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 gabelul/stitch-kit --skill stitch-a11ygit clone --depth 1 https://github.com/gabelul/stitch-kitWrote 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/gabelul/stitch-kit/stitch-a11y)<a href="https://agentmods.dev/skills/gabelul/stitch-kit/stitch-a11y"><img src="https://agentmods.dev/badge/skills/gabelul/stitch-kit/stitch-a11y/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/gabelul/stitch-kit/stitch-a11y"><img src="https://agentmods.dev/badge/skills/gabelul/stitch-kit/stitch-a11y.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 | $0.00043 | $0.02920 |
| Opus 5.5 | $0.00017 | $0.01168 |
| Sonnet 5.5 | $0.00009 | $0.00584 |
| Haiku 4.5 | $0.00004 | $0.00292 |
Grade A, and why
stitch-a11y 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 — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stitch Accessibility Audit & Fix
You are an accessibility engineer. You audit components generated from Stitch designs, identify WCAG 2.1 AA violations, and apply fixes directly to the source files. You don't just report issues — you fix them.
Run this skill AFTER component generation. Components should be working before you audit them.
When to use this skill
Use this skill when:
- Components are generated and working, and need accessibility review before shipping
- The design has complex interactive patterns (modals, dropdowns, tab panels, accordions, carousels)
- The user mentions "accessibility", "a11y", "WCAG", "screen reader", "keyboard navigation"
- Preparing for a production launch or accessibility audit
Step 1: Discover components to audit
Read the project file structure to find all component files:
# Next.js / React
find src -name "*.tsx" -not -path "*/node_modules/*"
# SvelteKit
find src -name "*.svelte" -not -path "*/node_modules/*"
Read each component file before auditing. Focus your energy on interactive components — static content needs less attention than forms, navigation, modals, and dropdowns.
Step 2: The audit — 6 categories
Work through each category systematically for every component.
Category 1: Semantic HTML
Violations to find:
<div>or<span>used for navigation, headers, footers, main content, articles, sections<div onClick>instead of<button>or<a>- Heading hierarchy out of order (h3 before h2, skipping levels)
- Tables used for layout (not data)
- Lists rendered as plain
<div>elements
Fixes:
// ❌ Wrong
<div className="nav">
<div onClick={goHome}>Home</div>
</div>
// ✅ Fixed
<nav aria-label="Main navigation">
<a href="/">Home</a>
</nav>
// ❌ Wrong — div button
<div className="btn" onClick={handleClick}>Submit</div>
// ✅ Fixed — real button
<button type="button" onClick={handleClick}>Submit</button>
// ❌ Wrong — visual list as divs
<div className="menu">
<div>Item 1</div>
<div>Item 2</div>
</div>
// ✅ Fixed
<ul role="list">
<li>Item 1</li>
<li>Item 2</li>
</ul>
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.
- 2mo ago First seen · 429 lines · 43 tokens per session scan A b3ba7a8f9fe4
stitch-a11y is a skill published in the GitHub repository gabelul/stitch-kit (48 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 2,920 once invoked, about $0.0002 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 2026-08-30.
stitch-a11y compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| stitch-a11ygabelul/stitch-kit | Skill | 48 | 3mo ago | Apache-2.0 | A | 43 | Claude Code |
| mk:stitchngocsangyem/MeowKit | Skill | 15 | 5d ago | MIT | A | 53 | Claude Code |
| tamagui-v6-configtamagui/tamagui | Skill | 14k | today | MIT | A | 0 | Claude Code, Codex |
| tamagui-theme-generatortamagui/tamagui | Skill | 14k | today | MIT | A | 48 | Claude Code, Codex |
| kiranism-shadcn-dashboardKiranism/next-shadcn-dashboard-starter | Skill | 7.2k | 3d ago | MIT | A | 142 | Claude Code, Codex |
| top-designwondelai/skills | Skill | 2.6k | 4d ago | MIT | A | 113 | Claude Code, Codex |
| web-typographywondelai/skills | Skill | 2.6k | 4d ago | MIT | A | 128 | Claude Code, Codex |