llms-maintainer

llms-maintainer is an agent for coding agents from davepoon/buildwithclaude. It costs 34 tokens per session (341 once invoked), scanned A, original, MIT.

An agent that creates and maintains an llms.txt file, a plain-text roadmap that helps AI crawlers understand a website's pages and structure. It discovers public pages and records their metadata and links.

In plain words
What is it for?
Scanning site directories, finding public pages, reading titles and descriptions, generating or updating public/llms.txt, and preserving custom content blocks.
Why use it?
The file can become outdated as pages, content, or build output changes. This keeps the roadmap aligned with the site's current user-facing structure.

Agent

Part of the agents-data-ai plugin — 12 agents shipped together

About the project

davepoon/buildwithclaude is a discovery hub and plugin marketplace for Claude Code extensions, including agents, commands, hooks, skills, plugins, MCP servers, and marketplace collections. Developers use it to browse, search, and find installation instructions for tools that extend Claude-related workflows. Catalogue entries include agents, plugins, commands, and skills from this collection.

davepoon/buildwithclaude · 3,415 stars · on GitHub

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.

agentmods
npx agentmods add agents/davepoon/buildwithclaude/llms-maintainer
Clone the repo
git clone --depth 1 https://github.com/davepoon/buildwithclaude

Or install agents-data-ai, the plugin that ships this one along with the rest of its 12 agents.

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-maintainer

README.md
[![agentmods](https://agentmods.dev/badge/agents/davepoon/buildwithclaude/llms-maintainer.svg)](https://agentmods.dev/agents/davepoon/buildwithclaude/llms-maintainer)
Your own site
<a href="https://agentmods.dev/agents/davepoon/buildwithclaude/llms-maintainer"><img src="https://agentmods.dev/badge/agents/davepoon/buildwithclaude/llms-maintainer.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 341 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00034 $0.00341
Opus 5 $0.00017 $0.00170
Sonnet 5 $0.00007 $0.00068
Haiku 4.5 $0.00003 $0.00034

Measured 5d ago against content hash 28274f516182, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

llms-maintainer 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 5d 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.

plugins/agents-data-ai/agents/llms-maintainer.md · 29 lines

What it actually says

You are the LLMs.txt Maintainer, a specialized agent responsible for generating and maintaining the llms.txt roadmap file that helps AI crawlers understand your site's structure and content.

When invoked:

  • Generate or update ./public/llms.txt following a systematic discovery and metadata extraction process
  • Identify site root and base URL from environment variables or package.json
  • Discover candidate pages by scanning content directories while ignoring private/internal paths
  • Extract metadata from Next.js metadata exports, HTML head tags, or front-matter YAML

Process:

  1. Identify base URL from process.env.BASE_URL, NEXT_PUBLIC_SITE_URL, or package.json homepage
  2. Recursively scan /app, /pages, /content, /docs, /blog directories for user-facing pages
  3. Extract titles and descriptions, generating concise descriptions (≤120 chars) when missing
  4. Build llms.txt with proper header structure and preserve custom content blocks
  5. Organize entries by top-level folders with proper URL and description formatting
  6. Compare with existing file and only update if changes detected

Provide:

  • Updated llms.txt file with complete site structure and metadata
  • Clear summary of changes made or confirmation that no update was needed
  • Page count and sections affected in the update
  • Error handling for missing base URLs, file permissions, or metadata extraction failures
  • Git commit operations when appropriate with proper commit messages
  • Preservation of any existing custom content blocks bounded by BEGIN/END CUSTOM markers
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. 5d ago First seen · 29 lines · 34 tokens per session scan A 28274f516182

Subscribe to this mod's changes

llms-maintainer is an agent published in the GitHub repository davepoon/buildwithclaude (3,415 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 341 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.