---
title: "llms.txt defined | Agent Ready Checklist"
description: "llms.txt: A markdown file at /llms.txt: an H1 name, a blockquote summary and H2 sections listing key pages with descriptions. AR-READ-07 asks for a lean one."
canonical: https://agentreadychecklist.com/glossary/llms-txt
site: "Agent Ready Checklist"
last_updated: 2026-11-05
section: "Glossary"
---

# llms.txt defined | Agent Ready Checklist

> llms.txt: A markdown file at /llms.txt: an H1 name, a blockquote summary and H2 sections listing key pages with descriptions. AR-READ-07 asks for a lean one.

Source: https://agentreadychecklist.com/glossary/llms-txt
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).

# llms.txt

A markdown file at /llms.txt: an H1 name, a blockquote summary and H2 sections listing key pages with descriptions. AR-READ-07 asks for a lean one. Example: # Acme > Acme ships a payments API. ## Docs - \[Quickstart\](https://example.com/docs/quickstart): first charge. Related rows: AR-FIND-01, AR-FIND-04, AR-READ-01, AR-READ-06, AR-READ-07. The Verify Kit check llms-linked tests llms.txt.

## Definition

A markdown file at /llms.txt: an H1 name, a blockquote summary and H2 sections listing key pages with descriptions. AR-READ-07 asks for a lean one.

## Example

```markdown
# Acme
> Acme ships a payments API.
## Docs
- [Quickstart](https://example.com/docs/quickstart): first charge
```

## Where it appears on the checklist

-   [AR-FIND-01](https://agentreadychecklist.com/checklist/ar-find-01/)Do not block agents: Do not block agent and crawler access to public content, in robots.txt or at the network layer (WAF, bot manager).
-   [AR-FIND-04](https://agentreadychecklist.com/checklist/ar-find-04/)AI Catalog at .well-known: Publish an AI Catalog at /.well-known/ai-catalog.json listing every agent-facing resource (MCP server card, OpenAPI, A2A card, docs, llms.txt, skills), linked with <link rel="ai-catalog"> and an HTTP Link header.
-   [AR-READ-01](https://agentreadychecklist.com/checklist/ar-read-01/)Answer in the initial HTML: Put the answer in the initial HTML: server-rendered or prerendered, not injected by a single-page app after load.
-   [AR-READ-06](https://agentreadychecklist.com/checklist/ar-read-06/)Link the discovery files: 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.
-   [AR-READ-07](https://agentreadychecklist.com/checklist/ar-read-07/)Ship llms.txt: Ship an llms.txt: a lean, described index of the key pages.
-   [Guide](https://agentreadychecklist.com/guides/one-day-agent-readiness-sprint/)The one-day agent-readiness sprint
-   [Guide](https://agentreadychecklist.com/guides/test-with-a-plain-fetch-client/)How to test with a plain-fetch client
-   [Guide](https://agentreadychecklist.com/guides/read-server-logs-for-agent-user-agents/)How to read your server logs for agent user agents

## Asked about it

### Does llms.txt control which crawlers can read my site?

No. llms.txt is an index for agents to read; it grants or denies nothing. Access is decided by robots.txt for compliant crawlers and by your WAF or bot manager for everything else.

### Where should I link llms.txt from?

From pages agents already read: the footer, a link rel=alternate in the head, or a resources section. 86% of llms.txt fetches in the traced runs arrived through a link, not a guessed path.

## Sources

-   [github.com/agentready-org/standard/blob/main/spec/spec.md](https://github.com/agentready-org/standard/blob/main/spec/spec.md)read 2026-11-04
-   [llmstxt.org](https://llmstxt.org/)read 2026-11-04

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