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 audit-offergit 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/audit-offer)<a href="https://agentmods.dev/skills/alexsmedile/hormozi-skills/audit-offer"><img src="https://agentmods.dev/badge/skills/alexsmedile/hormozi-skills/audit-offer/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/audit-offer"><img src="https://agentmods.dev/badge/skills/alexsmedile/hormozi-skills/audit-offer.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 | $0.00068 | $0.01376 |
| Opus 5.5 | $0.00027 | $0.00550 |
| Sonnet 5.5 | $0.00014 | $0.00275 |
| Haiku 4.5 | $0.00007 | $0.00138 |
Grade A, and why
audit-offer 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 — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Offer Audit (Weak Point Detector)
Purpose
Analyze any offer and identify what is stopping it from converting.
This skill:
- finds weak points
- diagnoses why the offer underperforms
- suggests clear, practical fixes
Goal: turn a weak or average offer into a strong, obvious buy.
When to Use
Activate this skill when:
- an offer is not selling
- conversions are low
- feedback is unclear or vague
- something feels “off” but you don’t know what
- you want to improve an existing offer
Inputs
This skill works with:
- an
OFFER.md - a sales page
- a pitch
- a product or service description
- pricing and value stack
- audience description
Core Outcome
The assistant produces:
- a full diagnosis of the offer
- a list of weak points
- severity level for each issue
- specific fixes
- prioritized action plan
Audit Framework (Hormozi-Based)
The audit is based on:
- Dream Outcome
- Perceived Likelihood
- Time Delay
- Effort & Sacrifice
Plus:
- market clarity
- offer clarity
- delivery model
- value stack
- pricing
- messaging
Assistant Behavior
1. Extract the offer
Identify:
- who it’s for
- what it promises
- how it works
- price
- format
Summarize:
This offer helps X achieve Y using Z.
2. Evaluate Dream Outcome
Check:
- is the result clear?
- is it specific?
- is it desirable?
- is it urgent?
Weak signs:
- vague outcomes (“grow”, “improve”)
- no measurable result
3. Evaluate Perceived Likelihood
Check:
- is there proof?
- is the path clear?
- is it believable?
Weak signs:
- no testimonials
- unclear process
- big promises without support
4. Evaluate Time Delay
Check:
- how fast results happen
- when the first win occurs
Weak signs:
- long delay before results
- no quick wins
5. Evaluate Effort & Sacrifice
Check:
- how hard it feels
- how many steps are required
- how much discipline is needed
Weak signs:
- too many steps
- unclear instructions
- heavy effort
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 · 370 lines · 68 tokens per session scan A f8f83580565f
audit-offer is a skill published in the GitHub repository alexsmedile/hormozi-skills (265 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 1,376 once invoked, about $0.0003 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.
audit-offer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| audit-offeralexsmedile/hormozi-skills | Skill | 265 | 1mo ago | MIT | A | 68 | Claude Code |
| lead-channel-optimizertourze/ai-infra | Skill | 5 | 7mo ago | none | A | 59 | Claude Code, Codex |
| admin-access-registersickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 49 | Claude Code |
| sop-writergenspark-ai/genoffice | Skill | 12k | yesterday | Apache-2.0 | A | 32 | Claude Code, Codex |
| executive-deckgenspark-ai/genoffice | Skill | 12k | yesterday | Apache-2.0 | A | 63 | Claude Code, Codex |
| ads-youtubeAgriciDaniel/claude-ads | Skill | 11k | 5d ago | MIT | A | 84 | Claude Code |
| ads-launchAgriciDaniel/claude-ads | Skill | 11k | 5d ago | MIT | A | 45 | Claude Code |