Agent skill · Audited from source

100m-leads

skill · getagentseal/founder-playbookMIT licenceAudited 20 Oct 2026 · source 5015fcf4cde3

★ 761pushed 13 days ago
✓SAFEGrade B · 89/100 · 20 Oct 2026 · 5015fcf
761repo stars · whole getagentseal/founder-playbook

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 5015fcf4cde3 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Builds lead generation systems using Alex Hormozi's Core Four framework (warm outreach, content, cold outreach, paid ads), lead magnets, and Rule of 100. Use when designing customer acquisition, scaling advertising,…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “100m-leads (getagentseal/founder-playbook)”. Retrieved 20 Oct 2026. https://modelsatlas.com/skills/getagentseal/100m-leads

Trust audit

Audit 0.4.1 · source read 20 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low1 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS1
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (1)

INFOPrompt injectionprompt.authority_framing · examples.md:238
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
Format: 14-day full access OR 3 free uses OR 1 unit of value
Why
No further detail recorded for this rule.
Fix
—

Audit 0.4.1 · source sha 5015fcf4cde3 · 20 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publishergetagentseal GitHub organizationOwner of the repository this skill is read from
  • Source foldergetagentseal/founder-playbook/skills/100m-leadsThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict5015fcf4cde3A new audit runs when the source changes
  • Repository statusNot archivedLast push 13 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Builds lead generation systems using Alex Hormozi's Core Four framework (warm outreach, content, cold outreach, paid ads), lead magnets, and Rule of 100. Use when designing customer acquisition, scaling advertising,…

---
name: "100m-leads"
description: Builds lead generation systems using Alex Hormozi's Core Four framework (warm outreach, content, cold outreach, paid ads), lead magnets, and Rule of 100. Use when designing customer acquisition, scaling advertising, choosing marketing channels for revenue stage, building referral programs, or fixing low lead flow. Covers lead magnets, LTGP:CAC math, More Better New scaling, and Lead Getters (referrals, employees, agencies, affiliates).
---

> **Note:** This skill is independent analysis and commentary, not a reproduction of the original text. It synthesizes the book's core ideas with modern startup practice, surfaces where frameworks are outdated or incomplete, and integrates perspectives from adjacent disciplines. For the full argument and context, read the original book.


# $100M Leads

> "How to get strangers to want to buy your stuff" - Alex Hormozi

## The Core Four Framework

All advertising falls into 4 categories on two axes:

| | Warm Audience (knows you) | Cold Audience (strangers) |
|---|---|---|
| **1-to-1** | Warm Outreach | Cold Outreach |
| **1-to-Many** | Post Free Content | Run Paid Ads |

**Rule:** Master ONE before adding another. Don't spread thin across all four.

## Decision Tree

```
Do you have 10 paying customers?
├─ NO → Warm outreach until you do
└─ YES → Pick based on resources:
         ├─ Have time, no money → Cold outreach or Content
         ├─ Have money, no time → Paid ads
         └─ Have both → Cold outreach + Content
```

```
Already running channels?
├─ Spreading across 4 → Cut to 1, master it
├─ One channel profitable → More Better New
├─ Hit personal capacity → Hire someone to run it
└─ Multiple channels profitable → Add lead getters (referrals/affiliates)
```

## Lead Definitions

| Term | Definition |
|------|------------|
| **Lead** | A person you can contact |
| **Engaged Lead** | A person who has shown interest |
| **Qualified Lead** | A person who can afford and is likely to buy |

Quality > volume. An engaged lead is worth many cold names.

## Lead Magnets

A lead magnet is a complete solution to a narrow problem. Free or low-cost. Reveals a bigger problem your core offer solves.

### 7 Steps to Create

1. **Pick the problem** - Narrow, meaningful, leads to your core offer
2. **Figure out the solution** - One of three types below
3. **Choose delivery method** - PDF, video, tool, trial
4. **Test the name** - Name matters more than content
5. **Make it easy to consume** - Under 10 minutes ideally
6. **Make it darn good** - Good enough to charge for
7. **Make it easy to ask for more** - Clear next step to your offer

### 3 Types of Lead Magnets

| Type | How It Works | Example |
|------|--------------|---------|
| **Reveal Problems** | Diagnosis showing problem they didn't know they had | Website speed test, posture analysis |
| **Samples/Trials** | Limited access to your core offer | Free month, 3 free uses, demo |
| **One Step of Multi-Step** | Solve step 1 of a 5-step process | Free template, calculator, checklist |

The lead magnet solves one problem, which reveals the NEXT problem your core offer solves.

## The Core Four Channels (Summary)

Detailed playbooks in **[frameworks.md](frameworks.md)**.

### 1. Warm Outreach (Free, 1-to-1)
Start here. Phone contacts, email, social media followers = your warm list. Personalize. Use ACA framework (Acknowledge, Compliment, Ask). Ask for referrals.

### 2. Post Free Content (Free, 1-to-Many)
Build an audience. Hook-Retain-Reward. Give-Give-Give-Ask pattern. Don't pitch until they reach out.

### 3. Cold Outreach (Free/Cheap, 1-to-1)
Reach strangers. Personalization + Big Fast Value. Volume + multi-channel follow-up. List of 1000+ to start.

### 4. Run Paid Ads (Paid, 1-to-Many)
Trade money for attention at scale. Three phases: Track Money → Lose Money → Print Money. Use lookalike + factor targeting. Detailed math in **[paid-ads.md](paid-ads.md)**.

## The Money Math: LTGP:CAC

**LTGP** = Lifetime Gross Profit (total customer revenue minus delivery cost)
**CAC** = Cost to Acquire Customer

| Ratio | Meaning |
|-------|---------|
| <3:1 | Struggling to scale |
| 3:1 | Minimum viable |
| >3:1 | Ready to scale |

**Note:** Hormozi uses LTGP (Lifetime Gross Profit) specifically, not LTV. The distinction matters - LTGP excludes delivery cost.

If CAC is above 3x industry average, fix ads. If below, fix the business model (increase LTGP).

### Client Financed Acquisition

Break even on acquisition cost in ~30 days = unlimited scaling. If a customer pays you back in 30 days, you can fund acquisition with a credit card and reinvest infinitely.

How: upsells, order bumps, higher upfront pricing - anything to collect more cash faster.

## Rule of 100

Every day, do ONE of:
- 100 cold outreach attempts (calls, emails, DMs)
- 100 minutes creating content
- 100 minutes of paid ad work
- $100 spent on ads

Minimum viable daily advertising. Do this for 100 days before concluding "it doesn't work."

### Open to Goal (Advanced)
Work until you hit a specific OUTCOME, not a number of inputs.

| Stage | Use |
|-------|-----|
| Starting | Rule of 100 (effort-based) |
| Scaling | Open to Goal (outcome-based) |

## More Better New (Scaling)

Framework for scaling what works:

1. **MORE** - Do 10x what you're currently doing. What's stopping you?
2. **BETTER** - Find the constraint, fix it, do more again
3. **NEW** - Only after exhausting more+better:
   - New placements on same platform
   - Same placements on new platform
   - New placements on new platform
   - Add another Core Four activity

"More" and "better" work together. Do more until it breaks, then make it better, then do more again.

## Lead Getters (Others Get Leads For You)

Once YOU can get leads, get others to do it.

### 4 Types

| Type | Who | How |
|------|-----|-----|
| **Customers** | Existing buyers | Referral program |
| **Employees** | Your team | Train + incentivize |
| **Agencies** | Marketing firms | Pay for r

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 5015fcf

Download folder ↗
git clone https://github.com/getagentseal/founder-playbook
git -C founder-playbook checkout 5015fcf4cde3

The author documents no install command, so this uses the repository directly. Our verdict covers commit 5015fcf4cde3 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 5015fcf4cde3

Similar skills

Questions about 100m-leads

What does the 100m-leads skill do?
15 proven business books distilled into AI-native skills. Works with Claude Code, ChatGPT, Gemini, Cursor.
Is 100m-leads safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can 100m-leads access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (5015fcf4cde3), read on 2026-10-20. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.