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/performance-debuggingnpx skills add HayoDev/safari-devtools-mcp --skill performance-debugginggit clone --depth 1 https://github.com/HayoDev/safari-devtools-mcpWhat 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 | $0.01192 |
| Opus 5 | $0.00000 | $0.00596 |
| Sonnet 5 | $0.00000 | $0.00238 |
| Haiku 4.5 | $0.00000 | $0.00119 |
Grade A, and why
performance-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 2d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Debugging with Safari DevTools MCP
Use this skill when investigating slow page loads, rendering issues, or optimizing Core Web Vitals in Safari.
Collect performance metrics
Use evaluate_script to capture key metrics from the browser:
Navigation Timing (TTFB, DOM load, full page load)
evaluate_script function="() => {
const nav = performance.getEntriesByType('navigation')[0];
if (!nav) return { error: 'No navigation entry found' };
return {
url: nav.name,
redirectTime: Math.round(nav.redirectEnd - nav.redirectStart),
dnsLookup: Math.round(nav.domainLookupEnd - nav.domainLookupStart),
tcpConnect: Math.round(nav.connectEnd - nav.connectStart),
ttfb: Math.round(nav.responseStart - nav.requestStart),
responseTime: Math.round(nav.responseEnd - nav.responseStart),
domInteractive: Math.round(nav.domInteractive),
domContentLoaded: Math.round(nav.domContentLoadedEventEnd),
fullLoad: Math.round(nav.loadEventEnd),
transferSize: nav.transferSize,
encodedBodySize: nav.encodedBodySize,
decodedBodySize: nav.decodedBodySize
};
}"
Core Web Vitals (LCP, CLS)
evaluate_script function="() => {
const results = {};
// LCP
const lcpEntries = performance.getEntriesByType('largest-contentful-paint');
if (lcpEntries.length > 0) {
const lcp = lcpEntries[lcpEntries.length - 1];
results.lcp = {
value: Math.round(lcp.startTime),
element: lcp.element?.tagName,
url: lcp.url || null,
rating: lcp.startTime <= 2500 ? 'good' : lcp.startTime <= 4000 ? 'needs-improvement' : 'poor'
};
}
// CLS
let clsValue = 0;
for (const entry of performance.getEntriesByType('layout-shift')) {
if (!entry.hadRecentInput) clsValue += entry.value;
}
results.cls = {
value: Math.round(clsValue * 1000) / 1000,
rating: clsValue <= 0.1 ? 'good' : clsValue <= 0.25 ? 'needs-improvement' : 'poor'
};
return results;
}"
Resource waterfall (slowest resources)
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.
- 2d ago First seen · 173 lines · 0 tokens per session scan A 3b7624b25343
performance-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 1,192 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…
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.
web-search
Search the public web and fetch page content as clean Markdown. Powered by omni-search-skill (optional companion). Provides search, fetch, resolve, and crawl operations.