A toolkit for automating X/Twitter through a web browser. It provides tools for scraping posts and accounts, publishing, engagement, and analytics, using Puppeteer, a browser-automation library.

Use it to collect X/Twitter data, publish or engage with posts, and inspect account or activity analytics.

It lets workflows interact with X/Twitter without paying for the platform’s API, while using a logged-in browser session.

xactions — Plugin for Claude Code by nirholas

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/nirholas/XActions

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/nirholas/xactions/xactions/github.svg)](https://agentmods.dev/plugins/nirholas/xactions/xactions)

Your own site

<a href="https://agentmods.dev/plugins/nirholas/xactions/xactions"><img src="https://agentmods.dev/badge/plugins/nirholas/xactions/xactions/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/nirholas/xactions/xactions"><img src="https://agentmods.dev/badge/plugins/nirholas/xactions/xactions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 50 skills, 1 MCP server cost 2,913 tokens a session between them.

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.

Security

Grade A, and why

xactions 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 1mo 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.

.claude-plugin/plugin.json · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "name": "xactions",
  "version": "3.5.0",
  "description": "Complete X/Twitter automation toolkit — 154 MCP tools for scraping, posting, engagement, analytics, and more. No API fees. Uses Puppeteer browser automation.",
  "author": "nichxbt",
  "homepage": "https://xactions.app",
  "repository": "https://github.com/nirholas/xactions",
  "license": "Apache-2.0",
  "tags": [
    "twitter",
    "x",
    "social-media",
    "automation",
    "scraping",
    "mcp",
    "engagement",
    "analytics"
  ],
  "setup": {
    "install": "npm install xactions",
    "instructions": "After installing, set XACTIONS_SESSION_COOKIE to your X/Twitter auth_token cookie (DevTools → Application → Cookies → auth_token on x.com)."
  },
  "mcpServers": {
    "xactions": {
      "command": "node",
      "args": [
        "node_modules/xactions/src/mcp/server.js"
      ],
      "env": {
        "XACTIONS_MODE": "local"
      }
    }
  },
  "skills": [
    {
      "name": "x-automation",
      "path": "./skills/x-automation.md"
    },
    {
      "name": "x-scraping",
      "path": "./skills/x-scraping.md"
    },
    {
      "name": "x-engagement",
      "path": "./skills/x-engagement.md"
    },
    {
      "name": "x-management",
      "path": "./skills/x-management.md"
    }
  ],
  "agents": [
    {
      "name": "growth",
      "description": "Automate X/Twitter growth — follow targets, engage with content, analyze performance",
      "path": "./agents/growth.md"
    },
    {
      "name": "cleanup",
      "description": "Clean up your X/Twitter account — unfollow non-followers, unlike old posts, clear bookmarks",
      "path": "./agents/cleanup.md"
    },
    {
      "name": "scrape",
      "description": "Scrape X/Twitter data — profiles, followers, tweets, trends. Export to JSON/CSV",
      "path": "./agents/scrape.md"
    }
  ],
  "commands": {
    "scrape-profile": {
      "description": "Scrape a user's X/Twitter profile",
      "agent": "./agents/scrape.md",
      "args": {

Read the full file on GitHub · 100 lines

Contents

What it installs

The manifest is a name and a version. 50 skills, 1 MCP server travel with it, and installing the plugin installs all of them — 2,913 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

9 files beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago Changed c7d63a78602b
1mo ago First seen · 100 lines scan A b012eba80486

Subscribe to this mod's changes

xactions is a plugin published in the GitHub repository nirholas/XActions (594 stars, last pushed today), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.

Browser automation Marketing and SEO ai-agent automation claude gpt mass-unfollow mcp

xactions

Getting it into your agent

Wrote this? Show the measurements

Grade A, and why

Nothing flagged

How it starts

What it installs

What ships with it

What this file has done since we first saw it

Other plugins, from other repositories

build-information

kernel-sdks

realbrowser

headless

chrome-multi-instance-warn

claudeshot