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/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-citation-monitor)<a href="https://agentmods.dev/commands/huifer/claude-code-seo/geo-citation-monitor"><img src="https://agentmods.dev/badge/commands/huifer/claude-code-seo/geo-citation-monitor/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/huifer/claude-code-seo/geo-citation-monitor"><img src="https://agentmods.dev/badge/commands/huifer/claude-code-seo/geo-citation-monitor.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 | $0.00023 | $0.02309 |
| Opus 5 | $0.00012 | $0.01154 |
| Sonnet 5 | $0.00005 | $0.00462 |
| Haiku 4.5 | $0.00002 | $0.00231 |
Grade A, and why
geo-citation-monitor 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 13d 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 — 252 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
AI 引用监控追踪内容在 ChatGPT、Claude、Perplexity、Google SGE 等搜索引擎中的引用次数、可见性评分和表现趋势，支持竞争对手对比分析。
使用场景
- 监控单个 URL 的 AI 搜索表现
- 对比多个竞争对手的 GEO 表现
- 追踪 AI 引用趋势和增长率
- 识别 AI 搜索优化机会
监控指标
1. 引用次数
- ChatGPT 引用次数
- Claude 引用次数
- Perplexity 引用次数
- Google SGE 引用次数
2. 可见性评分
- 每个引擎的可见性评分（0-100）
- 总体可见性评分（加权平均）
3. 引用趋势
- 日度/周度/月度变化
- 增长/下降百分比
- 移动平均趋势
4. 引用上下文
- 引用时的上下文情感
- 引用位置（开头/中间/结尾）
- 引用完整性
5. 竞争对手对比
- 相对位置
- 差距分析
- 超越机会
输出示例
# 📊 AI 搜索可见性报告
**监控 URL：** https://yoursite.com/seo-guide
**报告周期：** 2024-01-15 至 2024-02-15（30 天）
**生成时间：** 2024-02-15 10:30
---
## 📈 总体表现
### AI 搜索可见性评分：72/100 ⬆️ +12
| AI 引擎 | 可见性 | 引用次数 | 趋势 | 排名 | 状态 |
|---------|--------|----------|------|------|------|
| ChatGPT | 68/100 | 234 | ⬆️ +18% | Top 5 | ✅ |
| Claude | 75/100 | 189 | ⬆️ +22% | Top 3 | ⭐ |
| Perplexity | 70/100 | 156 | ⬆️ +15% | Top 5 | ✅ |
| Google SGE | 55/100 | 98 | ➡️ 稳定 | Top 10 | ⚠️ |
**综合排名：** #1 / 15 竞争对手
---
## 📊 引用趋势分析
### 30 天增长：+45%
**ChatGPT:** +18% ⬆️
**Claude:** +22% ⬆️⬆️ (最快)
**Perplexity:** +15% ⬆️
**Google SGE:** 0% ➡️
### 预测趋势（未来 30 天）
基于当前趋势和季节性因素：
- ChatGPT: 预计 +15-20%
- Claude: 预计 +20-25%
- Perplexity: 预计 +12-18%
- Google SGE: 预计 +5-10%
---
## 🏆 竞争对手对比
### 直接竞争对手
| 网站 | ChatGPT | Claude | Perplexity | Google SGE | 总分 | 排名 |
|------|---------|--------|------------|------------|------|------|
| **你们** | **68** | **75** | **70** | 55 | **268** | **#1** 🥇 |
| Competitor A | 45 | 52 | 48 | 62 | 207 | #2 🥈 |
| Competitor B | 38 | 41 | 35 | 48 | 162 | #3 🥉 |
### 竞争优势分析
#### 你们的优势 ⭐
1. **Claude 表现突出** (+23 分领先)
- 原因：内容结构清晰，实体关系明确
- 建议：保持优势，复制到其他页面
2. **ChatGPT 稳定增长** (+18%)
- 原因：持续的内容更新和引用来源
- 建议：继续保持更新频率
#### 竞争对手的优势
**Competitor A 在 Google SGE 表现更好 (+7 分)**
- 优势：更多结构化数据、更高内容更新频率
- 应对策略：添加 FAQPage Schema，提高更新频率
---
## 🔍 引用上下文分析
### 引用情感分析
| 引擎 | 积极 | 中性 | 消极 | 情感得分 |
|------|------|------|------|----------|
| ChatGPT | 78% | 20% | 2% | 0.76 ⭐⭐⭐⭐ |
| Claude | 82% | 16% | 2% | 0.80 ⭐⭐⭐⭐ |
| Perplexity | 75% | 22% | 3% | 0.72 ⭐⭐⭐ |
| Google SGE | 68% | 28% | 4% | 0.64 ⭐⭐⭐ |
**总体情感：** 积极 (0.73/1.0)
### 引用位置分布
| 位置 | ChatGPT | Claude | Perplexity | Google SGE |
|------|---------|--------|------------|------------|
| 开头 | 35% | 42% | 38% | 28% |
| 中间 | 45% | 40% | 42% | 50% |
| 结尾 | 20% | 18% | 20% | 22% |
### 引用完整性
| 引擎 | 完整引用 | 部分引用 | 歪曲引用 |
|------|----------|----------|----------|
| ChatGPT | 65% | 30% | 5% |
| Claude | 72% | 25% | 3% |
| Perplexity | 68% | 28% | 4% |
| Google SGE | 55% | 40% | 5% |
---
## 🎯 改进建议
### 快速获胜（本周可完成）
#### 1. 优化 Google SGE 表现 (+15 分)
```markdown
**当前：** 55/100
**目标：** 70/100
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.
- 13d ago First seen · 252 lines · 23 tokens per session scan A cfbfe9934a24
geo-citation-monitor is a command published in the GitHub repository huifer/claude-code-seo (110 stars, last pushed 8mo ago), licensed MIT. It adds 23 tokens to every session and 2,309 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 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.