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/llm-txtgit 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/llm-txt)<a href="https://agentmods.dev/commands/huifer/claude-code-seo/llm-txt"><img src="https://agentmods.dev/badge/commands/huifer/claude-code-seo/llm-txt.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 | $0.00013 | $0.04834 |
| Opus 5 | $0.00006 | $0.02417 |
| Sonnet 5 | $0.00003 | $0.00967 |
| Haiku 4.5 | $0.00001 | $0.00483 |
Grade A, and why
llm-txt 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.
curl http://localhost:3000/llm.txt How it starts
The opening of the file, as written. The whole thing — 727 lines — stays where its author put it; the contents beside it link to each section on GitHub.
生成 llm.txt 文件，帮助 AI/LLM 爬虫（如 GPTBot, ClaudeBot, Perplexity）更好地理解和索引网站内容。llm.txt 类似于 robots.txt，但是专门为 LLM 爬虫设计的协议。
功能
- ✅ 生成标准的 llm.txt 文件
- ✅ 提供 LLM 爬虫许可和指引
- ✅ 描述网站内容和结构
- ✅ 列出重要页面链接
- ✅ 指定内容授权和使用范围
- ✅ 帮助 AI 更准确地引用和展示网站内容
参数
--verbose: 生成更详细的描述（可选）- 包含更详细的内容说明
- 添加更多重要页面链接
- 提供内容类型和格式说明
背景
什么是 llm.txt？
llm.txt 是一个新兴的标准，类似于 robots.txt，但是专门为 AI/LLM 爬虫设计的。它：
- 告诉 LLM 爬虫哪些内容可以被使用
- 提供网站上下文和内容摘要
- 帮助 AI 更准确地理解和引用内容
- 指定内容使用的授权范围
为什么需要 llm.txt？
- AI 引用准确性 - 帮助 AI 正确引用来源
- 内容可见性 - 控制 LLM 是否可以索引你的内容
- 品牌保护 - 确保内容被正确呈现
- 流量引导 - 引导用户回到原始来源
使用示例
示例 1：基本用法
/llm-txt
输出：
# llm.txt 文件
为你的 Next.js 项目生成的 llm.txt 文件：
```txt
# LLM Crawler Directives
# Allow LLM crawlers to index this site
User-agent: *
Allow: /
# Site Information
Name: YourBrand
Description: [网站描述 - 1-2 句话]
Website: https://yourdomain.com
Language: zh-CN, en-US
# Content Scope
Topics: [主要话题列表]
Content-Type: blog, documentation, tutorials
# Important Pages
Homepage: https://yourdomain.com
About: https://yourdomain.com/about
Blog: https://yourdomain.com/blog
# Attribution Requirements
Require-Attribution: true
Attribution-URL: https://yourdomain.com
# License
License: https://yourdomain.com/license
Content-Use: educational, informational
# Contact
Contact-Email: [email protected]
文件位置
将此文件放置在项目根目录的 public/ 文件夹中：
路径： public/llm.txt
复制上面的内容到 public/llm.txt 文件。
验证
创建后，访问 https://yourdomain.com/llm.txt 验证文件可访问。
填写说明
Name（网站名称）
- 你的品牌或网站名称
- 示例：
SF Plumbing Services或Tech Blog
Description（网站描述）
- 1-2 句话描述你的网站
- 清晰简洁，包含主要话题
- 示例：
提供专业的管道维修和维护服务，覆盖旧金山湾区。包括紧急维修、预防性维护和管道安装服务。
Topics（主要话题）
- 逗号分隔的话题列表
- 示例：
plumbing, emergency services, home maintenance, DIY tutorials
Content-Type（内容类型）
- 主要内容类型
- 常见类型：blog, documentation, tutorials, news, products, services
Important Pages（重要页面）
- 列出你希望 LLM 了解的关键页面
- 包含：关于页面、主要服务页面、重要文章
Require-Attribution（要求归属）
true- 要求 AI 引用时提供链接false- 不要求
License（许可证）
- 指向你的内容许可证页面
- 可以是标准许可证（如 CC BY）
- 或自定义许可证
Content-Use（内容使用范围）
- 允许的使用场景
- 示例：
educational, informational - 或
all（允许所有用途）
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 · 727 lines · 13 tokens per session scan A ab16b1b1d44c
llm-txt is a command published in the GitHub repository huifer/claude-code-seo (110 stars, last pushed 8mo ago), licensed MIT. It adds 13 tokens to every session and 4,834 once invoked, about $0.0001 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.
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.