---
title: "Ship llms.txt and link it | Agent Ready Checklist"
description: "How to ship llms.txt and link it. Publish a lean described index at /llms.txt and link it from the footer or head so agents arrive by link."
canonical: https://agentreadychecklist.com/guides/ship-llms-txt-and-link-it
site: "Agent Ready Checklist"
last_updated: 2026-11-05
date: 2026-11-04
section: "Guides"
---

# Ship llms.txt and link it | Agent Ready Checklist

> How to ship llms.txt and link it. Publish a lean described index at /llms.txt and link it from the footer or head so agents arrive by link.

Source: https://agentreadychecklist.com/guides/ship-llms-txt-and-link-it
Site: Agent Ready Checklist
Last reviewed: 2026-11-05
Agent endpoints: https://agentreadychecklist.com/llms.txt (index), https://agentreadychecklist.com/openapi.json (API), https://agentreadychecklist.com/mcp (MCP server), https://agentreadychecklist.com/ask (search)
Access: https://agentreadychecklist.com/auth.md (no key). Pricing: https://agentreadychecklist.com/pricing.md (free).

# How to ship llms.txt and link it

Publish a lean described index at /llms.txt and link it from the footer or head so agents arrive by link. It covers 2 requirements: AR-READ-07, AR-READ-06. Agents reached llms.txt through links in 356 of 416 attributed fetches (86%). The llms.txt format starts with an H1 name, an optional blockquote summary, then H2 sections of markdown link lists.

## Before you start

You need a list of the pages you would send a new reader to first, with a one-line description of each.

## Steps

1.  **[AR-READ-07: Ship llms.txt.](https://agentreadychecklist.com/checklist/ar-read-07/)** Ship an llms.txt: a lean, described index of the key pages.
    
    ```bash
    curl -fsSL https://agentreadychecklist.com/kit/verify.sh | bash -s -- https://example.com --only=llms-linked
    ```
    
     Watch for: One multi-megabyte file that overflows the context window.
2.  **[AR-READ-06: Link the discovery files.](https://agentreadychecklist.com/checklist/ar-read-06/)** Link discovery files (llms.txt, .well-known/\*, openapi.json) from content agents already visit: the footer, <link rel="alternate"> in the head, or a resources section.
    
    ```bash
    curl -fsSL https://agentreadychecklist.com/kit/verify.sh | bash -s -- https://example.com --only=llms-linked,openapi
    ```
    
    Watch for: llms.txt published at the root with nothing pointing to it.
3.  **The shape of the file.** An H1 with the name, a one-line blockquote summary, then H2 sections that list key pages as markdown links with a short description each.
    
    ```markdown
    # Example Co
    
    > Example Co sells invoicing software for small firms.
    
    ## Docs
    
    - [Quick start](https://example.com/docs/start/): install and first invoice
    ```
    

## How you know it is done

You are done when /llms.txt returns 200 as text, starts with an H1, and the home page links to it so that an agent arrives by link.

## The facts behind it

-   The llms.txt format starts with an H1 name, an optional blockquote summary, then H2 sections of markdown link lists.primary source: [llmstxt.org](https://llmstxt.org/), read 2026-11-04
-   Agents reached llms.txt through links in 356 of 416 attributed fetches (86%).primary source, 2026-08-28: [vercel.com/kb/guide/make-your-site-readable-by-ai-agents](https://vercel.com/kb/guide/make-your-site-readable-by-ai-agents), read 2026-11-04
-   Of 329 runs that reached llms.txt, 120 (36%) grounded the final answer in its content.primary source, 2026-08-28: [vercel.com/kb/guide/make-your-site-readable-by-ai-agents](https://vercel.com/kb/guide/make-your-site-readable-by-ai-agents), read 2026-11-04
-   Cloudflare generates one llms.txt per top-level docs directory and omits about 450 directory-listing pages from them.primary source, 2026-04-17: [blog.cloudflare.com/agent-readiness/](https://blog.cloudflare.com/agent-readiness/), read 2026-11-04
-   Cloudflare isitagentready does not check llms.txt by default; it is an opt-in check.primary source, 2026-04-17: [blog.cloudflare.com/agent-readiness/](https://blog.cloudflare.com/agent-readiness/), read 2026-11-04

## Sources

-   [llmstxt.org](https://llmstxt.org/)read 2026-11-04
-   [vercel.com/kb/guide/make-your-site-readable-by-ai-agents](https://vercel.com/kb/guide/make-your-site-readable-by-ai-agents)read 2026-11-04
-   [blog.cloudflare.com/agent-readiness/](https://blog.cloudflare.com/agent-readiness/)read 2026-11-04

Edition

Data

2026-11-04

Reviewed

2026-11-05

Spec

AgentReady v2.0, 273d2d7

Crawl

13,071 rows, 2026-11-04

Ora

132 checks, contract 1.38.0, 2026-11-05

Verify with Ora

The scanner this site recommends for the whole checklist. 132 checks, a score out of 100, no account.

`npx ax@0.10 audit <url> --min-score <n>`

[Why Ora, and its limits](https://agentreadychecklist.com/verify-with-ora/)

Method

-   [How rows, commands and rates are made](https://agentreadychecklist.com/method/)
-   [How an Ora check is matched to a row](https://agentreadychecklist.com/checklist/ora-checks/)
-   [Pass rates by rank band](https://agentreadychecklist.com/data/by-rank/)

Sources and read dates sit at the foot of the page.

Last reviewed 2026-11-05. AgentReady v2.0, read 2026-11-04.