How do I install the Lexmount Webfetch skill?

Run npx skillmds@latest add lexmount/lexmount-webfetch in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Lexmount Webfetch safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Lexmount Webfetch?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Lexmount Webfetch free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Lexmount Webfetch?

lexmount (@lexmount) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Lexmount Webfetch by lexmount — Agent Skill

Name: Lexmount Webfetch
Author: lexmount

Lexmount Webfetch

Use Lexmount WebFetch through webfetch-cli for lightweight public page extraction and DOM dump tasks. Prefer this skill when the task needs structured extraction or rendered HTML capture without creating a live remote browser session.

lexmount 25d7973 11 files · 13.8 KB Updated Sep 17, 2026

File contents

Lexmount WebFetch CLI

Use webfetch-cli when a task needs to fetch a public page through Lexmount WebFetch instead of opening a live browser session.

Fast Path

Do not run setup checks before every extraction. For ordinary fetch tasks, call the target command directly:

webfetch-cli extract --url <url>
webfetch-cli dump-dom --url <url>

Run checks only when they change the next action:

First use in a new environment: webfetch-cli --version and webfetch-cli auth status.
Missing credentials: webfetch-cli auth login --open --connect-base-url https://browser.lexmount.cn, then webfetch-cli doctor --json.
Unexpected command/API failure: webfetch-cli doctor --json.
Unsure installed capability or output shape: webfetch-cli capabilities --json.
Skill file missing or stale: webfetch-cli skill status, then webfetch-cli skill install --force only if needed.

Do not ask users to paste API keys into chat. webfetch-cli auth login stores credentials locally after a one-time PKCE callback.

Commands

webfetch-cli extract --url <url> extracts structured page content.
webfetch-cli extract --dom-id <dom_id> extracts from an existing DOM dump.
webfetch-cli dump-dom --url <url> captures rendered DOM and returns a reusable dom_id when available.

Default output is Markdown optimized for agents. It includes metadata, content, and extraction/dump quality warnings while hiding trace/debug/raw response fields.

Use output formats deliberately:

--format md: default agent-readable Markdown.
--format text: plain text plus minimal metadata.
--format json: compact structured output without trace/debug fields.
--format json-full: original API response for debugging.

Use heavy debug fields only when needed:

webfetch-cli extract --url https://example.com --include-trace --format json-full
webfetch-cli extract --url https://example.com --include-raw-dom --format json-full

DOM dump supports engine and cleanup hints:

webfetch-cli dump-dom --url https://example.com --engine lightmount_dcl
webfetch-cli dump-dom --url https://example.com --filter-scripts-styles

Use --timeout-ms only when the default request timeout is insufficient.

---name: lexmount-webfetchdescription: Use Lexmount WebFetch through webfetch-cli for lightweight public page extraction and DOM dump tasks. Prefer this skill when the task needs structured extraction or rendered HTML capture without creating a live remote browser session.---# Lexmount WebFetch CLIUse `webfetch-cli` when a task needs to fetch a public page through Lexmount WebFetch instead of opening a live browser session.## Fast PathDo not run setup checks before every extraction. For ordinary fetch tasks, call the target command directly:```bashwebfetch-cli extract --url <url>webfetch-cli dump-dom --url <url>```Run checks only when they change the next action:- First use in a new environment: `webfetch-cli --version` and `webfetch-cli auth status`.- Missing credentials: `webfetch-cli auth login --open --connect-base-url https://browser.lexmount.cn`, then `webfetch-cli doctor --json`.- Unexpected command/API failure: `webfetch-cli doctor --json`.- Unsure installed capability or output shape: `webfetch-cli capabilities --json`.- Skill file missing or stale: `webfetch-cli skill status`, then `webfetch-cli skill install --force` only if needed.Do not ask users to paste API keys into chat. `webfetch-cli auth login` stores credentials locally after a one-time PKCE callback.## Commands- `webfetch-cli extract --url <url>` extracts structured page content.- `webfetch-cli extract --dom-id <dom_id>` extracts from an existing DOM dump.- `webfetch-cli dump-dom --url <url>` captures rendered DOM and returns a reusable `dom_id` when available.Default output is Markdown optimized for agents. It includes metadata, content,and extraction/dump quality warnings while hiding trace/debug/raw responsefields.Use output formats deliberately:- `--format md`: default agent-readable Markdown.- `--format text`: plain text plus minimal metadata.- `--format json`: compact structured output without trace/debug fields.- `--format json-full`: original API response for debugging.Use heavy debug fields only when needed:```bashwebfetch-cli extract --url https://example.com --include-trace --format json-fullwebfetch-cli extract --url https://example.com --include-raw-dom --format json-full```DOM dump supports engine and cleanup hints:```bashwebfetch-cli dump-dom --url https://example.com --engine lightmount_dclwebfetch-cli dump-dom --url https://example.com --filter-scripts-styles```Use `--timeout-ms` only when the default request timeout is insufficient.

Frequently asked questions