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/ai-content-generatorgit 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/ai-content-generator)<a href="https://agentmods.dev/commands/huifer/claude-code-seo/ai-content-generator"><img src="https://agentmods.dev/badge/commands/huifer/claude-code-seo/ai-content-generator.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 | $0.00022 | $0.04725 |
| Opus 5 | $0.00011 | $0.02363 |
| Sonnet 5 | $0.00004 | $0.00945 |
| Haiku 4.5 | $0.00002 | $0.00473 |
Grade A, and why
ai-content-generator 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 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.
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 — 775 lines — stays where its author put it; the contents beside it link to each section on GitHub.
完整实现
命令执行流程
# AI 内容生成执行流程
## 步骤 1: 参数解析和需求分析
输入：topic, type, length, tone, optimize-for
处理：
- 验证主题相关性
- 确定内容类型
- 设定字数目标
- 选择语气风格
输出：内容需求规范
## 步骤 2: 主题研究和信息收集
根据主题进行：
- 关键概念识别
- 引用来源搜索
- 竞争内容分析
- GEO 机会识别
输出：主题研究数据
## 步骤 3: 大纲生成
创建内容大纲：
- 生成多个标题选项
- 规划章节结构
- 列出关键要点
- 确定引用来源
输出：结构化大纲
## 步骤 4: 内容生成
根据大纲生成：
- 吸引人的标题
- 清晰的引言
- 详细的主体内容
- 有力的结论
- CTA（如果适用）
输出：完整初稿
## 步骤 5: GEO 优化（如果启用）
优化内容：
- 添加 TL;DR 总结
- 优化核心概念定义
- 添加引用来源标注
- 优化内容结构
- 生成 Schema.org 标记
输出：GEO 优化版本
## 步骤 6: 质量验证
检查内容质量：
- 事实准确性
- 语法正确性
- 可读性评分
- SEO 评分
- GEO 评分
输出：质量报告
## 步骤 7: 最终输出
保存到文件并返回摘要
内容类型详解
1. blog-post（博客文章）
特点：
- 字数：1,000-2,000 词
- 结构：引言 + 3-5 个小节 + 结论
- 语气：专业但易懂
- 目的：教育、吸引流量
生成模板：
# [标题]
## 引言
[100-150 词引言]
## [小节1]
[300-500 词内容]
## [小节2]
[300-500 词内容]
## [小节3]
[300-500 词内容]
## 结论
[100-150 词总结]
## 常见问题
### Q: [问题]？
**A:** [答案]
---
**作者：** [姓名]
**日期：** [日期]
2. guide（指南教程）
特点：
- 字数：2,000-4,000 词
- 结构：TL;DR + 定义 + 步骤 + FAQ
- 语气：指导性、详细
- 目的：教育、操作指导
- AI 引用率： 85%（最高）
生成模板：
# [主题]完整指南
## TL;DR
[100 字总结]
## [主题]是什么？
**定义：** [清晰定义]
**重要性：** [为什么重要]
**应用：** [适用于谁]
## 为什么重要？
1. [理由1]
2. [理由2]
3. [理由3]
## 如何实施（分步骤）
### 步骤1：[标题]
- **目标：** [明确目标]
- **所需时间：** [预期时间]
- **工具：** [推荐工具]
- **详细说明：**
1. [子步骤1]
2. [子步骤2]
3. [子步骤3]
- **示例：** [实际案例]
- **注意事项：** [重要提醒]
[继续其他步骤...]
## 常见问题
### Q: [问题]？
**A:** [直接答案]
**详情：** [详细解释]
**参考：** [来源链接]
## 专家建议
✅ [建议1]
✅ [建议2]
✅ [建议3]
## 相关资源
- [资源1](链接)
- [资源2](链接)
---
**最后更新：** [日期]
**作者：** [姓名 + 资质]
3. case-study（案例研究）
特点：
- 字数：1,200-1,800 词
- 结构：背景 + 策略 + 结果 + 要点
- 语气：叙述性、数据驱动
- 目的：展示成功案例
生成模板：
# 案例研究：[公司]如何[成果]
## 背景和挑战
**公司：** [公司名]
**行业：** [行业]
**规模：** [公司规模]
**挑战：** [面临问题]
- [挑战1]
- [挑战2]
- [挑战3]
## 策略和实施
### 第一阶段：[策略名]
[详细实施过程]
### 第二阶段：[策略名]
[详细实施过程]
### 第三阶段：[策略名]
[详细实施过程]
## 结果和数据
### 关键指标
| 指标 | 优化前 | 优化后 | 提升 |
|------|--------|--------|------|
| 流量 | 5,000 | 12,500 | +150% |
| 转化率 | 2.1% | 4.8% | +129% |
| 排名 | #15 | #3 | +12位 |
### 时间线
- **第1个月：** [结果]
- **第3个月：** [结果]
- **第6个月：** [结果]
## 关键要点
1. [要点1]
2. [要点2]
3. [要点3]
## 适用性
这个策略适用于：
- [适用场景1]
- [适用场景2]
## 经验教训
### 成功因素
- [因素1]
- [因素2]
### 潜在挑战
- [挑战1]
- [挑战2]
---
**案例研究期间：** [日期范围]
**数据来源：** [来源]
**联系方式：** [公司信息]
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 · 775 lines · 22 tokens per session scan A 959d1873de3c
ai-content-generator is a command published in the GitHub repository huifer/claude-code-seo (110 stars, last pushed 8mo ago), licensed MIT. It adds 22 tokens to every session and 4,725 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.
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.