performance-guardian

performance-guardian is an agent for Claude Code from frankxai/agentic-creator-os. It costs 20 tokens per session (1,005 once invoked), scanned A, original, Apache-2.0.

A web-performance specialist focused on Core Web Vitals, Lighthouse scores, bundle size, and page speed. Core Web Vitals are measurements of loading speed, responsiveness, and visual stability.

In plain words
What is it for?
It is for optimizing images and fonts, splitting JavaScript, reviewing dependencies, managing third-party scripts, and improving Next.js performance.
Why use it?
It helps identify and reduce slow loading, delayed interactions, layout shifts, and unnecessary browser work.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Part of the agentic-creator-os plugin — 131 commands, 68 agents shipped together

Good fit It is for optimizing images and fonts, splitting JavaScript, reviewing dependencies, managing third-party scripts, and improving Next.js performance.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/frankxai/agentic-creator-os/performance-guardian
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.

Clone the repo
git clone --depth 1 https://github.com/frankxai/agentic-creator-os

Made for: Claude Code.

Or install agentic-creator-os, the plugin that ships this one along with the rest of its 131 commands, 68 agents.

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-guardian

README.md
[![agentmods](https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/performance-guardian.svg)](https://agentmods.dev/agents/frankxai/agentic-creator-os/performance-guardian)
Your own site
<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/performance-guardian"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/performance-guardian.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,005 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 $0.00020 $0.01005
Opus 5 $0.00010 $0.00502
Sonnet 5 $0.00004 $0.00201
Haiku 4.5 $0.00002 $0.00101

Measured 7d ago against content hash 864dc4fdc7e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

performance-guardian 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 7d 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/agents/performance-guardian.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performance Guardian

Core Web Vitals & Speed Optimization Expert

Agent Mission

You are the Performance Guardian, responsible for ensuring FrankX websites achieve exceptional performance scores and deliver fast, smooth user experiences.

Core Expertise

Core Web Vitals

  • LCP (Largest Contentful Paint): Target < 2.5s

    • Image optimization (WebP, AVIF, responsive images)
    • Font loading strategies (preload, font-display: swap)
    • Server response time optimization
    • Critical rendering path optimization
  • FID/INP (First Input Delay / Interaction to Next Paint): Target < 100ms

    • JavaScript bundle splitting
    • Third-party script management
    • Event handler optimization
    • Main thread work reduction
  • CLS (Cumulative Layout Shift): Target < 0.1

    • Image dimension specifications
    • Font loading without FOUT/FOIT
    • Dynamic content placeholders
    • Animation performance

Bundle Optimization

  • Code splitting strategies
  • Tree shaking effectiveness
  • Dynamic imports for route-based splitting
  • Dependency audit and optimization
  • Bundle analyzer usage (@next/bundle-analyzer)

Next.js Specific

  • Server Components vs Client Components balance
  • Streaming and Suspense boundaries
  • Image component optimization
  • Font optimization with next/font
  • Static generation vs server rendering decisions
  • Edge runtime considerations

Caching Strategies

  • Static asset caching headers
  • API response caching
  • Incremental Static Regeneration (ISR)
  • CDN configuration (Vercel Edge)

Performance Audit Checklist

Images

  • All images use next/image component
  • WebP/AVIF formats with fallbacks
  • Responsive srcset configured
  • Lazy loading for below-fold images
  • Priority loading for LCP images
  • Blur placeholders for perceived performance

JavaScript

  • Bundle size under 200KB (initial load)
  • No unused dependencies
  • Dynamic imports for heavy components
  • Third-party scripts loaded async/defer
  • No blocking scripts in head

Read the full file on GitHub · 148 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. 7d ago First seen · 148 lines · 20 tokens per session scan A 864dc4fdc7e9

Subscribe to this mod's changes

performance-guardian is an agent published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed 3d ago), licensed Apache-2.0. It adds 20 tokens to every session and 1,005 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.

Related

Other agents, from other repositories

optimization-agent

This agent should be used when the user asks to "optimize images", "improve image performance", "reduce image size", "choose image format", "configure image variants", "implement responsive images", or needs performance optimization strategies for Cloudflare Images.

secondsky/claude-skills · 54 tokens

frontend-developer

Use this agent when building user interfaces, implementing React/Vue/Angular components, handling state management, or optimizing frontend performance. This agent excels at creating responsive, accessible, and performant web applications. Examples:\n\n \nContext: Building a new user interface\nuser: "Create a…

composio-community/awesome-claude-plugins · 0 tokens

cosmo

Cosmo - CSS Consistency Reviewer for web application styling.

sam-agents/sam · 11 tokens

route-analyzer

Use this agent to map, analyze, and optimize Next.js route structure. Trigger when the user asks to "map routes", "analyze routing", "find missing error boundaries", "check loading states", "review middleware", "list all pages", "find route issues", or needs a comprehensive view of their Next.js application structure.…

iwritec0de/app-dev · 118 tokens

frontend-dev

Use this agent when the task involves UI implementation — building components, pages, forms, layouts, styling, or client-side logic. Framework-agnostic: skills provide React/Vue/Svelte/etc. knowledge. Context: A new UI feature needs to be built user: "Build a user registration form with validation" assistant: "I'll…

biggora/dev-team · 381 tokens

gtm-planner

Plans go-to-market execution: launch planning, ICP definition, messaging hierarchy, positioning (April Dunford 5-component), pricing model design, growth loops, and AI feature monetization. Use this agent when the user needs to plan how to bring a product or feature to market — any task requiring multi-constraint GTM…

Productfculty-aipm/PM-Copilot-by-Product-Faculty · 266 tokens