npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

super-research-ai-agent

v1.2.2

Published

AI-powered Confluence/Jira research agent — scrapes pages and generates structured reports via Claude

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Git

Maintainers

koknijskoknijs

Keywords

confluencejiraclaudeanthropicairesearchpuppeteerreport

Readme

AI Confluence Reporter

🇬🇧 English | 🇷🇺 Русский

English

A CLI tool for automated analysis of Confluence and Jira pages using Claude AI. It scrapes the page tree, analyzes content, and generates structured reports in .md and .docx formats.

Requirements

Installation

Globally (recommended):

npm install -g super-research-ai-agent

From source:

git clone https://github.com/KokniJS/ai-confluence-reporter.git
cd ai-confluence-reporter
npm install
npm install -g .

Launching browser with remote debugging

The tool connects to an already running browser via WebSocket. Launch Chrome with the --remote-debugging-port flag:

macOS:

/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome \
  --remote-debugging-port=9222 \
  --user-data-dir=/tmp/chrome-debug

Windows:

chrome.exe --remote-debugging-port=9222 --user-data-dir=C:\tmp\chrome-debug

Linux:

google-chrome --remote-debugging-port=9222 --user-data-dir=/tmp/chrome-debug

After launching, open http://localhost:9222/json/version and copy the webSocketDebuggerUrl:

ws://127.0.0.1:9222/devtools/browser/xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx

Usage

research-agent

On first run the agent will ask for:

  1. Browser WebSocket URL — the address from the step above
  2. Claude API key — from console.anthropic.com

Credentials are saved to ~/.super-research-agent.json — no need to re-enter on subsequent runs.

How it works

  1. Agent lists all open browser tabs
  2. Select the Confluence/Jira tab
  3. Agent expands the full page tree in the sidebar
  4. Select sections to analyze (space to check, Enter to confirm)
  5. Agent reads all selected pages in parallel
  6. Claude analyzes the content and generates a report
  7. Report is saved to the reports/ folder as .md and .docx

Report structure

  • Description — project/task overview
  • Key details — concrete facts from the pages
  • Status and next steps
  • Team and access
  • List of analyzed pages
  • Summary (EN)

Reset saved credentials

rm ~/.super-research-agent.json

Русский

CLI-инструмент для автоматического анализа страниц Confluence и Jira с помощью Claude AI. Скрапит дерево страниц, анализирует содержимое и генерирует структурированные отчёты в форматах .md и .docx.

Требования

Установка

Глобально (рекомендуется):

npm install -g super-research-ai-agent

Из исходников:

git clone https://github.com/KokniJS/ai-confluence-reporter.git
cd ai-confluence-reporter
npm install
npm install -g .

Запуск браузера с remote debugging

Инструмент подключается к уже открытому браузеру через WebSocket. Запусти Chrome с флагом --remote-debugging-port:

macOS:

/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome \
  --remote-debugging-port=9222 \
  --user-data-dir=/tmp/chrome-debug

Windows:

chrome.exe --remote-debugging-port=9222 --user-data-dir=C:\tmp\chrome-debug

Linux:

google-chrome --remote-debugging-port=9222 --user-data-dir=/tmp/chrome-debug

После запуска открой http://localhost:9222/json/version и скопируй webSocketDebuggerUrl:

ws://127.0.0.1:9222/devtools/browser/xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx

Использование

research-agent

При первом запуске агент попросит:

  1. Browser WebSocket URL — адрес из шага выше
  2. Claude API key — ключ из console.anthropic.com

Учётные данные сохраняются в ~/.super-research-agent.json — при следующих запусках вводить не нужно.

Процесс работы

  1. Агент показывает список открытых вкладок браузера
  2. Выбери вкладку с Confluence/Jira
  3. Агент раскрывает дерево страниц в сайдбаре
  4. Выбери нужные разделы (пробел — отметить, Enter — подтвердить)
  5. Агент читает все страницы параллельно
  6. Claude анализирует данные и генерирует отчёт
  7. Отчёт сохраняется в папку reports/ в форматах .md и .docx

Структура отчёта

  • Описание — суть проекта/задачи
  • Ключевые детали — конкретные факты
  • Статус и следующие шаги
  • Команда и доступы
  • Список проанализированных страниц
  • Summary (EN) — краткий перевод на английский

Сброс сохранённых данных

rm ~/.super-research-agent.json

License

ISC