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/commands/vinvcn/addyosmani-agent-skills-zh/webperf)<a href="https://agentmods.dev/commands/vinvcn/addyosmani-agent-skills-zh/webperf"><img src="https://agentmods.dev/badge/commands/vinvcn/addyosmani-agent-skills-zh/webperf/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/commands/vinvcn/addyosmani-agent-skills-zh/webperf"><img src="https://agentmods.dev/badge/commands/vinvcn/addyosmani-agent-skills-zh/webperf.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 | $0.00014 | $0.00520 |
| Opus 5.5 | $0.00006 | $0.00208 |
| Sonnet 5.5 | $0.00003 | $0.00104 |
| Haiku 4.5 | $0.00001 | $0.00052 |
Grade A, and why
webperf 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.
What it actually says
/webperf 专门面向 web 应用。不要把它用于 utility libraries、CLIs，或没有浏览器端产物的 server-only 代码。
确定模式
Deep 模式 — 以下任意一项可用时激活：
- 一份 Lighthouse JSON 报告文件（例如
npx lighthouse <url> --output json --output-path ./report.json，或来自 Chrome DevTools MCP CLI 的npx -p chrome-devtools-mcp chrome-devtools lighthouse_audit --output-format=json） - 一份 PageSpeed Insights JSON 响应（包含 Lighthouse + CrUX）
- 一份 CrUX API 响应（需要
CRUX_API_KEY或GOOGLE_API_KEY） - 一份 DevTools performance trace
- 一个 live URL，外加 harness 中已配置的
chrome-devtoolsMCP server（agent 可以直接通过lighthouse_audit和performance_*tools 采集指标） - 在本地调用的 Chrome DevTools MCP CLI（通过
npx -p chrome-devtools-mcp chrome-devtools <tool>，或在npm i -g chrome-devtools-mcp之后）— 用户运行类似chrome-devtools lighthouse_audit --output-format=json的命令，并把 JSON 输出交给 agent
Quick 模式 — 以上都不可用时的默认模式。Agent 在源代码中扫描结构性反模式，并把每个发现标注为 potential impact。
运行审计
启动 web-performance-auditor subagent。显式传给它：
- 待 review 的文件、组件或 diff
- 任何产物路径（Lighthouse JSON、PSI JSON、CrUX 响应、trace）或粘贴的 JSON 内容
- 已知时的目标 URL 或页面名
- 一条关于你预期使用哪种模式（Quick 或 Deep）的说明，这样若本意是 Deep，agent 会把缺失的输入暴露出来
该 subagent 返回一份 scorecard（只填入有来源的数值）、一份排好序的 findings 列表、正面观察，以及主动给出的建议。
输出
把完整的审计报告返回给用户。不需要综合或合并步骤 — 这是单 persona 命令。
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 · 33 lines · 14 tokens per session scan A fd63ec6045b0
webperf is a command published in the GitHub repository vinvcn/addyosmani-agent-skills-zh (40 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 520 once invoked, about $0.0001 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 commands, from other repositories
ship
Run the pre-launch checklist via parallel fan-out to specialist personas, then synthesize a go/no-go decision.
plan
Break work into small verifiable tasks with acceptance criteria and dependency ordering.
build
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.
webperf
Run a web performance audit via the web-performance-auditor persona.
code-simplify
Simplify code for clarity and maintainability — reduce complexity without changing behavior.
review
Conduct a five-axis code review — correctness, readability, architecture, security, performance.