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/sigistry/marketplaceWrote 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/commands/sigistry/marketplace/a11y-audit)<a href="https://agentmods.dev/commands/sigistry/marketplace/a11y-audit"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/a11y-audit/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/commands/sigistry/marketplace/a11y-audit"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/a11y-audit.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 | $0.00021 | $0.01099 |
| Opus 5 | $0.00010 | $0.00549 |
| Sonnet 5 | $0.00004 | $0.00220 |
| Haiku 4.5 | $0.00002 | $0.00110 |
Grade A, and why
a11y-audit 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 10d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit the UI in $ARGUMENTS (or the components in the current diff if no path is given) for WCAG 2.2 conformance failures, and report each finding grouped by the success criterion it violates, with a severity and the concrete fix. This is a static audit, it reads source, not a running page, so it catches the structural and cross-element problems that a rendered-DOM scanner cannot. Load the wcag-remediation skill for the ARIA-pattern and focus-management catalogs.
Process
Step 1: Detect the framework and markup dialect
Read the target files. Determine the stack so you apply the right idioms:
| Stack | Signal |
|---|---|
| React / JSX | .jsx/.tsx, className, onClick, import React |
| Vue SFC | .vue, <template>, v-bind, @click |
| Svelte | .svelte, on:click, {#if} |
| Angular | .component.html, *ngIf, (click), [attr.aria-*] |
| Plain HTML | .html, raw <button>/<div> markup |
Note the component library too (MUI, Chakra, Radix, Headless UI, Vuetify, Angular Material), many ship accessible primitives that a hand-rolled <div onClick> is reinventing badly.
Step 2: Run the WCAG 2.2 checklist
For every interactive or content element, check each category and record the exact file:line:
| Category | What to flag | WCAG SC |
|---|---|---|
| Color contrast | Text/token pairs below 4.5:1 (3:1 for large text), UI-component/state contrast below 3:1 | 1.4.3, 1.4.11 |
| Text alternatives | <img> with no alt, icon-only buttons with no accessible name, decorative images missing alt="" |
1.1.1 |
| Labels & names | Inputs with no associated <label>/aria-label/aria-labelledby, placeholder-as-label |
1.3.1, 3.3.2, 4.1.2 |
| ARIA misuse | Invalid role, aria-* on an element that does not support it, redundant role (role="button" on <button>), aria-hidden on a focusable element |
4.1.2 |
| Keyboard operability | onClick on a non-interactive element with no role/tabIndex/key handler, positive tabindex, focus traps, no visible focus |
2.1.1, 2.1.2, 2.4.7 |
| Focus order | DOM order that does not match reading order, focus lost when a dialog closes | 2.4.3 |
| Headings & landmarks | Skipped heading levels, multiple <h1>, missing <main>/<nav> landmarks |
1.3.1, 2.4.6 |
| Name/role/value | Custom widgets missing the required state (aria-expanded, aria-checked, aria-selected) |
4.1.2 |
| Target size (2.2) | Interactive targets under 24×24 CSS px with no spacing exception | 2.5.8 |
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.
- 10d ago First seen · 53 lines · 21 tokens per session scan A 6337eac6fec2
a11y-audit is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 1,099 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
web-design
Design and build a complete website or webapp from a project brief — end-to-end workflow from design to working React/Vite code.
sculpt-ui
Guide AI-led creation of distinctive, production-grade frontend interfaces.
qfrontdev
Autonomous frontend implementation session with designer-level quality standards.
validate
Mechanically validate the sonu plugin repo before a PR — manifest sync, YAML frontmatter, shell-fence syntax, named-source and AI-attribution scans, cross-reference integrity, skill reachability. Only meaningful inside the claude-plugins repo; in any other repo, say so and stop.
esp-teach
One-time project setup -- discover hardware, find datasheets, persist context to CLAUDE.md.
motion-designer
Use when animation feels wrong. Transitions too slow or too bouncy, motion with no purpose, blanket transitions on every property, no reduced-motion support, or animation that drops frames.