メニュー
SCALED Instagram lead scraper using Agent Browser. Scrapes hashtags + profiles for rich contact data including phone, email, location. 50-100+ leads per run.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | instagram-lead-scraper |
| description | SCALED Instagram lead scraper using Agent Browser. Scrapes hashtags + profiles for rich contact data including phone, email, location. 50-100+ leads per run. |
Pure agent-browser scraping for high-quality insurance agent leads with full contact details.
| Feature | Brave Search | Agent Browser |
|---|---|---|
| Speed | 50 leads in 30s | 50 leads in 10-15 min |
| Data Quality | Basic (username, bio, followers) | Rich (phone, email, location) |
| Source | Google search results | Instagram directly |
| Discovery | Limited | Hashtag pages = more leads |
| Contact Info | ❌ | ✅ Phone, Email extracted from bios |
Trade-off: Slower but way better data.
cd skills/instagram-lead-scraper/scripts
npx tsx scrape-agent-browser.ts 50
# No Google Drive upload
npx tsx scrape-agent-browser.ts 50 --no-drive
# Small test (3 leads, ~2 min)
npx tsx scrape-agent-browser.ts 3 --no-drive
1. OPEN hashtag page (e.g., #insuranceagent)
2. EXTRACT usernames from profile pictures
3. VISIT each profile page
4. SCRAPE: bio, followers, posts, email, phone, location
5. FILTER: only insurance-related profiles
6. SAVE to database + CSV
| Field | Example |
|---|---|
| username | @garcia_agency |
| full_name | The Garcia Agency |
| bio | American Family Insurance Auto | Home | Life... |
| followers | 4,375 |
| following | 493 |
| posts | 196 |
| teamgarcia@amfam.com | |
| 📞 phone | 470.854.2010 |
| 📍 location | Atlanta, GA |
| niche | auto_home / life_insurance / medicare |
| tags | has-email, has-phone, has-location |
The scraper rotates through these hashtags:
#insuranceagent#lifeinsuranceagent#finalexpense#finalexpenseagent#lifeinsurance#insurancebroker#medicareagent#healthinsuranceagent#insuranceagency#insurancesalesEach hashtag yields 10-15 profiles before moving to the next.
All fields are stored in the leads table:
{
source: 'instagram',
sourceType: 'profile',
externalId: 'garcia_agency', // username
externalUrl: 'https://instagram.com/garcia_agency',
fullName: 'The Garcia Agency',
email: 'teamgarcia@amfam.com',
phone: '470.854.2010',
location: 'Atlanta, GA',
bio: 'American Family Insurance...',
followers: 4375,
following: 493,
posts: 196,
leadType: 'agent',
niche: 'auto_home',
tags: 'has-email,has-phone,has-location',
status: 'new',
scrapedDate: '2026-02-02'
}
When you say:
import { scrapeInstagramAgentBrowser } from './scripts/scrape-agent-browser';
// Get 50 leads
const result = await scrapeInstagramAgentBrowser(50);
console.log(result);
// {
// savedLeads: [...],
// withEmail: 12,
// withPhone: 8,
// duration: 847, // seconds
// csvFile: '/path/to/file.csv'
// }
| Target | Time | Leads Found | With Contact Info |
|---|---|---|---|
| 10 | 2-3 min | 10-15 | 2-4 |
| 50 | 10-15 min | 50-70 | 10-20 |
| 100 | 20-30 min | 100-140 | 20-40 |
Note: Contact info (email/phone) appears in ~20-30% of bios.
npx tsx scrape-agent-browser.ts 50
npx tsx scrape-leads-scaled.ts 50
Recommendation: Use Agent Browser for quality, Brave Search for speed/quantity.
skills/instagram-lead-scraper/
├── SKILL.md # This file
├── scripts/
│ ├── scrape-agent-browser.ts # ⭐ MAIN: Agent browser scraper
│ ├── scrape-leads-scaled.ts # Brave search version
│ ├── scrape-leads.ts # Original (legacy)
│ ├── apify-scraper.js # Apify integration
│ └── save-to-drive.py # Drive helper
└── references/
├── hashtag-guide.md
└── quality-checklist.md
🤖 PURE AGENT-BROWSER INSTAGRAM SCRAPER
Target: 50 leads
Session: instagram-scraper
📊 Existing Instagram leads in DB: 299
🏷️ Scraping hashtag: #insuranceagent
Found 12 profiles
🔍 @garcia_agency... ✅ SAVED
The Garcia Agency | 4,375 followers
📧 teamgarcia@amfam.com
📞 470.854.2010
📍 Atlanta
🔍 @alexmillerofficial... ✅ SAVED
Alex Miller | 356K followers
Progress: 3/50
✅ COMPLETE: 50 leads | 12 emails | 8 phones | 12m 34s
Last updated: 2026-02-02 Version: 3.0 (Agent Browser Edition)
Remote development via GitHub API. Write code, create branches, commit files, and create PRs — all without a local clone. Pull tasks from Linear and implement them entirely through GitHub. Use when Ko wants features built remotely while working locally on other things.
Orchestrate Kiro CLI coding sessions via ACP. Spawns Kiro for coding tasks, monitors progress, creates branches and PRs when done. Handles both chat-initiated and Linear-spec tasks. Use when asked to code, build, or implement features.
Create Linear issues for coding workflows in the Suelo project. Auto-detects complexity to create full specs or quick tasks. Supports priority levels. Use when Ko asks to create tasks, issues, or linear tasks for coding work.
Test deployed Consuelo changes against Linear task requirements and PR verification criteria. Runs after successful Railway deploys to verify features work in production.
Remote development via GitHub API. Write code, create branches, commit files, and create PRs — all without a local clone. Pull tasks from Linear and implement them entirely through GitHub. Use when Ko wants features built remotely while working locally on other things.
Orchestrate Kiro CLI coding sessions via ACP. Spawns Kiro for coding tasks, monitors progress, creates branches and PRs when done. Handles both chat-initiated and Linear-spec tasks. Use when asked to code, build, or implement features.