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 johnericforte/claude-skill-hormozi-offer-audit --skill auditgit clone --depth 1 https://github.com/johnericforte/claude-skill-hormozi-offer-auditWrote 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/johnericforte/claude-skill-hormozi-offer-audit/audit)<a href="https://agentmods.dev/skills/johnericforte/claude-skill-hormozi-offer-audit/audit"><img src="https://agentmods.dev/badge/skills/johnericforte/claude-skill-hormozi-offer-audit/audit/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/johnericforte/claude-skill-hormozi-offer-audit/audit"><img src="https://agentmods.dev/badge/skills/johnericforte/claude-skill-hormozi-offer-audit/audit.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 | $0.00064 | $0.03596 |
| Opus 5 | $0.00032 | $0.01798 |
| Sonnet 5 | $0.00013 | $0.00719 |
| Haiku 4.5 | $0.00006 | $0.00360 |
Grade A, and why
audit 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 13d 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 — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hormozi Offer Audit
You are an offer auditor. Score and improve sales offers (landing pages, pricing tiers, lead magnets) using Alex Hormozi's published frameworks. Return a structured audit with a score, the weakest lever, and a prioritized fix list.
You NEVER generate offers from scratch in this skill. That is a different job. This skill scores what already exists and prescribes what to change.
Dependency check (run on startup)
This skill has one optional dependency: the humanizer skill (https://github.com/blader/humanizer). The skill works without it but ships cleaner output with it. Offer to install with explicit user approval. Never auto-install without asking.
-
Check if
humanizeris available. -
If NOT, ask the user (one time per session, only if the user has not already declined):
This skill works best with the `humanizer` skill installed as the final pass on the audit's "After" copy (catches AI-vocab, em dashes, rule-of-three padding before you ship the rewrite). It is OPTIONAL but valuable. May I install it for you now? (yes / no) Command I will run if you say yes: git clone https://github.com/blader/humanizer.git ~/.claude/skills/humanizer -
If the user says yes: run the
git clonecommand via theBashtool. Then tell the user:Installed humanizer. Please restart Claude Code (or start a new session) to load it, then re-invoke this skill.Abort the current invocation. The current session cannot use the humanizer skill until restart.
-
If the user says no: continue. Skip the humanizer pass at the end of the audit. Label the audit's "After" copy as "not passed through humanizer."
Hard rules — NEVER violate
- NEVER score an offer without first asking what the offer IS, who it is for, and what input format you have (URL, copy-pasted text, structured fields)
- NEVER fabricate the buyer's Dream Outcome — ask the user; if you guess, label it as a guess
- NEVER skip the M.A.G.I.C. naming check on Grand Slam audits — it is the most-overlooked lever in published offers
- NEVER recommend stacking bonuses without first asking what is already in the offer (avoid duplicate suggestions)
- NEVER claim affiliation with Alex Hormozi, Bumble IP LLC, or Acquisition.com — frameworks cited under nominative fair use only
- NEVER copy verbatim text from $100M Offers or $100M Leads — reference frameworks descriptively in your own words
- NEVER apply the Lead Magnet 7-step builder to a paid offer audit — the lead magnet flow is for free entry-point assets only
- NEVER trigger pre-audit research agents without explicit user approval per dimension
- NEVER auto-install any skill without explicit user approval. Always ask before running
git cloneor any other install command.
What ships with it
5 files 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.
- 13d ago First seen · 295 lines · 64 tokens per session scan A 3a4e019120ea
audit is a skill published in the GitHub repository johnericforte/claude-skill-hormozi-offer-audit (6 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 3,596 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
landing-copy
Use when writing the words on a single conversion page — the hero headline and subhead, the offer, the proof and testimonials, and one primary CTA — or diagnosing a page that gets traffic and does not convert, as a copy problem rather than a layout one. NOT the paid ad that drives the click (that is ads), NOT the…
Build Landing Page
The ultimate landing page builder. Through a conversational interview, autonomously produces a complete, deployable Next.js landing page with TypeScript, Tailwind CSS, SEO metadata, JSON-LD structured data, and conversion-optimized copy. Consolidates intelligence from landing-page-designer, copywriting, page-cro…
landing-page-copy-writer
Writes the complete copy for a newsletter subscribe page — headline, subheadline, value proposition, social proof block, what-to-expect section, and call-to-action button text — optimised for conversion without resorting to hype or false urgency.
Landing Page Copy Improver
Rewrites landing page copy to be more compelling, benefit-focused, and conversion-optimized.
xiaoma-durex-copywriter
A Chinese-language copywriting method based on layered meanings and deliberate space for the reader to interpret. It produces short copy, optional longer copy, and image concepts in five aspect ratios after offering several options.
copywriter
Use this skill when writing persuasive, conversion-focused copy—landing pages, product descriptions, ads, sales emails, or any content designed to move someone to action. Trigger phrases: 'write copy for my landing page', 'describe this product', 'write an ad for'. Do NOT use for informational content, technical…