agentmods.dev

publish-page

publish-page is a command for Claude Code from dodobrands/ai-hub. It costs 33 tokens per session (4,905 once invoked), scanned A, original, MIT.

A command for creating or updating a page in the Buildin.ai wiki through its user-interface API. It accepts a parent page ID and can use a title, Markdown file, text, or structured content.

In plain words
What is it for?
Checking Buildin authentication, logging in when needed, and creating or updating wiki pages from Markdown, plain text, or structured content.
Why use it?
It provides a repeatable way to publish documentation to Buildin.ai and update an existing page instead of doing the work manually.

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 9repo changed 20d ago A scan 33 tokens original MIT

Good fit Checking Buildin authentication, logging in when needed, and creating or updating wiki pages from Markdown, plain text, or structured content.

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 publish-page

README.md
[![agentmods](https://agentmods.dev/badge/commands/dodobrands/ai-hub/publish-page/github.svg)](https://agentmods.dev/commands/dodobrands/ai-hub/publish-page)
Your own site
<a href="https://agentmods.dev/commands/dodobrands/ai-hub/publish-page"><img src="https://agentmods.dev/badge/commands/dodobrands/ai-hub/publish-page/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 publish-page

Your own site · 80×15
<a href="https://agentmods.dev/commands/dodobrands/ai-hub/publish-page"><img src="https://agentmods.dev/badge/commands/dodobrands/ai-hub/publish-page.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,905 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 $0.00033 $0.04905
Opus 5.5 $0.00013 $0.01962
Sonnet 5.5 $0.00007 $0.00981
Haiku 4.5 $0.00003 $0.00490

Measured 20d ago against content hash 9757291b0627, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

publish-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 20d 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/publish-page.md · 358 lines

How it starts

The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Publish Page — создание и обновление страницы в Buildin (UI API)

Создаёт или обновляет страницу в Buildin.ai. Поддерживает создание из markdown-файлов, текста или структурированного контента.

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

Входные параметры

Аргумент: $ARGUMENTS — parent_page_id и опционально заголовок.

Формат: <parent_page_id> [page_title]

Workflow

Фаза 0: Проверь авторизацию

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

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

ℹ️ Создавать новую страницу или дополнять существующую? Если пользователь просит «добавить / дописать / обновить» уже существующую страницу — переходи к разделу «Обновление существующей страницы» вместо Фаз 1–4.

Фаза 1: Подготовка

  1. Разбери аргументы:
    • Первый аргумент — parent_page_id (UUID родительской страницы)
    • Второй аргумент (опционально) — заголовок страницы
  2. Если заголовок не указан, спроси пользователя через AskUserQuestion

Фаза 2: Сбор контента

  1. Спроси пользователя, что опубликовать:
    • Файл — путь к markdown/текстовому файлу в репозитории
    • Текст — пользователь введёт текст напрямую
    • Пустая страница — создать страницу только с заголовком
  2. Если указан файл, прочитай его содержимое через Read

Фаза 3: Создание страницы

bash "$BUILDIN_SCRIPTS/buildin-pages.sh" create "<parent_page_id>" "<title>"

Read the full file on GitHub · 358 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. 20d ago Changed · +47 lines · +16 tokens per session 9757291b0627
  2. 1mo ago Changed · +51 lines cb6e602e1c6b
  3. 1mo ago Changed · +2 lines 08e43ab39ac4
  4. 1mo ago Changed · +28 lines cbc28d4aa924
  5. 2mo ago First seen · 230 lines · 17 tokens per session scan A cb02601578d5

Subscribe to this mod's changes

publish-page is a command published in the GitHub repository dodobrands/ai-hub (9 stars, last pushed 13d ago), licensed MIT. It adds 33 tokens to every session and 4,905 once invoked, about $0.0001 per session on Opus 5.5. 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.

Writing and docs
Related

publish-page compared with commands from other repositories

publish-page next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
publish-pagedodobrands/ai-hubCommand913d agoMITA33Claude Code
checklistgithub/spec-kitCommand149ktodayMITA13Claude Code
clarifygithub/spec-kitCommand149ktodayMITA27Claude Code
specifygithub/spec-kitCommand149ktodayMITA13Claude Code
convergegithub/spec-kitCommand149ktodayMITA35Claude Code
implementgithub/spec-kitCommand149ktodayMITA14Claude Code
speckit.bug.fixgithub/spec-kitCommand149ktodayMITA12Claude Code