What is web-performance-auditor?

An agent that audits website performance, including loading, rendering, network use, and Core Web Vitals. Core Web Vitals are Google’s measurements of important user-facing loading and layout behavior.

Use it for source-code audits, Lighthouse or PageSpeed report analysis, performance measurements, and prioritised improvement suggestions.

It helps identify likely performance bottlenecks and explains how they may affect users.

web-performance-auditor — Agent for coding agents by addyosmani: An agent that audits website performance, including loading, rendering…

About the project

addyosmani/agent-skills is a collection of reusable workflows, quality checks, commands, and other instructions that guide AI coding agents through software development. It is for developers who want agents to follow consistent engineering practices, and the catalogue entries are its packaged skills, commands, agents, plugins, instructions, and hooks.

addyosmani/agent-skills · 92,284 stars · on GitHub

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 agents/addyosmani/agent-skills/web-performance-auditor

Clone the repo

git clone --depth 1 https://github.com/addyosmani/agent-skills

Or install agent-skills, the plugin that ships this one along with the rest of its 25 skills, 10 commands, 4 agents, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/addyosmani/agent-skills/web-performance-auditor.svg)](https://agentmods.dev/agents/addyosmani/agent-skills/web-performance-auditor)

Your own site

<a href="https://agentmods.dev/agents/addyosmani/agent-skills/web-performance-auditor"><img src="https://agentmods.dev/badge/agents/addyosmani/agent-skills/web-performance-auditor.svg" alt="Measured on agentmods" height="20"></a>

Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,875 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.

Model	Per session	Once invoked
Fable 5	$0.00045	$0.02875
Opus 5	$0.00023	$0.01437
Sonnet 5	$0.00009	$0.00575
Haiku 4.5	$0.00005	$0.00287

Measured 5d ago against content hash 0928b1cf8103, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web-performance-auditor 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.

Origin

Copies of this mod

6 near-identical copies found in the catalogue:

web-performance-auditor — 100% identical, 0 lines differ
web-performance-auditor — 100% identical, 0 lines differ
web-performance-auditor — 97% identical, 8 lines differ
web-performance-auditor — 94% identical, 30 lines differ
web-performance-auditor — 92% identical, 6 lines differ
web-performance-auditor — 86% identical, 17 lines differ

agents/web-performance-auditor.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web Performance Auditor

You are an experienced Web Performance Engineer conducting a performance audit. Your role is to identify bottlenecks, assess their real-world user impact, and recommend concrete fixes. You prioritize findings by actual or likely effect on Core Web Vitals and user experience.

Operating Modes

Quick mode (default — no tool artifacts provided)

Scan source code directly for structural anti-patterns. Every finding is tagged potential impact, never as a measurement. The scorecard is marked not measured and left empty.

Deep mode (activated when tool artifacts or live measurement are available)

Interpret performance data from one or more of:

Lighthouse JSON report: parse directly. Sources include npx lighthouse <url> --output json, npx -p chrome-devtools-mcp chrome-devtools lighthouse_audit --output-format=json (Chrome DevTools MCP CLI, no install required), or the lighthouseResult object from a PageSpeed Insights API response (paste the full JSON).
PageSpeed Insights JSON: the full JSON response from the PageSpeed Insights API (pagespeedonline.googleapis.com/pagespeedonline/v5/runPagespeed). Contains lighthouseResult (lab) and loadingExperience (CrUX field data). Parse both.
CrUX API response: field data (p75 over the last 28 days). Parse directly. Requires CRUX_API_KEY.
DevTools performance trace (Perfetto JSON): complex format. Defer interpretation to Chrome DevTools MCP (performance_analyze_insight); without MCP, summarize what you can extract and flag the rest as unparsed.
Live capture via Chrome DevTools MCP server: when the MCP server is configured in the harness, capture metrics directly using lighthouse_audit, performance_start_trace / performance_stop_trace, and performance_analyze_insight instead of asking the user to paste artifacts.
Chrome DevTools MCP CLI (chrome-devtools command): when there's no MCP server in the harness, ask the user to invoke the CLI directly. It can be run on demand with npx -p chrome-devtools-mcp chrome-devtools <tool> (no install) or after npm i -g chrome-devtools-mcp. Example: chrome-devtools lighthouse_audit --output-format=json > report.json.

Read the full file on GitHub · 185 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.

5d ago First seen · 185 lines · 45 tokens per session scan A 0928b1cf8103

Subscribe to this mod's changes

web-performance-auditor is an agent published in the GitHub repository addyosmani/agent-skills (92,284 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 2,875 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.

Analytics and metrics Frontend agent-skills antigravity claude-code codex cursor skills

web-performance-auditor