generate-llmstxt

generate-llmstxt is a skill for Claude Code from YoungjaeDev/my-claude-plugins. It costs 84 tokens per session (467 once invoked), scanned A, original, MIT.

A tool for creating an llms.txt file from a documentation website or local folder. The file is a directory of useful documentation links for language-model tools.

In plain words
What is it for?
Use it to build an llms.txt from a website or repository, group its links into sections, and record short descriptions of the sources.
Why use it?
It turns scattered documentation pages into a compact, organized index that automated tools can use to find relevant information.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions Claude Code; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the scout plugin — 4 skills, 8 agents, 1 MCP server shipped together

Good fit Use it to build an llms.txt from a website or repository, group its links into sections, and record short descriptions of the sources.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add YoungjaeDev/my-claude-plugins
Claude Code
/plugin install scout

Made for: Claude Code.

Or install scout, the plugin that ships this one along with the rest of its 4 skills, 8 agents, 1 MCP server.

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 generate-llmstxt

README.md
[![agentmods](https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/generate-llmstxt/github.svg)](https://agentmods.dev/skills/youngjaedev/my-claude-plugins/generate-llmstxt)
Your own site
<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/generate-llmstxt"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/generate-llmstxt/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 generate-llmstxt

Your own site · 80×15
<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/generate-llmstxt"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/generate-llmstxt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 467 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 $0.00084 $0.00467
Opus 5 $0.00042 $0.00234
Sonnet 5 $0.00017 $0.00093
Haiku 4.5 $0.00008 $0.00047

Measured 4d ago against content hash d233b9c798b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

generate-llmstxt 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 4d 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/scout/skills/generate-llmstxt/SKILL.md · 22 lines

What it actually says

Generate llms.txt

Generate a well-structured llms.txt from a URL (via sitemap discovery + Bright Data scrape) or a local directory (via Glob + Read). Invoke it as /scout:generate-llmstxt or let the model reach for it on matching requests.

  1. Confirm the input source: URL or local path. If ambiguous, ask.
  2. Follow the workflow in the procedure file for the matched input type.
  3. Write llms.txt to the current directory and report sources processed, sections created, and any errors.

See references/generate-llmstxt-procedure.md in this plugin's installed root for the full workflow and guidelines. Under Claude Code this resolves to ${CLAUDE_PLUGIN_ROOT}/references/generate-llmstxt-procedure.md; under Codex the equivalent path lives next to skills/ in the plugin cache.

Requirements

This skill does NOT call the DeepWiki MCP: the procedure only uses Bright Data (URL mode) or Glob + Read (local mode). Pick the row for the input you pass:

  • URL mode: Bright Data MCP must be available; mcp__brightdata__scrape_as_markdown is the one hard requirement; scrape_batch is used when present and otherwise stood in for by looping scrape_as_markdown per URL (it may sit in a Pro group a default Rapid/Free MCP does not load). The bdata CLI is the terminal fallback for both. If none is reachable, run the brightdata-guide four-gate preflight, report the failing gate, and stop instead of degrading to a plain fetch. Internet connection required (the scrape hits external sites).
  • Local directory mode: read permission on the target directory. No MCP or network required.
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. 4d ago Changed d233b9c798b5
  2. 9d ago First seen · 22 lines · 84 tokens per session scan A 05a8edcfeb11

Subscribe to this mod's changes

generate-llmstxt is a skill published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 84 tokens to every session and 467 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens