What is a sales opportunity?

A sales opportunity is a qualified prospect who has shown interest in your product or service and has the potential to become a paying customer. We help identify and nurture these opportunities through automated systems.

Who is this service for?

Our revenue systems are designed for B2B companies, SaaS businesses, and enterprises looking to optimize their go-to-market strategy and scale their top-of-funnel operations through AI-powered automation tools like Clay, n8n, and Instantly.ai.

How does your pricing work?

Every company is typically in a different place, so we have various engagement models designed to meet different needs. Most engagements begin with a launch package where we stand up infrastructure suitable for your volume needs. We typically charge on retainer as an engaged, ongoing partnership to build and maintain systems and deliverability. We also offer project-based website build-outs delivered in phases. Our pricing is value-based and tailored to your specific needs, infrastructure requirements, and growth goals.

How are you different from traditional lead generation agencies?

We don't consider ourselves a lead generation agency. We build top-of-funnel revenue systems designed to increase your top line and support sustainable growth. Rather than just generating leads, we plug into your existing offerings and consult to deliver your solution to market more effectively. We help bridge the gap to raise top-line revenue, optimize go-to-market strategy, improve operational efficiency, and drive continued growth. Our approach includes gaining market intelligence, rapidly testing outbound campaigns at scale to validate product-market fit, and consulting on creative approaches to pique curiosity, raise awareness, and start new conversations with qualified opportunities.

What is a sales opportunity?

We define a 'sales opportunity' as a targeted person in your target market who is interested in talking to you about your product or service.

Who is this service for?

This service is for B2B businesses who want to scale their offerings and are not already using email marketing effectively. It's perfect for founders who want to spend more time closing deals instead of prospecting, have a compelling offer and strong value proposition, and are prepared to handle interested leads with care and attention. If you're buying into multiple tools like Apollo or ZoomInfo, we can save you time and money while automating and scaling your process.

How does your pricing work?

Our pricing is value-based and tailored to your specific needs, infrastructure requirements, and growth goals. We typically charge on retainer as an engaged, ongoing partnership. Most engagements begin with a launch package where we stand up the infrastructure suitable for your volume needs to generate opportunities and pipeline. We also offer website build-outs which are typically project-based and delivered in a phased approach. For detailed pricing, visit our pricing page or book a consultation.

How are you different from traditional lead generation agencies?

We don't consider ourselves a lead generation agency. We build top-of-funnel revenue systems designed to increase your top line and support sustainable growth. Rather than just generating leads, we plug into your existing offerings and consult to deliver your solution to market more effectively. Our approach includes gaining market intelligence, rapidly testing outbound campaigns at scale to validate product-market fit, and consulting on creative approaches to pique curiosity and start new conversations with qualified opportunities. We optimize what you currently have, test hypotheses quickly, and build systems that scale—not just send emails.

What do I need to do to get started?

To get started, we schedule a discovery call to ensure we are a good fit for your business needs and goals. From there, we set up your inboxes (domain purchases, inbox configurations, DMARC/DKIM, etc), which require a two-week warm up period. We schedule an onboarding session with you and develop a creative winning strategy with your offer.

Agent Tools

Forked & Extended by BrandonIn Our OpenClaw Stackpi skill

Chrome CDP Skill

Give your AI agent eyes into your live Chrome session — the tabs you already have open, the accounts you’re already logged into, the tools you use every day.

Most browser tools launch a fresh, empty browser that has to log in from scratch. This one connects directly to Chrome you’re already running. No extra setup. No re-authentication. One toggle to enable.

View on GitHub

Toggle to Enable

Commands

100+

Tabs Supported

Re-Logins

terminal

$ pi install git:github.com/bcharleson/chrome-cdp-skill

or clone the repo and copy skills/chrome-cdp/ to your agent skills directory

Setup in 2 Steps

Enable Chrome Remote Debugging

Open Chrome, go to this URL, and flip the toggle. That’s the only Chrome configuration needed. Chrome will show a one-time “Allow debugging” modal the first time each tab is accessed — after that, the skill holds the connection open silently.

Paste in Chrome address bar

chrome://inspect/#remote-debugging

Install the Skill

For pi-based CLI agents (one command):

Terminal

pi install git:github.com/bcharleson/chrome-cdp-skill

For other agents (Claude Code, Amp, Cursor, etc.) — clone and copy the skills directory:

Terminal

git clone https://github.com/bcharleson/chrome-cdp-skill
# Copy skills/chrome-cdp/ to wherever your agent loads skills from
# Requires Node.js 22+ — no npm install needed

Verify It Works

Terminal

scripts/cdp.mjs list
# Returns a list of all open Chrome tabs
# Copy the targetId prefix for any tab you want to interact with

The targetId is an ID like 6BE827FA. You only need a unique prefix — 6-8 chars is usually enough.

Why This Is Different From Other Browser Tools

Other browser automation tools

Launch a fresh, empty browser — no cookies, no sessions, not logged in to anything
Require you to pass credentials, set cookies, or manage session tokens just to reach gated pages
LinkedIn, HubSpot, Gmail, Notion — all block or break under headless browser traffic
Can time out or lose sessions with many tabs open
Reconnect on every command — Chrome modal can re-appear repeatedly

Chrome CDP Skill

Connects to the Chrome you already have open — all sessions, all logins, all tabs intact
No credential management — your agent inherits your authenticated state automatically
LinkedIn, HubSpot, Gmail, your internal tools — all readable because you are already logged in
Holds a persistent daemon per tab — handles 100+ tabs without timeouts
Chrome modal fires once per tab, then the connection stays open silently

Real Use Cases

From non-technical GTM workflows to advanced browser automation — here is how this changes the game.

Pre-Call LinkedIn Research

GTM / Sales

Agent Prompt

“Read my prospect's LinkedIn profile and pull their current role, recent posts, and company news before my call.”

You're already logged into LinkedIn. Your agent reads the profile tab you have open — no LinkedIn API, no scraping blocks, no rate limits. Just real data from your live session.

scripts/cdp.mjs list

Find your LinkedIn tab targetId

scripts/cdp.mjs snap <target>

Get accessibility tree of the profile page

scripts/cdp.mjs html <target> ".pv-top-card"

Extract structured profile card HTML

Extract Data from Your CRM

GTM / RevOps

Agent Prompt

“Pull the top 10 open opportunities from my HubSpot pipeline and summarize deal stage, size, and last activity.”

Most CRM scraping is blocked or requires API keys with complex setup. With Chrome CDP, your agent reads your HubSpot dashboard exactly as you see it — no API, no config.

scripts/cdp.mjs list

Find your HubSpot tab

scripts/cdp.mjs shot <target>

Screenshot the pipeline view

scripts/cdp.mjs snap <target>

Extract deal data via accessibility tree

Monitor Outbound Campaigns Live

GTM / Outbound

Agent Prompt

“Check my Instantly campaign stats right now — open rates, reply rates, bounces — and flag anything that looks off.”

Your agent reads your Instantly or Smartlead dashboard in real time. No API polling, no export CSV, no waiting — it sees exactly what you see on screen.

scripts/cdp.mjs snap <target>

Snapshot the campaign stats table

scripts/cdp.mjs eval <target> "document.querySelector('.stats-table').innerText"

Extract stats as text

scripts/cdp.mjs shot <target>

Capture a screenshot for visual reference

Automated Form Filling & Clicks

GTM / Operations

Agent Prompt

“Fill in this contact form on our partner portal and submit it — I'm already logged in.”

Agent clicks into fields, types text, and submits forms in tools you're authenticated to. No cookies to steal, no session to set up — it uses your live session.

scripts/cdp.mjs click <target> "#first-name"

Focus the first name field

scripts/cdp.mjs type <target> "Brandon"

Type the value (works in iframes too)

scripts/cdp.mjs click <target> "button[type=submit]"

Submit the form

Authenticated API Docs Extraction

Technical

Agent Prompt

“Crawl our internal Notion workspace and extract the GTM runbook into structured markdown.”

Internal tools, Notion, Confluence, private GitHub repos — anything you're logged into. The agent reads it through your existing authenticated session via the CDP WebSocket.

scripts/cdp.mjs list

Find the Notion tab

scripts/cdp.mjs html <target>

Extract the page content as HTML

scripts/cdp.mjs nav <target> https://notion.so/next-page

Navigate to next page and repeat

Debug & Inspect Live Pages

Technical

Agent Prompt

“Take a screenshot of what the agent is seeing, inspect the accessibility tree, and identify why the submit button isn't clickable.”

Full DevTools access from the terminal — screenshots at native resolution, accessibility tree, network timing, and raw CDP commands. The complete browser debugging toolkit.

scripts/cdp.mjs shot <target> /tmp/debug.png

Screenshot at native resolution with DPR

scripts/cdp.mjs net <target>

Check network resource timing

scripts/cdp.mjs evalraw <target> "DOM.getDocument" '{}'

Raw CDP command passthrough

Commands Reference

All commands use scripts/cdp.mjs. The <target> is a unique prefix of the targetId shown by list.

chrome-cdp commands

scripts/cdp.mjs listList every open Chrome tab with targetId, title, and URL

scripts/cdp.mjs shot <target> [file]Screenshot the viewport → /tmp/screenshot.png (default). Prints DPR for coordinate mapping.

scripts/cdp.mjs snap <target>Accessibility tree snapshot — compact, semantic. Preferred over raw HTML for page structure.

scripts/cdp.mjs html <target> [".selector"]Full page HTML or scoped to a CSS selector.

scripts/cdp.mjs eval <target> "expression"Run JavaScript in the page context and return the result.

scripts/cdp.mjs nav <target> https://...Navigate the tab to a URL and wait for page load.

scripts/cdp.mjs click <target> "selector"Click an element by CSS selector.

scripts/cdp.mjs clickxy <target> <x> <y>Click at CSS pixel coordinates (divide screenshot pixel coords by DPR).

scripts/cdp.mjs type <target> "text"Type at the focused element. Works in cross-origin iframes where eval cannot reach.

scripts/cdp.mjs loadall <target> "selector" [ms]Click a "Load more" button repeatedly until it disappears. Default 1500ms between clicks.

scripts/cdp.mjs net <target>Network resource timing entries — inspect what loaded and how long it took.

scripts/cdp.mjs evalraw <target> <method> [json]Raw CDP command passthrough — send any DevTools Protocol method directly.

scripts/cdp.mjs stop [target]Stop one or all background daemons.

Coordinates tip: shot saves images at native resolution (CSS pixels × DPR). CDP events like clickxy take CSS pixels. Convert: CSS px = screenshot px / DPR. The shot command prints the DPR so you always know.

How It Works (Technical)

For the technically curious — what’s happening under the hood.

Direct CDP WebSocket

Connects to Chrome’s remote debugging WebSocket at localhost:9222 — no Puppeteer, no Playwright, no intermediary layer. Pure protocol, minimal overhead.

Persistent Daemon Per Tab

On first access to a tab, a lightweight background daemon is spawned to hold the session open. Chrome’s “Allow debugging” modal fires once — all subsequent commands reuse the daemon. Daemons auto-exit after 20 min of inactivity.

Cross-Origin Iframe Support

The type command uses Input.insertText via CDP directly, bypassing JavaScript sandbox restrictions. This works in embedded iframes where eval cannot reach — critical for forms inside third-party widgets.

Zero Dependencies

Uses Node.js 22+ built-in WebSocket — no npm install needed. Just clone, enable the toggle in Chrome, and run. That’s why it works as a drop-in skill for any agent.

100+ Tab Reliability

Tools built on Puppeteer often time out during target enumeration with many tabs open. Because chrome-cdp connects per-tab and holds daemons, it handles 100+ open tabs reliably — matching real power-user workflows.

Raw CDP Passthrough

evalraw lets you send any Chrome DevTools Protocol method directly — DOM.getDocument, Network.getCookies, Performance.getMetrics. The full DevTools API surface from the terminal.

Where It Fits in Our Stack

We use Chrome CDP as the live-session browser layer in our OpenClaw agent stack — complementing Firecrawl for public web scraping with authenticated, real-time browser access.

Public Web

Firecrawl CLI

Scrape any public URL, crawl sites, web search

Authenticated / Live

Chrome CDP Skill

Your logged-in Chrome session — LinkedIn, CRM, internal tools

Structured APIs

CLI Tools

Instantly, HubSpot, Close CRM, Clay — JSON-first

Three layers. Any data surface your agent needs to reach.

Get OpenClaw deployed for your GTM motion

Chrome CDP is one layer of the full OpenClaw agent stack — browser access, outbound automation, CRM integration, and enrichment pipelines, built and managed for you as a service.

The discovery call is the first step of our engagement process — we scope your use case, map the stack, and determine fit before anything else.

View on GitHub

Agents-as-a-service starting at $5K/mo. Discovery call is how we determine fit.