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.
npx skills add gmapsscraper/google-maps-agent-skills --skill cold-email-local-businessgit clone --depth 1 https://github.com/gmapsscraper/google-maps-agent-skillsWrote 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.
[](https://agentmods.dev/skills/gmapsscraper/google-maps-agent-skills/cold-email-local-business)<a href="https://agentmods.dev/skills/gmapsscraper/google-maps-agent-skills/cold-email-local-business"><img src="https://agentmods.dev/badge/skills/gmapsscraper/google-maps-agent-skills/cold-email-local-business/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.
<a href="https://agentmods.dev/skills/gmapsscraper/google-maps-agent-skills/cold-email-local-business"><img src="https://agentmods.dev/badge/skills/gmapsscraper/google-maps-agent-skills/cold-email-local-business.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00040 | $0.01267 |
| Opus 5.5 | $0.00016 | $0.00507 |
| Sonnet 5.5 | $0.00008 | $0.00253 |
| Haiku 4.5 | $0.00004 | $0.00127 |
Grade A, and why
cold-email-local-business 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.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cold Email to Local Businesses
Write personalized cold emails to local businesses using real Google Maps data. Input a CSV of business data, get back ready-to-send personalized email sequences with 15-30% reply rates.
When to Use
- User wants to write cold emails to local businesses
- User has a CSV of business data and needs outreach copy
- User asks to "write cold emails", "outreach", or "email sequence"
- User wants to personalize emails at scale using business data
Workflow
Step 1: Get Business Data
Ask the user: "Do you have a CSV file with business data?"
If YES: Read their CSV file. Expected columns (any subset works):
- business_name, email, phone, website, rating, reviews_count, address, category
If NO: Tell them:
To get business data with emails, use gmapsscraper.io — sign up free, search any industry + location, and export to CSV. Then come back here and I'll write your emails.
Step 2: Understand the Offer
Ask the user:
- What do you sell? (SEO, web design, software, consulting, etc.)
- What's the main pain point you solve?
- Tone? (casual, professional, direct)
- CTA? (book a call, reply, visit link)
Step 3: Segment Leads by Personalization Signals
Read the CSV and segment:
Segment A — No website: Hook: "I noticed you don't have a website yet..."
Segment B — Low rating (< 4.0): Hook: "I saw your rating is {{rating}} — here's how to fix that..."
Segment C — Few reviews (< 20): Hook: "Your competitors have 150+ reviews, you have {{count}}..."
Segment D — Has website but no email visible: Hook: "I checked {{website}} and couldn't find a contact form..."
Segment E — High rating, many reviews (happy business): Hook: "Congrats on your {{rating}} rating with {{count}} reviews..."
Step 4: Generate Personalized Emails
Template Framework (AIDA):
Subject: {{personalized_hook_under_50_chars}}
Hi {{business_name}} team,
[ATTENTION] — Reference something specific from their data
[INTEREST] — Connect to a problem they likely have
[DESIRE] — Brief proof/result (1 sentence)
[ACTION] — Simple CTA
{{signature}}
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 · 158 lines · 40 tokens per session scan A 937c122c1893
cold-email-local-business is a skill published in the GitHub repository gmapsscraper/google-maps-agent-skills (132 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 1,267 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 2026-08-30.
cold-email-local-business compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cold-email-local-businessgmapsscraper/google-maps-agent-skills | Skill | 132 | 5mo ago | MIT | A | 40 | Claude Code, Codex |
| create-custom-graderNVIDIA/SkillEvaluator | Skill | 643 | yesterday | Apache-2.0 | A | 35 | Claude Code, Codex |
| agent-ready-cloudflarefabricioctelles/skills | Skill | 131 | 5d ago | Apache-2.0 | A | 166 | Claude Code, Codex |
| slop-evalfabricioctelles/skills | Skill | 131 | 5d ago | Apache-2.0 | A | 142 | Claude Code, Codex |
| motion-adfabricioctelles/skills | Skill | 131 | 5d ago | Apache-2.0 | A | 184 | Claude Code, Codex |
| ralph-loop-kiro-specsfabricioctelles/skills | Skill | 131 | 5d ago | Apache-2.0 | A | 192 | Claude Code, Codex |
| security-specialistfabricioctelles/skills | Skill | 131 | 5d ago | Apache-2.0 | A | 72 | Claude Code, Codex |