Cursor rule | 226 | 2d ago | MIT | A | 12 | Cursor |
| ultraciteelie222/inbox-zero | Cursor rule | 13k | today | none | A | 0 | Cursor |
| ui-componentsAgentDock/AgentDock | Cursor rule | 1.8k | 4mo ago | MIT | A | 0 | Cursor |
| always-push-pritsmemeworks/adhx | Cursor rule | 19 | 5d ago | MIT | A | 279 | Cursor |
| ui-design-systemkrivoox/agent-stack-template | Cursor rule | 30 | 1mo ago | MIT | A | 0 | Cursor |
| accessibility-guidelinesWebDevPeterGriffin/The-VibeCode-Bible | Cursor rule | 42 | 7d ago | none | A | 0 | Cursor |