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-fix-focus)<a href="https://agentmods.dev/commands/sigistry/marketplace/a11y-fix-focus"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/a11y-fix-focus/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-fix-focus"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/a11y-fix-focus.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 | $0.00016 | $0.00854 |
| Opus 5 | $0.00008 | $0.00427 |
| Sonnet 5 | $0.00003 | $0.00171 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
a11y-fix-focus 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix the keyboard-operability and focus-management defects in the component at $ARGUMENTS (or the components in the current diff), and produce reviewable before/after diffs annotated with the WCAG success criterion each change satisfies. Focus management is exactly the class of problem automated scanners miss, it is about behavior over time (what happens when a dialog opens, where focus goes when it closes), not a single element's attributes. This command dispatches the a11y-remediator agent and loads the wcag-remediation skill's focus-management recipes.
Process
Step 1: Detect the widget type and framework
Read the target. Identify what interaction pattern the component implements, modal dialog, dropdown menu, combobox/autocomplete, tabs, disclosure/accordion, listbox, or a custom composite, and the framework (React, Vue, Svelte, Angular, plain HTML). The correct focus behavior is defined by the ARIA Authoring Practices pattern for that widget; look it up in the skill's references/aria-patterns.md.
Step 2: Diagnose the focus defects
Check each behavior and cite file:line:
| Defect | Symptom in code | WCAG SC |
|---|---|---|
| No focus trap | A modal renders without confining Tab/Shift+Tab to its contents | 2.1.2, 2.4.3 |
| Focus not moved in | Dialog opens but focus stays on the page behind it | 2.4.3 |
| Focus not restored | Dialog closes without returning focus to the trigger | 2.4.3 |
| Background not inert | Content behind the modal is still tabbable / read by AT | 1.3.1, 4.1.2 |
| No visible focus | outline: none with no :focus-visible replacement |
2.4.7 |
| Missing skip link | No "skip to content" before a long repeated nav | 2.4.1 |
| Wrong tabindex | Positive tabindex, or every composite child in the tab order |
2.4.3 |
| No roving tabindex | Menu/tablist/listbox where arrow keys don't move focus | 2.1.1 |
Step 3: Apply the fixes via the a11y-remediator agent
Launch the a11y-remediator agent to edit the component. It applies the framework-idiomatic recipe for each defect: a focus trap that cycles at both ends, useEffect/onMount/ngAfterViewInit to move focus in on open and restore it on close, inert/aria-hidden on the background, a :focus-visible style, a skip link, and roving tabindex (or aria-activedescendant) with the arrow-key handler the pattern requires.
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 · 42 lines · 16 tokens per session scan A ae10b56fdd00
a11y-fix-focus is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 854 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
sculpt-ui
Guide AI-led creation of distinctive, production-grade frontend interfaces.
qfrontdev
Autonomous frontend implementation session with designer-level quality standards.
design-audit
Audit an existing HTML/CSS design. Deterministic checks only (contrast, fonts, colors, states, dark mode) plus a visual pass. No generation.
form-designer
Use when a form is losing people. Too many fields, validation that interrupts typing, unclear required fields, a multi-step flow with no sense of progress, or inputs with no labels.
healthcare-ux-specialist
Use when designing clinical or patient-facing interfaces. Clinical workflows, displaying sensitive patient data, HIPAA considerations in the UI, and medical terminology patients do not speak.
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.