workflow-review-performance

workflow-review-performance is a command for Claude Code from rcdelacruz/claude-code-agents. It costs 11 tokens per session (2,713 once invoked), scanned A, original, MIT.

A command for reviewing web performance, focusing on load times and Core Web Vitals, measurements used by browsers to assess loading, responsiveness, and visual stability.

In plain words
What is it for?
Use it to inspect and improve page loading, images, fonts, server rendering, CSS, main-thread work, and above-the-fold content.
Why use it?
It helps identify slow images, blocked rendering, heavy browser work, and layout movement that can make a website feel slow.

Command for Claude Code

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 commands/rcdelacruz/claude-code-agents/workflow-review-performance
Clone the repo
git clone --depth 1 https://github.com/rcdelacruz/claude-code-agents

Made for: Claude Code.

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 workflow-review-performance

README.md
[![agentmods](https://agentmods.dev/badge/commands/rcdelacruz/claude-code-agents/workflow-review-performance.svg)](https://agentmods.dev/commands/rcdelacruz/claude-code-agents/workflow-review-performance)
Your own site
<a href="https://agentmods.dev/commands/rcdelacruz/claude-code-agents/workflow-review-performance"><img src="https://agentmods.dev/badge/commands/rcdelacruz/claude-code-agents/workflow-review-performance.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,713 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 $0.00011 $0.02713
Opus 5 $0.00005 $0.01357
Sonnet 5 $0.00002 $0.00543
Haiku 4.5 $0.00001 $0.00271

Measured 4d ago against content hash 7f92d3c09c2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workflow-review-performance 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 4d 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.

.claude/commands/workflow-review-performance.md · 425 lines

How it starts

The opening of the file, as written. The whole thing — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are in PERFORMANCE REVIEW MODE.

Use performance agent to optimize for Core Web Vitals and fast load times.

Performance Audit Process

1. Core Web Vitals Analysis (20 mins)

Largest Contentful Paint (LCP) - Target: < 2.5s
// ❌ SLOW: Large unoptimized image
<img src="/hero.jpg" width="1200" height="630" />

// ✅ FAST: Optimized with next/image
import Image from 'next/image'

<Image
  src="/hero.jpg"
  alt="Hero"
  width={1200}
  height={630}
  priority // Preload above-the-fold
  quality={85}
  placeholder="blur"
  blurDataURL="data:image/..." // Or import from static
/>

LCP Optimization Checklist:

  • Hero images use next/image with priority
  • Above-the-fold content loads first
  • Server-side rendering for initial paint
  • Fonts optimized with next/font
  • CSS not blocking render
  • No layout shifts during load
First Input Delay (FID/INP) - Target: < 100ms
// ❌ SLOW: Heavy computation on main thread
function ExpensiveComponent() {
  const data = complexCalculation(largeArray) // Blocks rendering!
  return <div>{data}</div>
}

// ✅ FAST: Memoized expensive calculation
function ExpensiveComponent() {
  const data = useMemo(
    () => complexCalculation(largeArray),
    [largeArray]
  )
  return <div>{data}</div>
}

// ✅ BETTER: Web Worker for heavy computation
function ExpensiveComponent() {
  const [data, setData] = useState(null)

  useEffect(() => {
    const worker = new Worker('/workers/calculation.js')
    worker.postMessage(largeArray)
    worker.onmessage = (e) => setData(e.data)
    return () => worker.terminate()
  }, [largeArray])

  return <div>{data}</div>
}

FID/INP Optimization Checklist:

  • No long tasks blocking main thread
  • Heavy computation memoized or in Web Workers
  • Event handlers debounced/throttled
  • Code splitting for large bundles
  • Third-party scripts loaded async
Cumulative Layout Shift (CLS) - Target: < 0.1
// ❌ LAYOUT SHIFT: No dimensions on image
<img src="/banner.jpg" alt="Banner" />

// ✅ NO SHIFT: Dimensions specified
<Image
  src="/banner.jpg"
  alt="Banner"
  width={1200}
  height={300} // Prevents shift
/>

// ❌ LAYOUT SHIFT: Dynamic content without placeholder
{isLoading && <Spinner />}
{data && <Content data={data} />}

// ✅ NO SHIFT: Consistent height
<div className="min-h-[400px]">
  {isLoading && <Spinner />}
  {data && <Content data={data} />}
</div>

Read the full file on GitHub · 425 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. 4d ago First seen · 425 lines · 11 tokens per session scan A 7f92d3c09c2a

Subscribe to this mod's changes

workflow-review-performance is a command published in the GitHub repository rcdelacruz/claude-code-agents (2 stars, last pushed 10mo ago), licensed MIT. It adds 11 tokens to every session and 2,713 once invoked, about $0.0001 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 2026-08-31.