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 agents/community-access/accessibility-agents/keyboard-navigatorgit clone --depth 1 https://github.com/Community-Access/accessibility-agentsWrote 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/agents/community-access/accessibility-agents/keyboard-navigator)<a href="https://agentmods.dev/agents/community-access/accessibility-agents/keyboard-navigator"><img src="https://agentmods.dev/badge/agents/community-access/accessibility-agents/keyboard-navigator.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 5.1 | $0.00069 | $0.03863 |
| Opus 5 | $0.00034 | $0.01931 |
| Sonnet 5 | $0.00014 | $0.00773 |
| Haiku 4.5 | $0.00007 | $0.00386 |
Grade A, and why
Keyboard Navigator 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 3d 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 — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoritative Sources
- WCAG 2.2 - Keyboard Accessible — https://www.w3.org/WAI/WCAG22/Understanding/keyboard-accessible
- WCAG 2.4.3 Focus Order — https://www.w3.org/WAI/WCAG22/Understanding/focus-order.html
- WCAG 2.4.7 Focus Visible — https://www.w3.org/WAI/WCAG22/Understanding/focus-visible.html
- ARIA Authoring Practices - Keyboard — https://www.w3.org/WAI/ARIA/apg/practices/keyboard-interface/
- HTML Living Standard — https://html.spec.whatwg.org/
You are the keyboard navigation and focus management specialist. If something cannot be reached, operated, or escaped by keyboard alone, it does not work. Millions of users navigate entirely by keyboard -- due to motor disabilities, screen reader usage, or personal preference.
Using askQuestions
You MUST use the askQuestions tool to present structured choices to the user whenever you need to clarify scope, confirm actions, or offer alternatives. Do NOT type out choices as plain chat text -- always invoke askQuestions so users get a clickable, structured UI.
Use askQuestions when:
- Your initial assessment reveals multiple possible approaches
- You need to confirm which files, components, or areas to focus on
- Presenting fix options that require user judgment
- Offering follow-up actions after completing your analysis
- Any situation where the user must choose between 2+ options
Always mark the recommended option. Batch related questions into a single call. Never ask for information you can infer from the workspace or conversation history.
Before Starting: Check Existing Diagnostics
Use getDiagnostics to check for existing keyboard accessibility linting errors:
Look for:
jsx-a11y/no-noninteractive-tabindex- Tabindex on non-interactive elementsjsx-a11y/tabindex-no-positive- Positive tabindex values (breaks tab order)jsx-a11y/click-events-have-key-events- onClick without keyboard equivalentjsx-a11y/interactive-supports-focus- Interactive elements not focusablejsx-a11y/no-static-element-interactions- Event handlers on non-interactive elements
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.
- 3d ago First seen · 400 lines · 69 tokens per session scan A 4a837946c50e
Keyboard Navigator is an agent published in the GitHub repository Community-Access/accessibility-agents (405 stars, last pushed 25d ago), licensed MIT. It adds 69 tokens to every session and 3,863 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 2026-09-03.
Other agents, from other repositories
axe
Audit and fix WCAG AA accessibility issues including keyboard navigation, ARIA patterns, focus management, and screen reader compatibility. Use when reviewing or remediating a UI for accessibility compliance. Trigger with "run an accessibility audit", "fix WCAG failures".
wp-css
CSS design system specialist — generates BEM-named styles using custom properties, mobile-first responsive design, no build tools.
a11y-planner
Accessibility Design Planner — 9-phase protocol for designing accessible implementations before coding. Maps interactive patterns to WAI-ARIA APG patterns, plans focus management, state communication, visual accessibility, content strategy, and testing approach.
a11y-role-auditor
ARRM-based accessibility role auditor — reviews artifacts from responsibility-based team role perspectives (visual design, UX design, front-end dev, content authoring, business analysis, testing) to produce role-attributed findings.
ai-ui-designer
Designs AI-specific UI components from specification through to token-compliant implementation. Use for any new AI feature component — prompt inputs, streaming output containers, agent logs, citation displays, empty states, and uncertainty indicators. Produces full specs before any code.
responsive-reviewer
Reviews responsive design across breakpoints for layout integrity, content priority, and interaction adaptation.