llms-txt

llms-txt is a cursor rule for Cursor from thatrebeccarae/claude-marketing. It costs 41 tokens per session (2,493 once invoked), scanned A, original, MIT.

A tool for creating and maintaining an `llms.txt` file, a plain-text guide in a project that tells AI systems which documentation and content matter most. The format was proposed by Answer.AI to make projects easier for AI answer systems to understand.

In plain words
What is it for?
Use it when launching or restructuring a project or documentation site, and refresh it after major repository changes.
Why use it?
It organizes important project information in one place so AI systems are less likely to overlook, misunderstand, or misrepresent it.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use it when launching or restructuring a project or documentation site, and refresh it after major repository changes.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/thatrebeccarae/claude-marketing/llms-txt
Install

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.

Clone the repo
git clone --depth 1 https://github.com/thatrebeccarae/claude-marketing

Made for: Cursor.

Wrote 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.

agentmods badge for llms-txt

README.md
[![agentmods](https://agentmods.dev/badge/rules/thatrebeccarae/claude-marketing/llms-txt/github.svg)](https://agentmods.dev/rules/thatrebeccarae/claude-marketing/llms-txt)
Your own site
<a href="https://agentmods.dev/rules/thatrebeccarae/claude-marketing/llms-txt"><img src="https://agentmods.dev/badge/rules/thatrebeccarae/claude-marketing/llms-txt/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for llms-txt

Your own site · 80×15
<a href="https://agentmods.dev/rules/thatrebeccarae/claude-marketing/llms-txt"><img src="https://agentmods.dev/badge/rules/thatrebeccarae/claude-marketing/llms-txt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,493 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.02493
Opus 5 $0.00020 $0.01247
Sonnet 5 $0.00008 $0.00499
Haiku 4.5 $0.00004 $0.00249

Measured 9d ago against content hash 9941ccc6634f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

llms-txt 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 9d 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.

integrations/cursor/llms-txt.mdc · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

llms.txt Generator

Generate and maintain llms.txt files that help AI answer engines surface your project accurately.

When to Use

  • Launching a new open-source project or documentation site
  • Major documentation restructure or content overhaul
  • Improving your project's visibility in AI search (ChatGPT, Perplexity, Google AI Overviews)
  • Onboarding a project to AI-friendly discoverability standards
  • Periodic refresh after significant repo changes

What Is llms.txt

llms.txt is a plain-text markdown file placed in a project's root that gives LLMs a curated map of the project's most important content. Think of it as robots.txt for AI comprehension — instead of telling crawlers where they can go, it tells them what matters and how the project is organized.

The specification was proposed by Answer.AI and is documented at llmstxt.org. Adoption is growing across developer tools, documentation sites, and open-source projects. Projects with an llms.txt are easier for AI to understand, cite, and recommend accurately.

Usage

/llms-txt generate [repo-path]

Scan a repository and generate a new llms.txt file. If no path is provided, uses the current working directory.

/llms-txt audit [repo-path]

Check an existing llms.txt for completeness, broken links, stale descriptions, and missing high-priority content. Produces a report with specific recommendations.

/llms-txt update [repo-path]

Refresh an existing llms.txt based on current repo state. Preserves manually curated descriptions while adding new content and removing references to deleted files.

Procedure

Step 1: Scan Repo Structure

Identify all documentation-relevant files in the repository:

  • README.md (root and significant subdirectories)
  • docs/ directory and its contents
  • API documentation (OpenAPI specs, API reference pages)
  • Tutorials, guides, and getting-started content
  • CHANGELOG.md, CONTRIBUTING.md, FAQ.md
  • Architecture and design decision docs
  • Configuration and deployment guides
  • Example directories with their own READMEs

Read the full file on GitHub · 241 lines

Changes

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.

  1. 9d ago First seen · 241 lines · 41 tokens per session scan A 9941ccc6634f

Subscribe to this mod's changes

llms-txt is a cursor rule published in the GitHub repository thatrebeccarae/claude-marketing (133 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 2,493 once invoked, about $0.0002 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.