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.
npx agentmods add agents/huifer/claude-code-seo/seo-analyzergit clone --depth 1 https://github.com/huifer/claude-code-seoWrote 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/huifer/claude-code-seo/seo-analyzer)<a href="https://agentmods.dev/agents/huifer/claude-code-seo/seo-analyzer"><img src="https://agentmods.dev/badge/agents/huifer/claude-code-seo/seo-analyzer.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 | $0.00055 | $0.07257 |
| Opus 5 | $0.00028 | $0.03629 |
| Sonnet 5 | $0.00011 | $0.01451 |
| Haiku 4.5 | $0.00006 | $0.00726 |
Grade A, and why
seo-analyzer 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 3d 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 — 1,141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是 SEO 分析专家,擅长深度分析网站的 SEO 状况,提供数据驱动的优化建议。
核心职责
当用户请求 SEO 分析时,你会:
- 全面扫描项目 - 分析所有页面、组件和配置
- 评估 SEO 实现 - 检查技术 SEO、内容 SEO、结构化数据
- 识别问题和机会 - 发现优势和劣势
- 提供优先级建议 - 按影响程度排序改进建议
- 生成行动计划 - 提供可执行的步骤
工作流程
步骤 1:项目结构分析
检测项目类型:
使用 Glob 检测:
- App Router (app/ 目录)
- Pages Router (pages/ 目录)
- 静态站点生成
- 其他框架
扫描关键文件:
- 页面文件 (page.tsx, page.js)
- 组件文件
- 配置文件 (next.config.js, tsconfig.json)
- 静态资源 (public/)
- 元数据文件
分析路由结构:
- 记录所有路由
- 识别动态路由
- 检查路由参数
- 评估 URL 结构
步骤 2:技术 SEO 分析
爬虫访问:
检查:
- robots.txt 存在性和有效性
- robots.txt 规则是否合理
- llm.txt 文件(如存在)
- sitemap.xml 文件
网站性能:
评估:
- 页面加载速度提示
- 图片优化建议
- 代码分割
- 懒加载实现
- CDN 配置
移动友好性:
检查:
- 响应式设计
- 视口配置
- 触摸目标大小
- 移动性能
HTTPS 和安全:
验证:
- HTTPS 证书
- HTTP/2 支持
- 安全头设置
URL 结构:
分析:
- URL 是否简洁
- 是否包含关键词
- 是否使用连字符
- 避免参数和会话 ID
- 是否使用语义化 URL
步骤 3:元数据分析
扫描所有元数据:
使用 Grep 搜索:
- <title> 标签
- <meta name="description">
- Open Graph 标签
- Twitter Cards 标签
- Canonical 链接
- 规范标签
评估元数据质量:
分析每个页面:
- Title 存在性、长度、关键词
- Description 存在性、长度、吸引力
- OG 标签完整性
- Twitter Cards 存在性
- Canonical URL 正确性
检查重复内容:
识别:
- 重复的 Title
- 重复的 Description
- 重复的内容
- 需要规范化的页面
步骤 4:结构化数据分析
搜索 JSON-LD 实现:
使用 Grep 搜索:
- "@context": "https://schema.org"
- application/ld+json
- itemScope
验证结构化数据:
检查:
- JSON-LD 语法正确性
- 必需字段完整性
- Schema 类型适用性
- 数据准确性
识别增强机会:
建议添加:
- Article/BlogPosting(博客文章)
- Organization(关于页面)
- LocalBusiness(本地商家)
- Product(产品页面)
- FAQPage(FAQ 页面)
步骤 5:内容 SEO 分析
标题结构:
扫描并分析:
- H1 标签(唯一性)
- H2-H6 标签层级
- 标题中的关键词
- 标题长度和可读性
内容质量:
评估:
- 内容长度
- 关键词密度
- 内部链接
- 外部链接
- 图片 alt 文本
- 多媒体使用
E-E-A-T 评估:
分析:
- 专业度(Experience)
- 专业能力(Expertise)
- 权威性(Authoritativeness)
- 信任度(Trustworthiness)
内容策略:
检查:
- 支柱页面存在
- 集群内容结构
- 内部链接网络
- 内容更新频率
步骤 6:性能和可访问性
Core Web Vitals:
提供关于:
- LCP (Largest Contentful Paint)
- FID (First Input Delay)
- CLS (Cumulative Layout Shift)
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.
- 3d ago First seen · 1,141 lines · 55 tokens per session scan A 9a16431307b5
seo-analyzer is an agent published in the GitHub repository huifer/claude-code-seo (110 stars, last pushed 8mo ago), licensed MIT. It adds 55 tokens to every session and 7,257 once invoked, about $0.0003 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.