Skip to content
LLMSRank

AGENTS.md and agent-instructions builder

Answer eight short sections about your site and get two things: a block for your llms.txt (“For AI agents”, “Intent routing”, “Data freshness” and “Identity”) and an AGENTS.md. Every line comes from what you typed. The builder runs in your browser and nothing you type is sent anywhere, unless you choose to score a file against your site’s latest scan.

These files are instructions, not controls. Our audits check that the sections are there. They can’t tell you what any agent does with them. Sources: Our audit doc: Role and scope (A1); Our research: Does ChatGPT, Claude, Perplexity or Google read llms.txt? (vendor statements, checked 2026-09-29). Claims checked 2026-10-02.

The audit panel scores your llms.txt text for Role and scope, Data-freshness tiers, Intent routing, FAQ blocks, Entity identity and shows whether your AGENTS.md is at least 200 bytes. The form has no industry field, so the industry compliance audit (P2) is not shown here; a scan of your site covers it. The panel does not add the audits into one number.

Your details

Everything stays in your browser. Start from an example, or fill the sections in yourself.

Your site
1. Role and scope

The llms.txt block helps only agents that fetch llms.txt. The block does nothing for an agent that never fetches your llms.txt. We checked vendor documentation on 2026-09-29. No AI vendor has documented reading other sites’ llms.txt files, in an assistant, a search product or a crawler. Google says Google Search ignores them. The tools documented to read llms.txt read a file that a user points them at. Sources: Our research: Does ChatGPT, Claude, Perplexity or Google read llms.txt? (vendor statements, checked 2026-09-29) (2026-09-29); Google Search Central: Optimizing your website for generative AI features on Google Search (“Google Search ignores them”) (2026-07-10).

“The engine credits this” is not “agents obey this”. Our audits check that sections such as “For AI agents”, “Data freshness” and “Intent routing” are present and worded as the audit expects. A full score on A1, A2 or A3 means the text is there. It says nothing about whether an agent read it or acted on it. No agent is bound by your llms.txt or your AGENTS.md. Sources: Our audit doc: Role and scope (A1); Our audit doc: Data-freshness tiers (A2); Our audit doc: Intent routing (A3); Our research: Does ChatGPT, Claude, Perplexity or Google read llms.txt? (vendor statements, checked 2026-09-29) (2026-09-29).

2. Citation
3. Never confirm without a live check
4. Data freshness

Freshness and never-confirm lines are requests. A data-freshness tier or a never-confirm rule asks an agent to be careful. It can’t stop an agent from quoting an old price or a sold-out item as current. Keep prices, stock and availability on your own systems. Check them there before you accept any order, booking or quote. Sources: Our audit doc: Data-freshness tiers (A2).

5. Intent routing

“The engine credits this” is not “agents obey this”. Our audits check that sections such as “For AI agents”, “Data freshness” and “Intent routing” are present and worded as the audit expects. A full score on A1, A2 or A3 means the text is there. It says nothing about whether an agent read it or acted on it. No agent is bound by your llms.txt or your AGENTS.md. Sources: Our audit doc: Role and scope (A1); Our audit doc: Data-freshness tiers (A2); Our audit doc: Intent routing (A3); Our research: Does ChatGPT, Claude, Perplexity or Google read llms.txt? (vendor statements, checked 2026-09-29) (2026-09-29).

6. Handoff to a person

“The engine credits this” is not “agents obey this”. Our audits check that sections such as “For AI agents”, “Data freshness” and “Intent routing” are present and worded as the audit expects. A full score on A1, A2 or A3 means the text is there. It says nothing about whether an agent read it or acted on it. No agent is bound by your llms.txt or your AGENTS.md. Sources: Our audit doc: Role and scope (A1); Our audit doc: Data-freshness tiers (A2); Our audit doc: Intent routing (A3); Our research: Does ChatGPT, Claude, Perplexity or Google read llms.txt? (vendor statements, checked 2026-09-29) (2026-09-29).

7. Identity

Also known as

Identifiers

Glossary

Identifiers help only when they are right. An LEI, a Wikidata ID, a stock ticker or a registration number can help an agent tell you apart from a similar name. That holds only if the value is correct and matches the rest of your site. Use the same legal name and identifiers in your Organization JSON-LD (our JSON-LD agreement audit, E4) and in the Identity section (our Entity identity audit, A8). A wrong identifier points to another organization. Sources: Our audit doc: Entity identity (A8); Our audit doc: JSON-LD agreement (E4).

8. API (only if you have one)

Freshness and never-confirm lines are requests. A data-freshness tier or a never-confirm rule asks an agent to be careful. It can’t stop an agent from quoting an old price or a sold-out item as current. Keep prices, stock and availability on your own systems. Check them there before you accept any order, booking or quote. Sources: Our audit doc: Data-freshness tiers (A2).

Audits

Fill in a section or pick an example to see the audits. They are scored in your browser as you type.

Agent files E7AGENTS.md ≥ 200 bytes: not yet (0 bytes)

Only the size is checked here. A scan checks that the file is served at your site root.

Your llms.txt block

Paste this under the existing sections of your llms.txt. You can edit it here; changing the form writes it again and replaces your edits.

Your AGENTS.md

AGENTS.md is a code-repository convention. agents.md calls AGENTS.md “a README for agents.” It says to put the file at the root of a code repository. Coding agents read it while they work in that repository, and the closest AGENTS.md to the edited file wins. It is plain Markdown with no required fields. OpenAI contributed it to the Agentic AI Foundation (AAIF) when the Linux Foundation formed that foundation on 2025-12-09. agents.md now says the AAIF stewards it. Sources: agents.md: “a README for agents”; “Create an AGENTS.md file at the root of the repository”; “just standard Markdown”; “The closest AGENTS.md to the edited file wins”; Linux Foundation press release: formation of the Agentic AI Foundation (AAIF), with MCP, goose and AGENTS.md (contributed by OpenAI) (2025-12-09).

A web-root /AGENTS.md is our rubric’s recommendation. agents.md says nothing about websites serving `/AGENTS.md`. We found no agent documented as fetching one from a website. Our rubric’s Agent files audit (E7) checks for one at your site root, and counts it from 200 bytes. That is our rubric’s recommendation, not a published standard for websites. Sources: agents.md: “a README for agents”; “Create an AGENTS.md file at the root of the repository”; “just standard Markdown”; “The closest AGENTS.md to the edited file wins”; Our audit doc: Agent files (E7); Our guide: llms.txt vs AGENTS.md.

Export

Before you publish: these are instructions for agents, not controls. A full audit score means the sections are present. Check prices and availability on your own systems. Make sure every identifier is correct. Sources: Our audit doc: Role and scope (A1); Our audit doc: Data-freshness tiers (A2); Our audit doc: Entity identity (A8).

Files are saved as UTF-8 text with LF line endings and one final newline, and no byte order mark.

Put AGENTS.md at the root of your code repository, where coding agents look for it. Serving a copy at your site root is our rubric’s recommendation (audit E7), not a published standard.

Load my current llms.txt

Optional: fetch your live file so the block can be appended to it and scored with it. This counts as one of your free scans.

Compare with my live AGENTS.md

Optional: fetch the AGENTS.md served at your site root to see what your new one changes. This counts as one of your free scans.