agentmods.dev

read-page

read-page is a command for Claude Code from dodobrands/ai-hub. It costs 22 tokens per session (1,076 once invoked), scanned A, original, MIT.

A command that reads a Buildin.ai page and returns its contents as Markdown. It accepts a page URL, page ID, or search query.

In plain words
What is it for?
Use it to fetch a Buildin.ai page or find one by search, then read its page content in Markdown form.
Why use it?
It removes the need to manually copy page blocks from Buildin.ai into a text document. The description does not provide further details about the returned Markdown or supported authentication setup.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

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 buildin plugin — 2 commands shipped together

not rated 6repo 7d ago A scan 22 tokens original MIT

Good fit Use it to fetch a Buildin.ai page or find one by search, then read its page content in Markdown form.

Compare 6 commands from other repositories ↓
View source ↗ dodobrands/ai-hub
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 dodobrands/ai-hub
Claude Code
/plugin install buildin

Made for: Claude Code.

Or install buildin, the plugin that ships this one along with the rest of its 2 commands.

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 read-page

README.md
[![agentmods](https://agentmods.dev/badge/commands/dodobrands/ai-hub/read-page.svg)](https://agentmods.dev/commands/dodobrands/ai-hub/read-page)
Your own site
<a href="https://agentmods.dev/commands/dodobrands/ai-hub/read-page"><img src="https://agentmods.dev/badge/commands/dodobrands/ai-hub/read-page.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,076 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 $0.00022 $0.01076
Opus 5 $0.00011 $0.00538
Sonnet 5 $0.00004 $0.00215
Haiku 4.5 $0.00002 $0.00108

Measured 8d ago against content hash 332bea902869, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

read-page 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 8d 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.

integrations/buildin/commands/read-page.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read Page — чтение страницы Buildin (UI API)

Читает страницу из Buildin.ai и выводит содержимое как markdown. UI API возвращает все блоки за один запрос.

Константы

Каталог скриптов резолвится так, чтобы команда работала из любого репозитория (standalone-клон, subtree-overlay, marketplace-install). Выполни строку-резолвер перед вызовом скриптов; если bash-блоки запускаются отдельными shell'ами и переменная между ними не сохраняется — повтори её в начале нужного блока.

# resolve-buildin-dir:start — первый существующий из кандидатов: плагин-кеш → overlay → standalone
BUILDIN_SCRIPTS=$(ls -d "${CLAUDE_PLUGIN_ROOT:-/nope}/scripts" "$PWD"/integrations/*/integrations/buildin/scripts "$PWD"/integrations/buildin/scripts 2>/dev/null | head -1)
# resolve-buildin-dir:end

BUILDIN_SPACE_ID = YOUR_SPACE_ID

Известные корневые страницы

Root Page = YOUR_ROOT_PAGE_ID

Входные параметры

Аргумент: $ARGUMENTS

Поддерживаемые форматы:

  • URL: https://buildin.ai/<space_id>/<page_id>
  • UUID: 2a904afe-42e9-4ebd-a94e-f6fe0cbacf58
  • Поисковый запрос: любой текст без UUID — ищет через UI Search API

Workflow

Фаза 0: Проверь авторизацию

bash "$BUILDIN_SCRIPTS/buildin-login.sh" check

Если error:* — запусти /ai-hub:buildin-login для логина.

Фаза 1: Определить page_id

  1. Если аргумент содержит UUID (8-4-4-4-12 hex) — это page_id, извлеки его
  2. Если аргумент — текст без UUID — это поисковый запрос. UI Search API — КРАЙНИЙ способ (качество низкое, результаты часто нерелевантны, к тому же поиск scoped на конкретный space). Порядок:
    • Сначала ищи в shadow-индексе (мгновенно): 
      bash "$BUILDIN_SCRIPTS/buildin-shadow.sh" search "<query>"
    • Если известна базовая страница по теме — обходи дерево от неё вглубь (попутно наполняет shadow-индекс для будущих поисков): 
      bash "$BUILDIN_SCRIPTS/buildin-nav.sh" children "<base_page_id>"
    • Только если выше ничего не дало — UI Search API (укажи нужный space_id, иначе ищет не там): 
      bash "$BUILDIN_SCRIPTS/buildin-nav.sh" search "<query>" "<space_id>"
    Используй найденный page_id. Если не найдено — сообщи пользователю.

Read the full file on GitHub · 110 lines

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. 8d ago First seen · 110 lines · 22 tokens per session scan A 332bea902869

Subscribe to this mod's changes

read-page is a command published in the GitHub repository dodobrands/ai-hub (6 stars, last pushed 7d ago), licensed MIT. It adds 22 tokens to every session and 1,076 once invoked, about $0.0001 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.

Browser automationDocuments
Related

Other commands, from other repositories

pdf

Captures the current page in tandem's Chrome as a PDF (if headless Chrome) or full-page PNG screenshot (in normal tandem mode). Saves to /.claude/tandem/output/.

bgmacris/quimera-ai · 39 tokens

browse

Generate a single-file markdown browser HTML — tree sidebar + marked.js render. Scans project docs/ + /.claude/{plans,projects} by default.

Guohao1020/docs-cockpit · 31 tokens

view-document

Open Trio wiki in the browser, rooted at the current working directory. Auto-invoke when the user asks to open their Markdown wiki, browse notes, or view the current folder as a wiki.

10XTeams/trio · 39 tokens

scrape

Scrape one or more web pages to clean Markdown.

jlehman/api-scribe · 0 tokens

auto-browse

Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.

marcusquinn/aidevops · 18 tokens

brand-generate

Generate an on-brand document from a saved Brand Profile.

ferdinandobons/brand-docs · 0 tokens