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 alexsmedile/hormozi-skills --skill hormozi-hooksgit clone --depth 1 https://github.com/alexsmedile/hormozi-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/alexsmedile/hormozi-skills/hormozi-hooks)<a href="https://agentmods.dev/skills/alexsmedile/hormozi-skills/hormozi-hooks"><img src="https://agentmods.dev/badge/skills/alexsmedile/hormozi-skills/hormozi-hooks/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/alexsmedile/hormozi-skills/hormozi-hooks"><img src="https://agentmods.dev/badge/skills/alexsmedile/hormozi-skills/hormozi-hooks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00071 | $0.01575 |
| Opus 5 | $0.00036 | $0.00788 |
| Sonnet 5 | $0.00014 | $0.00315 |
| Haiku 4.5 | $0.00007 | $0.00158 |
Grade A, and why
hormozi-hooks 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 12d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- hormozi-hooks — 100% identical, 7 lines differ
How it starts
The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Hook Generator (Hormozi-Style)
Purpose
Create scroll-stopping hooks that attract the right people and make them want to keep reading.
This skill focuses on:
- grabbing attention fast
- promising a real outcome
- reducing friction immediately
- aligning hooks with the offer
Goal: make the right person think
“this is exactly for me”
When to Use
Activate this skill when:
- content is not getting attention
- hooks feel weak or generic
- you need ideas for posts, ads, emails
- you want higher retention
- you want hooks that attract buyers, not just views
Inputs
This skill works with:
- an
OFFER.md - a product or service
- a target audience
- a desired outcome
- a pain point
Core Outcome
The assistant produces:
- multiple high-performing hooks
- variations across different styles
- hooks aligned with pain + outcome
- hooks that reduce objections early
Core Principles (Hormozi Style)
- lead with outcome
- be specific (numbers, constraints)
- make it feel fast
- make it feel easy
- remove objections early
- call out a clear audience
- use contrast (fast vs slow, easy vs hard)
- add slight contrarian angle when useful
- keep it simple (one idea)
- promise real value
Core Formula
WHO + RESULT + SPEED/EASE + OBJECTION REMOVAL
Example:
• “Coaches: get 3 clients this week without ads”
⸻
Assistant Behavior
1. Extract core elements
Identify:
• WHO (target audience)
• RESULT (desired outcome)
• PAIN (what they struggle with)
• SPEED (how fast result can happen)
• EASE (how hard it feels)
• OBJECTIONS (what stops them)
Then simplify:
This helps X achieve Y fast, without Z.
⸻
2. Improve weak inputs
If vague, refine:
• “grow business” → “get 5 clients”
• “lose weight” → “lose 5kg in 30 days”
Make everything:
• specific
• measurable
• visual
⸻
3. Generate hooks by type
Create 3–5 variations for each type.
⸻
1. Outcome Hooks
Get [result]
⸻
2. Time-Based Hooks
Get [result] in [time]
⸻
3. Effort Reduction Hooks
Get [result] without [pain]
⸻
4. Callout Hooks
If you are [audience], this is for you
⸻
5. “How I” Hooks (Proof)
How I [achieved result] in [time]
⸻
6. Contrarian Hooks
[Common belief] is wrong
⸻
7. Pain Hooks
If you struggle with [pain], read this
⸻
8. Mechanism Hooks
The system that helps you [result]
⸻
9. Transformation Hooks
From [bad state] to [desired state]
⸻
10. Hybrid Hooks (Best performers)
Combine multiple elements:
WHO + RESULT + TIME + WITHOUT X
⸻
4. Inject speed and ease
Upgrade hooks by adding:
• time (“in 7 days”)
• effort reduction (“without ads”)
• simplicity (“even if you’re a beginner”)
⸻
5. Add objection handling
Include phrases like:
• “even if…”
• “without…”
• “no experience needed”
⸻
6. Add contrast
Improve clarity with:
• before vs after
• slow vs fast
• hard vs easy
⸻
7. Keep hooks simple
Rules:
• one idea per hook
• short sentences
• no fluff
• no complex wording
⸻
8. Select best hooks
Pick top 5–10 based on:
• clarity
• specificity
• relevance
• strength of outcome
⸻
9. Suggest use cases
For each top hook:
• best for Instagram
• best for ads
• best for email
• best for landing page
⸻
Output Format
# HOOKS.md
## 1. Core Message
- Audience:
- Result:
- Pain:
- Speed:
- Ease:
- Key objection:
---
## 2. Hook Variations
### Outcome Hooks
- Hook 1
- Hook 2
- Hook 3
### Time-Based Hooks
- Hook 1
- Hook 2
- Hook 3
### Effort Reduction Hooks
- Hook 1
- Hook 2
- Hook 3
### Callout Hooks
- Hook 1
- Hook 2
- Hook 3
### “How I” Hooks
- Hook 1
- Hook 2
- Hook 3
### Contrarian Hooks
- Hook 1
- Hook 2
- Hook 3
### Pain Hooks
- Hook 1
- Hook 2
- Hook 3
### Mechanism Hooks
- Hook 1
- Hook 2
- Hook 3
### Transformation Hooks
- Hook 1
- Hook 2
- Hook 3
### Hybrid Hooks (Best)
- Hook 1
- Hook 2
- Hook 3
---
## 3. Top Hooks
### Top 1
- Hook:
- Why it works:
### Top 2
- Hook:
- Why it works:
### Top 3
- Hook:
- Why it works:
---
## 4. Usage Suggestions
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 387 lines · 71 tokens per session scan A dbadba4e7850
hormozi-hooks is a skill published in the GitHub repository alexsmedile/hormozi-skills (156 stars, last pushed 13d ago), licensed MIT. It adds 71 tokens to every session and 1,575 once invoked, about $0.0004 per session on Opus 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.
Other skills, from other repositories
lead-channel-optimizer
Use this skill when users need to optimize lead generation channels, identify highest-ROI marketing activities, stop wasting time on low-performing channels, or systematize customer acquisition. Activates for lead gen strategy, marketing channel analysis, or "where should I focus" questions.
ads-linkedin
Audit LinkedIn Ads measurement, Insight Tag and conversions, professional audiences, lead generation, ABM, creative, bidding, budgets, pacing, automation, and policy. Use for LinkedIn Ads, Campaign Manager, Insight Tag, Lead Gen Forms, Thought Leader Ads, ABM campaigns, or B2B paid media.
ads-youtube
Audit YouTube Ads campaign setup, video and Demand Gen inventory, Shorts, in-stream, CTV, creative, audiences, brand safety, bidding, and measurement. Use for YouTube Ads, video ads, pre-roll, bumper ads, skippable in-stream, Shorts ads, Demand Gen, VAC migration, CTV, or YouTube campaign optimization.
ads-launch
Draft or explicitly apply a paid-ad campaign launch through Claude Ads capability-gated adapters. Use for campaign creation, launch plans, publishing ads, activating campaigns, uploading creative, or requests to push a campaign live.
bun-test-mocking
Use for mock functions in Bun tests, spyOn, mock.module, implementations, and test doubles.
api-response-optimization
Optimizes API performance through payload reduction, caching strategies, and compression techniques. Use when improving API response times, reducing bandwidth usage, or implementing efficient caching.