performance-audit

performance-audit is a skill for Claude Code from arozumenko/sdlc-skills. It costs 40 tokens per session (643 once invoked), scanned A, original, MIT.

A website check that looks for slow or failed network requests, browser errors, warnings, and common JavaScript problems. It estimates loading health when full Core Web Vitals measurements are unavailable.

In plain words
What is it for?
Use it to review browser network activity and console messages, spot failed requests and oversized resources, and identify JavaScript issues such as async errors, memory leaks, or deprecated APIs.
Why use it?
It helps find technical problems that can make a page slow, unreliable, or difficult to debug without relying on a complete performance score.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the sdlc-skills plugin — 53 skills shipped together

Good fit Use it to review browser network activity and console messages, spot failed requests and oversized resources, and identify JavaScript issues such as async errors, memory leaks, or deprecated APIs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/arozumenko/sdlc-skills/performance-audit
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.

Any agent
npx skills add arozumenko/sdlc-skills --skill performance-audit
Clone the repo
git clone --depth 1 https://github.com/arozumenko/sdlc-skills

Made for: Claude Code.

Or install sdlc-skills, the plugin that ships this one along with the rest of its 53 skills.

Wrote 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.

agentmods badge for performance-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/performance-audit/github.svg)](https://agentmods.dev/skills/arozumenko/sdlc-skills/performance-audit)
Your own site
<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/performance-audit"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/performance-audit/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.

agentmods 80×15 button for performance-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/performance-audit"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/performance-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 643 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00040 $0.00643
Opus 5 $0.00020 $0.00321
Sonnet 5 $0.00008 $0.00129
Haiku 4.5 $0.00004 $0.00064

Measured 9d ago against content hash 01d7de87add6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

performance-audit 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 9d 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.

bundles/manual-qa/skills/performance-audit/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performance, Network & Console Analysis

Three analysis passes:

  • Performance 📡 — load/resource health, network issues
  • Console 🖥️ — runtime errors, warnings, CSP violations
  • JavaScript ⚡ — async issues, memory leaks, deprecated APIs

Data Sources

Performance uses browser_network_requests():

  • Request/response status, resource types and (where reported) sizes
  • 4xx/5xx requests, CORS failures, timeouts

Console uses browser_console_messages(level:"error") (also run with level:"warning" for the Console pass).

Limitation: the factory's Playwright MCP toolset has no browser_evaluate, so there is no reliable way to read performance.getEntriesByType or compute full Core Web Vitals (LCP, CLS, INP, FCP, TTFB) in this environment. Do not report specific CWV numbers or a Lighthouse-style score. Instead, approximate load/resource health from browser_network_requests() (request count, resource sizes where reported, error rate, obviously oversized responses) and from how long the page visibly took to settle during Step-0 collection. Score confidence low-to-medium (per the evidence rule in audit-methodology.md) for any performance finding, and say explicitly that it is an approximation, not a measured CWV metric.

Performance 📡 — Approximate Thresholds

See references/cwv-thresholds.md for the full CWV/budget reference table (use it for resource-size and network-error priority mapping; do not cite the CWV rows as measured values — see Limitation above).

Look for: obviously slow/oversized resources, waterfall bottlenecks visible in the network log, missing caching headers, CORS errors, render-blocking scripts, broken resource URLs.

Console 🖥️ — Focus Areas

Look for: JS errors, deprecated API warnings, CSP violations, failed resource loads, unhandled rejections, compatibility warnings.

Priority: console.error = p1, console.warn = p2, deprecated API = p3.

JavaScript ⚡ — Focus Areas

Look for: uncaught promise rejections, missing error handlers, blocking operations, memory leaks, race conditions, deprecated APIs, failed dynamic imports.

Read the full file on GitHub · 69 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 69 lines · 40 tokens per session scan A 01d7de87add6

Subscribe to this mod's changes

performance-audit is a skill published in the GitHub repository arozumenko/sdlc-skills (20 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 643 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

inspecting-hermes-desktop-dom

Read the live Hermes desktop DOM/CSS over CDP.

NousResearch/hermes-agent · 20 tokens

a11y-debugging

Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.

ChromeDevTools/chrome-devtools-mcp · 50 tokens

devtools

Drop-in inspector panel for any json-render app. Use when the user wants to debug a generative UI, inspect the spec tree, edit state at runtime, see dispatched actions, follow stream patches live, browse a catalog, or pick DOM elements to find their spec keys. Triggers include "add devtools", "debug json-render"…

vercel-labs/json-render · 108 tokens

copilotkit-debug

Use when diagnosing CopilotKit issues -- runtime connectivity failures, agent not responding, streaming errors, tool execution problems, transcription failures, version mismatches, and AG-UI event tracing.

CopilotKit/CopilotKit · 42 tokens

migrate-oxlint

Guide for migrating a project from ESLint to Oxlint. Use when asked to migrate, convert, or switch a JavaScript/TypeScript project's linter from ESLint to Oxlint.

oxc-project/oxc · 44 tokens

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens