What is cm-browser-crawler?

A framework for building browser crawlers that read websites through an already open Google Chrome profile. It supports scrolling, pauses, page-data extraction, and saving results in SQLite with WAL, a database mode designed to handle reading and writing together.

Building crawlers for browser-based research, extracting page content from active Chrome tabs, and storing collected data in a local database.

It provides a defined way to collect website data without using Playwright or starting a separate browser.

cm-browser-crawler — Skill for Claude Code and Codex by tody-agent

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.

Any agent

npx skills add tody-agent/affiliate-product --skill cm-browser-crawler

Clone the repo

git clone --depth 1 https://github.com/tody-agent/affiliate-product

Made for: Claude Code, Codex.

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/skills/tody-agent/affiliate-product/cm-browser-crawler/github.svg)](https://agentmods.dev/skills/tody-agent/affiliate-product/cm-browser-crawler)

Your own site

<a href="https://agentmods.dev/skills/tody-agent/affiliate-product/cm-browser-crawler"><img src="https://agentmods.dev/badge/skills/tody-agent/affiliate-product/cm-browser-crawler/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/skills/tody-agent/affiliate-product/cm-browser-crawler"><img src="https://agentmods.dev/badge/skills/tody-agent/affiliate-product/cm-browser-crawler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,457 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.

Model	Per session	Once invoked
Fable 5.1	$0.00056	$0.01457
Opus 5.5	$0.00022	$0.00583
Sonnet 5.5	$0.00011	$0.00291
Haiku 4.5	$0.00006	$0.00146

Measured 2mo ago against content hash 9387d20ed791, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cm-browser-crawler 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 2mo 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.

skills/cm-browser-crawler/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🌐 CodyMaster Browser Crawler (`cm-browser-crawler`)

Kỹ năng kiến trúc, thiết lập tự động & đóng gói động cơ cào dữ liệu qua Google Chrome (Active Profile / Zero-Playwright)

📦 1. Danh Sách Kỹ Năng, MCP Server & Connector Phụ Thuộc (Dependency Stack)

Để mang sang máy tính khác chạy ngay lập tức mà không gặp lỗi, hệ thống được thiết kế theo chuẩn Zero External Dependencies (Không cần cài thư viện pip ngoài):

A. MCP Server & Connectors:

affiliate-marketplace MCP Server: Chạy tại bin/affiliate-marketplace-mcp qua giao thức chuẩn stdio.
Cơ chế Connector Trình Duyệt:
- macOS (Mặc định): Tận dụng osascript (AppleScript + System Events) có sẵn 100% trên hệ điều hành để điều khiển Google Chrome profile chính.
- Cross-Platform (Linux / Windows): Sử dụng Chrome DevTools Protocol (--remote-debugging-port=9222) hoặc plugin chrome-devtools.

B. Các Kỹ Năng (Skills) Tương Hỗ Trong Hệ Sinh Thái:

cm-browser-crawler: Skill kiến trúc & thiết lập môi trường cào dữ liệu tự động.
fastmoss-category-trends: Worker cào 500 ngành hàng xu hướng.
fastmoss-hashtag-trends: Worker cào 500 thẻ chủ đề TikTok.
fastmoss-hashtag-analyzer: Thẩm định ngách Video vs Video & Cơ hội đại dương xanh.
fastmoss-mcn-crawler: Worker cào 300 MCN Agency & Talent Networks.
fastmoss-sql-intelligence: Truy vấn & khai thác 3 cơ sở dữ liệu SQLite.
aff-video-product: Tự động chuyển đổi dữ liệu cào được thành kịch bản VideoFactory 6 cảnh.

⚡ 2. Cơ Chế Tự Động Cài Đặt Khi Đem Sang Máy Tính Khác (1-Click Auto Setup)

Khi sao chép mã nguồn sang một máy tính mới, bạn chỉ cần chạy 1 lệnh duy nhất:

# Tự động kiểm tra, khởi tạo database, đăng ký MCP server và đồng bộ skills:
affiliate setup
# hoặc:
affiliate setup-crawler

Quy Trình 5 Bước Tự Động Hóa Của Lệnh `affiliate setup`:

Kiểm tra Python & SQLite3: Xác nhận Python >= 3.9 và hỗ trợ chế độ ghi nhanh WAL.
Kiểm tra Google Chrome: Kiểm tra xem Chrome đã được cài đặt và cấp quyền Accessibility / Apple Events chưa.
Khởi tạo 3 Database SQLite Độc Lập: Tự động tạo thư mục data/ và cấu trúc bảng cho:
- data/products.db
- data/fastmoss_category_trends.db
- data/fastmoss_mcn_agencies.db
Tự Động Đăng Ký MCP Server: Cấu hình tự động kết nối MCP Server (affiliate-marketplace) cho Antigravity, Claude Desktop, Claude Code, OpenAI Codex và Cursor.
Đồng Bộ Hệ Thống Skills: Đồng bộ các kỹ năng nghiệp vụ e-commerce tương ứng cho các AI agent.

Read the full file on GitHub · 103 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.

2mo ago First seen · 103 lines · 56 tokens per session scan A 9387d20ed791

Subscribe to this mod's changes

cm-browser-crawler is a skill published in the GitHub repository tody-agent/affiliate-product (2 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 1,457 once invoked, about $0.0002 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.

Browser automation Research

cm-browser-crawler next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cm-browser-crawlertody-agent/affiliate-product	Skill	2	2mo ago	MIT	A	56	Claude Code, Codex
interactive-loginyc-software/qm	Skill	16k	today	MIT	A	46	Claude Code, Codex
pinchtab-mcppinchtab/pinchtab	Skill	11k	11d ago	MIT	A	52	Claude Code, Codex
azure-messaging-webpubsub-javamicrosoft/skills	Skill	3.2k	yesterday	MIT	A	43	Claude Code
cua-driverdavidondrej/skills	Skill	4.3k	yesterday	MIT	A	68	Claude Code, Codex
open-design-browsercompozy/compozy	Skill	2.9k	today	MIT	A	56	Claude Code, Codex
southwestborski/travel-hacking-toolkit	Skill	906	2d ago	MIT	A	40	Claude Code