Skip to main content
prompt GP ChatGPT

web_read_page · wangzan101, entries — Claude Code prompt: read web pages

web_read_page is a Claude Code prompt that reads the text of a web page. Give it a URL to use a temporary background tab, or leave the URL out to read the current tab.

Apache-2.0 ★ 9,488 updated 2026-11-16

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/web_read_page.md
Open on GitHub

What web_read_page does

web_read_page returns the readable page text. Long pages are split into parts; pass nextOffset as offset to continue from the next position.

The result includes a verdict: ok means the read succeeded, thin signals little text, needssignin indicates a sign-in requirement, refused covers verification, refusal, or an HTTP error, and imagetext means the page is mostly images. This prompt does not inspect or operate the page itself; use web_navigate for that.

What it helps with

  • read the text of a page from its URL
  • extract text from the current browser tab
  • continue reading a long page from its next offset
  • identify why a page yielded little or no readable text

Example prompts for the agent

  • Read the full text of the page at this URL.
  • Extract the text from the current tab.
  • Continue from the page's nextOffset.

How to install web_read_page

Manually: put the files in place

.claude/commands/web_read_page.md

Questions about web_read_page

How do I install web_read_page in Claude Code?

Add the command file at .claude/commands/web_read_page.md.

What does web_read_page do?

It reads page text from a supplied URL in a temporary background tab, or from the current tab when no URL is supplied. Long results arrive in parts.

What does the verdict from web_read_page mean?

It reports ok, thin, needssignin, refused, or imagetext to describe the read result. Use web_navigate to inspect or operate the page itself.

Source text

web_read_page.md · Apache-2.0
Read the whole readable text of a web page: with url, that address in a temporary background tab; without url, the current tab. Long pages come in parts: pass nextOffset as offset to read on. verdict tells how the read went: ok; thin (little text); needs_sign_in; refused (a verification, refusal or HTTP error page); image_text (mostly pictures). To look at or operate the page itself, open it with web_navigate.

© wangzan101 · Apache-2.0 · wangzan101/Mika

Similar prompts

Prompts catalog →

web_read_page by other authors comes first.

web_read_page wangzan101 The web_read_page Claude Code prompt extracts readable text from a web page, including content beyond the visible area. It can read the current tab or an address supplied in the request. GP ChatGPT ★ 9,488repo stars read-claude-web-conversation daymade read-claude-web-conversation reads or exports Claude.ai conversations from private and shared links. Use it to pass a web chat to an agent for analysis or keep a local copy. CX Codex +1 394installs Claude Web Page Redesign Planning Prompt [email protected] Claude Web Page Redesign Planning Prompt — a prompt that makes the model audit the current markup and code first, then hand back a redesign plan in markdown. No edits get made. GP ChatGPT ★ 178,201repo stars gws-sheets-read official googleworkspace gws-sheets-read reads cell values and sheets from Google Spreadsheets via CLI. Useful when an agent needs spreadsheet data without risk of altering it. CX Codex +1 52,800installs gws-gmail-read official googleworkspace gws-gmail-read — a skill for Claude Code and Codex: reads a Gmail message and extracts the body or headers via the gws CLI. Runs by message ID when an agent needs to read incoming mail. CX Codex +1 42,800installs read tw93 read fetches a URL or PDF and returns a summary or clean Markdown, with a DeepSeek search fallback when built-in search comes up thin. CX Codex +1 14,600installs read-arxiv-paper karpathy The read-arxiv-paper skill reads an arXiv paper from its source files and writes a Markdown report. It is useful when research needs to be connected to nanochat. CX Codex +1 2,900installs

From the same set132

The whole set →
web_back The web_back Claude Code prompt returns the current browser tab to its previous page. If the address stays the same, the agent follows the page’s own back link. GP ChatGPT ★ 9,488repo stars settings_list The settings_list Claude Code prompt lists Mika settings that can be changed. It runs before settings_set when a user asks to change Mika’s behavior. GP ChatGPT ★ 9,488repo stars run_bundled_script The run_bundled_script Claude Code prompt runs scripts shipped with an app or website entry, or a skill. The agent gets each script’s source and path from knowledge_read or skill_read. GP ChatGPT ★ 9,488repo stars web_search The web_search Claude Code prompt searches through a user-configured endpoint. It runs before opening pages when result titles and snippets are enough to answer the query. GP ChatGPT ★ 9,488repo stars profile_edit The profile_edit prompt for Claude Code and ChatGPT edits one profile sentence after an explicit user request. Changes take effect in the next run. GP ChatGPT ★ 9,488repo stars share_file The share_file Claude Code prompt moves a file from /workspace to the phone’s Download/Mika folder and presents it as a file card. Exported images can also go back to an image-capable messaging conversation when the task ends. GP ChatGPT ★ 9,488repo stars web_wait_for The web_wait_for Claude Code prompt waits for a change on the current tab. It checks page text, the URL, or network activity for a set time. GP ChatGPT ★ 9,488repo stars phone_query The phone_query Claude Code prompt finds controls in an Android accessibility tree. It filters nodes by text, resource ID, or role and returns refs for later actions. GP ChatGPT ★ 9,488repo stars

Project sponsors

Companies that keep this analytics open