performance-debugging

A process for diagnosing slow page loads and rendering problems in Safari, Apple's web browser.

In plain words
What is it for?
Use it to investigate Safari performance, capture Navigation Timing data, and examine Core Web Vitals such as largest contentful paint and layout stability.
Why use it?
It replaces guesswork with browser measurements such as server response time, page-loading stages, and key user-experience metrics.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/hayodev/safari-devtools-mcp/performance-debugging
Any agent
npx skills add HayoDev/safari-devtools-mcp --skill performance-debugging
Clone the repo
git clone --depth 1 https://github.com/HayoDev/safari-devtools-mcp

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,192 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 3b7624b25343, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

skills/performance-debugging/SKILL.md · 173 lines

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)

Read the full file on GitHub · 173 lines

Changes

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.

  1. 2d ago First seen · 173 lines · 0 tokens per session scan A 3b7624b25343

Subscribe to this mod's changes

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.

Related

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…

LambdaTest/kane-cli · 159 tokens

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…

SDLLL/claude-for-safari · 81 tokens

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…

LambdaTest/kane-cli · 159 tokens

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…

dominion525/familiar · 111 tokens

react-sentinel-debug

Use React-Sentinel when a task needs live browser or React runtime inspection rather than static code reading alone.

edgarbnt/ReactSentinel · 26 tokens

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.

d-wwei/browser-control-skill · 36 tokens