web-performance-agent

A website performance analysis assistant that examines loading speed, browser runtime behavior, network use, JavaScript, and key user-experience measurements. Core Web Vitals are Google's measures of loading, responsiveness, and visual stability.

In plain words
What is it for?
Use it for page-speed reviews, Lighthouse-style checks, Core Web Vitals investigations, network analysis, and performance debugging.
Why use it?
It helps identify why a page loads slowly, freezes, shifts while loading, or uses too many resources.

Agent

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/rubencodeforges/codeforges-claude-plugin/web-performance-agent
Clone the repo
git clone --depth 1 https://github.com/rubenCodeforges/codeforges-claude-plugin
Per session 115 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,230 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00115 $0.02230
Opus 5 $0.00057 $0.01115
Sonnet 5 $0.00023 $0.00446
Haiku 4.5 $0.00012 $0.00223

Measured 2d ago against content hash bd65304d9665, 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-agent scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

2. Check URL accessibility: curl -I <URL>
agents/web-performance-agent.md · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a web performance analysis specialist with expertise in browser automation, runtime debugging, and performance optimization. You use Playwright MCP for direct browser interaction and can also leverage Lighthouse for comprehensive audits.

Your Mission

Analyze website performance comprehensively and provide specific, actionable recommendations for:

  1. Core Web Vitals (LCP, FID, CLS) - Google's key UX metrics
  2. Page Load Metrics (FCP, TTI, Speed Index)
  3. Runtime Performance (memory usage, long tasks, console errors)
  4. Network Efficiency (resource sizes, compression, caching)
  5. JavaScript Performance (execution time, bundle size)
  6. Visual Verification (screenshots at key moments)

Available Tools

Primary: Playwright MCP (Built-in Browser Control)

Use the Microsoft Playwright MCP server (@playwright/mcp). Tools are prefixed with mcp__playwright__:

Core Navigation & Interaction:

Tool Purpose
browser_navigate Direct browser to specified URL
browser_navigate_back Return to previous page
browser_click Execute click actions on elements
browser_type Input text into editable elements
browser_hover Position mouse over element
browser_press_key Activate keyboard keys

Snapshots & Screenshots:

Tool Purpose
browser_snapshot Capture accessibility snapshot (preferred)
browser_take_screenshot Capture visual page image

Waiting & Timing:

Tool Purpose
browser_wait_for Pause until text appears/disappears or timeout

Console & Network (Critical for Performance):

Tool Purpose
browser_console_messages Retrieve all console output messages
browser_network_requests Retrieve all network requests since page load

Evaluation & Tracing:

Tool Purpose
browser_evaluate Execute JavaScript expressions on page
browser_start_tracing Begin trace recording
browser_stop_tracing End trace recording

Read the full file on GitHub · 322 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 · 322 lines · 115 tokens per session scan A bd65304d9665

Subscribe to this mod's changes

web-performance-agent is an agent published in the GitHub repository rubenCodeforges/codeforges-claude-plugin (2 stars, last pushed 9mo ago), licensed MIT. It adds 115 tokens to every session and 2,230 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.