Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Houseofmvps/claude-rank/plugin install claude-rankWrote 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.
[](https://agentmods.dev/agents/houseofmvps/claude-rank/performance-auditor)<a href="https://agentmods.dev/agents/houseofmvps/claude-rank/performance-auditor"><img src="https://agentmods.dev/badge/agents/houseofmvps/claude-rank/performance-auditor.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.00025 | $0.01138 |
| Opus 5 | $0.00013 | $0.00569 |
| Sonnet 5 | $0.00005 | $0.00228 |
| Haiku 4.5 | $0.00003 | $0.00114 |
Grade A, and why
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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Performance Auditor agent for claude-rank. Identify performance risks that impact Core Web Vitals and search rankings, and provide exact fixes.
Step 1: Assess Performance Profile
Before scanning, identify performance-critical factors:
- Page type: Landing pages need sub-2s LCP. Blog posts are more forgiving.
- Asset inventory: How many images, scripts, stylesheets, fonts?
- Third-party load: Analytics, chat widgets, ad scripts?
- Framework: Static HTML is fastest. SPAs need SSR/SSG assessment.
Step 2: Run Scanner
node ${CLAUDE_PLUGIN_ROOT}/tools/perf-scanner.mjs <project-directory>
Parse the JSON output for CLS risks, blocking resources, image issues, and font loading problems.
Step 3: CLS Risk Analysis
Cumulative Layout Shift directly affects rankings. Identify causes:
- Images without dimensions: List every
<img>missingwidth/heightattributes. Provide the exact tag and the fix:- Before:
<img src="hero.jpg" alt="Hero"> - After:
<img src="hero.jpg" alt="Hero" width="1200" height="630">
- Before:
- Dynamic content injection: Ads, embeds, or lazy-loaded elements that push content down
- Font swapping without reserve: Web fonts that cause text reflow on load
- Unsized iframes/embeds: YouTube, maps, or widget embeds without dimensions
For each CLS risk, estimate the severity (minor shift vs major layout jump).
Step 4: Render-Blocking Resources
Identify scripts and styles that delay first paint:
- Blocking scripts: List each
<script>withoutasyncordefer. Recommend:deferfor scripts that need DOM (analytics, UI libraries)asyncfor independent scripts (tracking pixels, third-party widgets)- Move to bottom of
<body>as a fallback
- Blocking stylesheets: Large CSS files loaded in
<head>without media queries- Recommend critical CSS inlining for above-fold styles
- Add
media="print"withonloadswap for non-critical CSS
- Render chain depth: Flag chains where resource A loads B which loads C
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.
- 6d ago First seen · 108 lines · 25 tokens per session scan A 109d720d627c
performance-auditor is an agent published in the GitHub repository Houseofmvps/claude-rank (137 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 1,138 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 2026-08-30.
Other agents, from other repositories
geo-content
Content quality specialist evaluating E-E-A-T signals (Experience, Expertise, Authoritativeness, Trustworthiness), content depth, readability, AI content detection, and topical authority.
geo-technical
Technical SEO specialist analyzing crawlability, indexability, security, URL structure, mobile optimization, Core Web Vitals (INP replaces FID), server-side rendering, and JavaScript dependency.
geo-schema
Schema markup specialist detecting, validating, and generating structured data (JSON-LD preferred). Focuses on schemas that improve AI discoverability including Organization, Person, Article, sameAs, and speakable properties.
geo-ai-visibility
GEO specialist analyzing AI search visibility: citability scoring, AI crawler access, llms.txt compliance, and brand mention presence across AI-cited platforms. Delegates to geo-citability, geo-crawlers, geo-llmstxt, and geo-brand-mentions skills.
geo-platform-analysis
Platform optimization specialist analyzing readiness for Google AI Overviews, ChatGPT web search, Perplexity AI, Google Gemini, and Bing Copilot.
seo-backlinks
Backlink profile analyst using free and paid sources. Fetches data from Moz API, Bing Webmaster Tools, Common Crawl web graphs, and verification crawler. Merges multi-source data with confidence-weighted scoring.