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 skills/hayodev/safari-devtools-mcp/a11y-debuggingnpx skills add HayoDev/safari-devtools-mcp --skill a11y-debugginggit clone --depth 1 https://github.com/HayoDev/safari-devtools-mcpWrote 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/hayodev/safari-devtools-mcp/a11y-debugging)<a href="https://agentmods.dev/skills/hayodev/safari-devtools-mcp/a11y-debugging"><img src="https://agentmods.dev/badge/skills/hayodev/safari-devtools-mcp/a11y-debugging.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 | $0.00000 | $0.00684 |
| Opus 5 | $0.00000 | $0.00342 |
| Sonnet 5 | $0.00000 | $0.00137 |
| Haiku 4.5 | $0.00000 | $0.00068 |
Grade A, and why
a11y-debugging 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 5d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Debugging with Safari DevTools MCP
Use this skill when auditing a page for accessibility issues in Safari.
Quick audit workflow
-
Navigate to the target page:
navigate_page url="https://example.com" -
Take a verbose snapshot to see the full a11y tree:
take_snapshot verbose=true -
Review the snapshot for common issues:
- Elements with
role="generic"that should have semantic roles - Interactive elements (buttons, links) with empty names (
"") - Images without descriptive names (missing alt text)
- Form inputs without associated labels
- Elements with
-
For a more thorough automated audit, inject axe-core:
Note: This fetches a script from a public CDN. Two things to be aware of: (1) a strict Content Security Policy may block it — if the audit returns no results, check the console for CSP errors; (2) on internal or authenticated pages, prefer loading axe-core from a local copy rather than a CDN to avoid sending page context to a third party.
evaluate_script function="async () => { const script = document.createElement('script'); script.src = 'https://cdnjs.cloudflare.com/ajax/libs/axe-core/4.10.0/axe.min.js'; document.head.appendChild(script); await new Promise(r => script.onload = r); const results = await window.axe.run(); return { violations: results.violations.map(v => ({ id: v.id, impact: v.impact, description: v.description, nodes: v.nodes.length })), passes: results.passes.length, incomplete: results.incomplete.length }; }" -
Check specific element styles for contrast issues:
get_computed_style uid="<element-uid>" properties=["color", "background-color", "font-size"]
What to look for in the snapshot
- Headings: Should follow a logical hierarchy (h1 → h2 → h3).
Check that roles include
headingwith proper nesting. - Links: Every
linkrole should have a descriptive name, not just "click here" or the raw URL. - Forms: Every
textbox,combobox,checkboxshould have a name (label). Empty names mean missing labels. - Images:
imgroles should have a meaningful name unless decorative. - Buttons:
buttonroles with empty names are keyboard-inaccessible. - Landmarks: Look for
navigation,main,banner,contentinforoles. Pages without landmarks are harder to navigate with screen readers.
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.
- 5d ago First seen · 79 lines · 0 tokens per session scan A 918cf06afebf
a11y-debugging is a skill published in the GitHub repository HayoDev/safari-devtools-mcp (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 684 tokens. 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 skills, from other repositories
kane-cli
Browser automation + AI test authoring via kane-cli - run browser objectives, generate & refine test scenarios/cases from a description, design requirement-linked test suites from a PRD/spec (assurance), parse NDJSON output, inspect logs, save runnable test.md. Use for any task requiring a real browser (navigate…
claude-for-safari
Control the user's real Safari browser on macOS through AppleScript, page JavaScript, screenshots, and carefully verified System Events input. Use when an agent needs to inspect or operate the user's existing Safari tabs and login sessions, including reading pages, navigating, clicking, filling non-sensitive forms…
kane-cli
Browser automation + AI test authoring via kane-cli - run browser objectives, generate & refine test scenarios/cases from a description, design requirement-linked test suites from a PRD/spec (assurance), parse NDJSON output, inspect logs, save runnable test.md. Use for any task requiring a real browser (navigate…
naive-user
Drive the live app as an uninformed first-time user. Hover, click, and type in a real browser, observe what actually happens, and report the gaps (bugs, broken expectations, UX surprises, accessibility issues) before deploy. Source-blind: forms expectations from the screen plus web conventions, never from source.…
familiar
Use when you specifically need to drive the user's own everyday Google Chrome on macOS via AppleScript (Apple Events) — not a fresh headless/automated browser, and not the DevTools Protocol or Playwright. Especially for pages behind bot/WAF defenses that block automated browsers, since this is the real signed-in…
react-sentinel-debug
Use React-Sentinel when a task needs live browser or React runtime inspection rather than static code reading alone.