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 skills/monkilabs/opencastle/accessibility-standardsnpx skills add monkilabs/opencastle --skill accessibility-standardsgit clone --depth 1 https://github.com/monkilabs/opencastleWrote 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/skills/monkilabs/opencastle/accessibility-standards)<a href="https://agentmods.dev/skills/monkilabs/opencastle/accessibility-standards"><img src="https://agentmods.dev/badge/skills/monkilabs/opencastle/accessibility-standards.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.00552 |
| Opus 5 | $0.00032 | $0.00276 |
| Sonnet 5 | $0.00013 | $0.00110 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
accessibility-standards 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 4d 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.
What it actually says
Accessibility Standards
Code must conform to WCAG 2.2 Level AA. Use people-first language ("person using a screen reader," not "blind user"); flag uncertain implementations with reasoning. Composite widget patterns (roving tabindex, aria-activedescendant) in REFERENCE.md.
Contrast
- Body text ≥4.5:1; large text (18.5px bold / 24px) ≥3:1.
- Graphics, controls, and state indicators (pressed, focus, checked) ≥3:1 against adjacent colors.
- Color is never the sole conveyor of information.
Keyboard
- No
tabindexon static elements;tabindex="-1"only for elements receiving programmatic focus. - Hidden elements must never be focusable.
- Skip link is the first focusable element, hidden via
.sr-only:not(:focus):not(:active) { clip-path: inset(50%); position: absolute; width: 1px; height: 1px; overflow: hidden; }. - Navigation:
<nav>+<ul>, NOTmenu/menubarroles. Togglearia-expanded; roving tabindex across top-level items.
Voice Access
An interactive element's accessible name must contain its visible label text — including when the name comes from aria-label.
Forms
- Required fields: asterisk in label +
aria-required="true". - Errors:
aria-invalid="true"+aria-describedbypointing at the message. - Never disable submit — show errors and focus the first invalid field.
- Disambiguate repeated labels ("Remove") with
aria-label.
Tables
<table> for static data; role="grid" with role="gridcell" nested in role="row" for interactive grids (date pickers, calendars).
Page Title
Unique per page, front-loading the unique info: "[Page] - [Section] - [Site]".
Validation
Run axe-core (axe-playwright or pa11y in CI); fix all high/critical findings and re-run until clean. Tab through the page to confirm order and visible focus. Accessibility Insights for manual passes.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 45 lines · 63 tokens per session scan A 4dce25d742b0
accessibility-standards is a skill published in the GitHub repository monkilabs/opencastle (61 stars, last pushed 7d ago), licensed MIT. It adds 63 tokens to every session and 552 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
design-audit
Audit a finished frontend change by measuring rendered rects and computed styles before using screenshots as human-checkable evidence.
frontend-design
Design thinking and decision-making for web UI. Use when designing components, layouts, color schemes, typography, or creating aesthetic interfaces. Teaches principles, not fixed values.
tailwind-patterns
Tailwind CSS v4 principles. CSS-first configuration, container queries, modern patterns, design token architecture.
tokens
Generates site/css/tokens.css from DESIGN-LOCK.md and brief/animation.md. Refuses to work until DESIGN-LOCK is frozen. Sole writer of tokens.css in the project.
gridproof
Automated spacing & grid QA for web UIs, inside the agent loop. Use for "design QA", "check spacing", "fix my grid/spacing", "audit UI", "design review", "show me the spacing issues", "generate a design report", "give me an audit report", and automatically after you generate or modify frontend UI. Renders the running…
ui-final-polish
Final visual polish for an existing UI without redesigning it. Use after structure is clear, when asked to improve spacing, alignment, text hierarchy, readability, shadows, highlights, effects, action placement, or overall production feel. For screen structure, layer naming, code handoff, preview scenes, or animation…