llm-page-context-cli

name	llm-page-context-cli
description	Use this skill when you need to turn one URL into an LLM context text file for an agent workflow. It runs the llm-page-context-cli package, saves the context text into ./llm-page-context by default, and returns machine-readable JSON containing the absolute file path and token estimate.

llm-page-context-cli

Use this skill when:

• the user gives you a URL and wants a saved context text file
• the output should be agent-friendly and machine-readable
• you need the absolute file path of the saved context file
• you need an approximate token count for the saved context

Default behavior

The CLI:

1. opens the URL in a browser
2. extracts the main readable content
3. builds a single llm_context string
4. saves it as ./llm-page-context/<slug>.txt
5. prints JSON to stdout

Command

From the monorepo root:

pnpm run extract:context-file -- <url>

Direct package command:

node packages/cli/bin/llm-page-context-cli.mjs <url>

Published package form:

npx llm-page-context-cli <url>

Options

• --output-dir <dir> to change the target directory
• --file-slug <slug> to override the generated filename

Output contract

Success:

{
  "ok": true,
  "url": "https://example.com/",
  "title": "Example Domain",
  "filePath": "/absolute/path/to/llm-page-context/example-comhome.txt",
  "tokens": 78,
  "bytes": 312,
  "capturedAt": "2026-03-21T10:00:00.000Z"
}

Failure:

{
  "ok": false,
  "error": "..."
}

Notes

• Prefer using the JSON output directly instead of parsing human-readable logs.
• The saved file is plain text and is intended to be dropped directly into an LLM prompt.
• Token count is approximate.