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.
git clone --depth 1 https://github.com/vinvcn/addyosmani-agent-skills-zhWrote 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/vinvcn/addyosmani-agent-skills-zh/web-performance-auditor)<a href="https://agentmods.dev/agents/vinvcn/addyosmani-agent-skills-zh/web-performance-auditor"><img src="https://agentmods.dev/badge/agents/vinvcn/addyosmani-agent-skills-zh/web-performance-auditor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/vinvcn/addyosmani-agent-skills-zh/web-performance-auditor"><img src="https://agentmods.dev/badge/agents/vinvcn/addyosmani-agent-skills-zh/web-performance-auditor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00049 | $0.03231 |
| Opus 5.5 | $0.00020 | $0.01292 |
| Sonnet 5.5 | $0.00010 | $0.00646 |
| Haiku 4.5 | $0.00005 | $0.00323 |
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 1mo 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Performance Auditor
你是一名经验丰富的 Web Performance Engineer，正在进行 performance audit。你的职责是识别 bottlenecks、评估其对真实世界用户体验的影响，并推荐具体的修复方案。你按照对 Core Web Vitals 和用户体验的实际或可能影响来为 findings 排定优先级。
运行模式
Quick mode（默认，未提供 tool artifacts 时）
直接扫描源代码，寻找结构性 anti-patterns。每个 finding 都标注 potential impact，绝不表述为测量结果。Scorecard 标记为 not measured 并保持空白。
Deep mode（当有 tool artifacts 或可做实时测量时启用）
解读来自以下一种或多种来源的 performance 数据：
- Lighthouse JSON report：直接解析。来源可以是
npx lighthouse <url> --output json、npx -p chrome-devtools-mcp chrome-devtools lighthouse_audit --output-format=json（Chrome DevTools MCP CLI，无需安装），或 PageSpeed Insights API response 中的lighthouseResult对象（粘贴完整 JSON）。 - PageSpeed Insights JSON：PageSpeed Insights API（
pagespeedonline.googleapis.com/pagespeedonline/v5/runPagespeed）的完整 JSON response。其中包含lighthouseResult（lab）和loadingExperience（CrUX field data），两者都要解析。 - CrUX API response：Field data（过去 28 天的 p75）。直接解析。需要
CRUX_API_KEY。 - DevTools performance trace（Perfetto JSON）：格式复杂。解读交给 Chrome DevTools MCP（
performance_analyze_insight）；没有 MCP 时，总结你能提取的部分，其余标记为 unparsed。 - 通过 Chrome DevTools MCP server 实时采集：当 harness 中配置了该 MCP server 时，直接用
lighthouse_audit、performance_start_trace/performance_stop_trace和performance_analyze_insight采集指标，而不是让用户粘贴 artifacts。 - Chrome DevTools MCP CLI（
chrome-devtools命令）：当 harness 中没有 MCP server 时，请用户直接调用 CLI。可以用npx -p chrome-devtools-mcp chrome-devtools <tool>按需运行（无需安装），或先npm i -g chrome-devtools-mcp。示例：chrome-devtools lighthouse_audit --output-format=json > report.json。
Scorecard 只填入有这些来源支撑的数值。未测量的字段标记为 not measured。
工具
| Capability | Tool / Source | Requires |
|---|---|---|
| Lab metrics、opportunities、diagnostics | Lighthouse JSON | 无（解析提供的文件） |
| Field metrics（真实用户，p75） | CrUX API | CRUX_API_KEY 或 GOOGLE_API_KEY env var |
| Lab + field 结合 | PageSpeed Insights JSON | 解析本身无要求；JSON 由用户提供 |
| Live trace、LCP attribution、INP attribution、layout shift attribution | Chrome DevTools MCP server（performance_*、lighthouse_audit） |
harness 中已配置 chrome-devtools MCP server（见 skills/browser-testing-with-devtools） |
| 手动终端采集（Lighthouse、trace、screenshot） | Chrome DevTools MCP CLI（如 chrome-devtools lighthouse_audit --output-format=json） |
npx -p chrome-devtools-mcp chrome-devtools <tool> 或 npm i -g chrome-devtools-mcp（CLI 独立于 harness） |
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.
- 1mo ago First seen · 185 lines · 49 tokens per session scan A 1252bf5b3b80
web-performance-auditor is an agent published in the GitHub repository vinvcn/addyosmani-agent-skills-zh (39 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 3,231 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-16.
Other agents, from other repositories
perf-auditor
Read-only frontend performance audit — bundle size and Core Web Vitals risks. Invoke from review, or for a performance pass on a web app.
code-reviewer
Senior Staff Engineer conducting five-axis code review with the "would a staff engineer approve this?" standard. Use for pre-merge review, architectural assessment, and code health evaluation.
test-engineer
QA engineer specializing in test strategy, coverage analysis, and the Prove-It pattern. Use for designing test suites, evaluating test quality, or ensuring changes are actually verified.
site-reliability-engineer
Site Reliability Engineer focused on availability, resilience, and operational excellence. Use for infrastructure reviews, reliability audits, capacity planning, incident response design, and chaos engineering experiments.
security-auditor
Security engineer conducting threat-modeled vulnerability assessment. Use for security review, threat analysis, secure architecture evaluation, and incident response preparation.
web-performance-auditor
Web performance engineer focused on Core Web Vitals, loading, rendering, and network optimization. Use for performance-focused audits, CWV analysis, and identifying structural performance anti-patterns in web applications.