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 commands/huifer/claude-code-seo/geo-content-auditgit 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/commands/huifer/claude-code-seo/geo-content-audit)<a href="https://agentmods.dev/commands/huifer/claude-code-seo/geo-content-audit"><img src="https://agentmods.dev/badge/commands/huifer/claude-code-seo/geo-content-audit.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 | $0.00039 | $0.02893 |
| Opus 5 | $0.00019 | $0.01447 |
| Sonnet 5 | $0.00008 | $0.00579 |
| Haiku 4.5 | $0.00004 | $0.00289 |
Grade A, and why
geo-content-audit scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- URL:使用 Bash (curl/wget) 获取内容 How it starts
The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
功能说明
核心功能
GEO 内容审计分析内容在 AI 搜索引擎中的引用优化潜力,通过 6 维度评分系统识别引用障碍,并提供优先级排序的优化建议。
使用场景
- 评估博客文章的 AI 引用潜力
- 优化产品页面以提升 AI 搜索可见性
- 分析竞争对手内容的 GEO 表现
- 监控内容优化前后的 AI 引用率变化
执行流程
步骤 1: 内容读取
- 输入: 文件路径或 URL
- 处理:
- 本地文件:使用 Read 工具直接读取
- URL:使用 Bash (curl/wget) 获取内容
- 输出: 原始内容字符串
步骤 2: 权威性信号检测
使用 Grep 工具检测:
# 检测 Schema.org JSON-LD
grep -r '@type' --include='*.json' --include='*.ld'
# 检测作者信息
grep -r 'author' --include='*.md' --include='*.tsx' --include='*.jsx'
# 检测引用来源
grep -E '\[.*\]\(http.*\)' content.md
# 检测时间戳
grep -E '(20\d{2}-\d{2}-\d{2}|January|February|March|April|May|June|July|August|September|October|November|December)' content.md
评分逻辑:
- 作者信息完整(+7 分)
- 有引用来源(+7 分)
- 有时间戳(+6 分)
步骤 3: 实体关系分析
使用 Grep + Read 工具:
# 提取标题结构
grep -E '^#+\s' content.md
# 计算段落长度
awk 'NF {print length}' content.md
# 检测内部链接
grep -E '\[.*\]\(\/.*\)' content.md
# 检测外部链接
grep -E '\[.*\]\(http.*\)' content.md
评分逻辑:
- 标题层级清晰(+7 分)
- 段落长度适中(50-150 词)(+7 分)
- 内部链接丰富(+6 分)
步骤 4: 数据质量评估
手动分析:
- 内容准确性(+7 分):无明显错误
- 数据新鲜度(+7 分):6 个月内更新
- 内容完整性(+6 分):覆盖全面
步骤 5: 生成优化建议
基于评分结果,生成:
- 🔴 高优先级建议(影响 +10 分以上)
- 🟡 中优先级建议(影响 +5-10 分)
- 🟢 低优先级建议(影响 +1-5 分)
步骤 6: 生成报告
- 保存到:
.claude-flow/cache/reports/geo/audit-时间戳.json - 输出:Markdown 格式报告
输出示例
Markdown 输出(默认)
# 🤖 AI 引用优化分析
## 内容分析:blog/post.md
**分析时间:** 2024-01-15 14:30
**目标引擎:** ChatGPT, Claude, Perplexity, Google SGE
---
## 📊 总体评分:58/100 ⚠️
| 维度 | 得分 | 满分 | 状态 |
|------|------|------|------|
| 权威性 | 42/100 | 20 | 🔴 |
| 实体关系 | 68/100 | 20 | 🟡 |
| 内容结构 | 55/100 | 20 | 🟡 |
| 数据质量 | 75/100 | 20 | ✅ |
| 引用密度 | 60/100 | 10 | 🟡 |
| 技术优化 | 50/100 | 10 | 🔴 |
**目标评分:** 70+/100
**当前差距:** -12 分
---
## 🔴 高优先级问题(影响 +10 分以上)
### 1. 缺少作者权威性标识 (-15 分)
**问题:**
- ❌ 无作者 Schema.org 标记
- ❌ 缺少作者资质说明
- ❌ 无专业背景信息
**修复方案:**
```html
<script type="application/ld+json">
{
"@context": "https://schema.org",
"@type": "Article",
"author": {
"@type": "Person",
"name": "张三",
"jobTitle": "高级 SEO 专家",
"worksFor": {
"@type": "Organization",
"name": "Your Company"
},
"credential": "Google 认证 SEO 专家,10 年行业经验",
"sameAs": [
"https://linkedin.com/in/zhangsan",
"https://twitter.com/zhangsan"
]
},
"datePublished": "2024-01-15",
"dateModified": "2024-01-15"
}
</script>
预期提升: +15 分
2. 实体关系不明确 (-12 分)
问题:
- ❌ 核心概念缺少明确定义
- ❌ 实体间关系不清晰
- ❌ 缺少知识图谱结构
修复方案:
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 · 364 lines · 39 tokens per session scan A dc2b03e86c0d
geo-content-audit is a command published in the GitHub repository huifer/claude-code-seo (110 stars, last pushed 8mo ago), licensed MIT. It adds 39 tokens to every session and 2,893 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.