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 skills add mikeparcewski/wicked-garden --skill accessibilitygit clone --depth 1 https://github.com/mikeparcewski/wicked-gardenWrote 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/mikeparcewski/wicked-garden/accessibility)<a href="https://agentmods.dev/skills/mikeparcewski/wicked-garden/accessibility"><img src="https://agentmods.dev/badge/skills/mikeparcewski/wicked-garden/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/skills/mikeparcewski/wicked-garden/accessibility"><img src="https://agentmods.dev/badge/skills/mikeparcewski/wicked-garden/accessibility.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00072 | $0.01749 |
| Opus 5.5 | $0.00029 | $0.00700 |
| Sonnet 5.5 | $0.00014 | $0.00350 |
| Haiku 4.5 | $0.00007 | $0.00175 |
Grade A, and why
wicked-garden-product-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.
How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Skill
WCAG 2.1 Level AA compliance auditing and inclusive design guidance.
Core Principle
Accessibility is not optional. It's legal compliance, user respect, and better code.
WCAG 2.1 Four Principles: POUR
1. Perceivable
Information must be presentable to users in ways they can perceive.
- Text alternatives for images
- Color contrast 4.5:1 (normal), 3:1 (large)
- No info by color alone
2. Operable
Interface components must be operable.
- All functionality via keyboard
- No keyboard traps
- Visible focus indicators
3. Understandable
Information and operation must be understandable.
- Form labels associated
- Error messages clear
- Consistent navigation
4. Robust
Content must work with assistive technologies.
- Valid HTML (no duplicate IDs)
- Proper ARIA usage
- Status messages announced
Full WCAG checklists: See refs/wcag-checklist.md
Quick Audit Process
1. Automated Scan
Open a screenshot file with your harness's file reader, or capture via browser automation if available (e.g., Playwright, Puppeteer, or an MCP browser tool). For automated WCAG scanning, use axe DevTools, Lighthouse, WAVE, or pa11y.
2. Keyboard Test (5 minutes)
- Tab through entire page
- Can reach all interactive elements?
- Focus always visible?
- Tab order logical?
- Can escape modals/menus?
Full keyboard testing guide: See refs/keyboard-testing-basics.md and refs/keyboard-testing-patterns.md
3. Screen Reader Spot Check
- Turn on VoiceOver (Mac) or NVDA (Windows)
- Are images described?
- Are buttons/links clear?
- Are form labels read?
Full screen reader guide: See refs/screen-reader-testing-commands.md and refs/screen-reader-testing-advanced.md
4. Code Review
# Find potential issues — the wicked-garden-search skill over html files:
# <div.*onclick non-semantic buttons
# <img(?!.*alt) missing alt
# aria- ARIA usage
What ships with it
12 files 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.
- refs/aria-patterns-basics.md 5.8 KB
- refs/aria-patterns-dynamic.md 4.4 KB
- refs/aria-patterns-interactive.md 6.0 KB
- refs/audit-report-findings.md 5.0 KB
- refs/audit-report-results.md 5.7 KB
- refs/common-violations-html-css.md 5.8 KB
- refs/common-violations-interactive.md 6.7 KB
- refs/keyboard-testing-basics.md 5.5 KB
- refs/keyboard-testing-patterns.md 4.1 KB
- refs/screen-reader-testing-advanced.md 6.7 KB
- refs/screen-reader-testing-commands.md 6.3 KB
- refs/wcag-checklist.md 7.6 KB
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 Changed · -6 lines dab4c6bca6df
- 2mo ago First seen · 197 lines · 72 tokens per session scan A ab49319b518e
wicked-garden-product-accessibility is a skill published in the GitHub repository mikeparcewski/wicked-garden (9 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 1,749 once invoked, about $0.0003 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 2026-09-03.
wicked-garden-product-accessibility compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wicked-garden-product-accessibilitymikeparcewski/wicked-garden | Skill | 9 | yesterday | MIT | A | 72 | Claude Code |
| accessibility-compliancebromso/metapowers | Skill | 3 | 14d ago | MIT | A | 90 | Claude Code |
| webgl-particle-galaxynexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 126 | Claude Code, Codex |
| webgl-liquid-metalnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 121 | Claude Code, Codex |
| webgl-horizontal-parallaxnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 41 | Claude Code, Codex |
| top-designwondelai/skills | Skill | 2.6k | 6d ago | MIT | A | 113 | Claude Code, Codex |
| designlang-tokensManavarya09/design-extract | Skill | 4.9k | 3d ago | MIT | A | 30 | Claude Code |