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 lucasheriques/shipmate --skill money-modelsgit clone --depth 1 https://github.com/lucasheriques/shipmateWrote 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/lucasheriques/shipmate/money-models)<a href="https://agentmods.dev/skills/lucasheriques/shipmate/money-models"><img src="https://agentmods.dev/badge/skills/lucasheriques/shipmate/money-models.svg" alt="Measured on agentmods" 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 | $0.00076 | $0.02344 |
| Opus 5 | $0.00038 | $0.01172 |
| Sonnet 5 | $0.00015 | $0.00469 |
| Haiku 4.5 | $0.00008 | $0.00234 |
Grade A, and why
money-models 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 8d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Money Models: design the sequence, not the sale
When to use
Use when the question is "what do we sell, in what order, and how do they pay" — pricing ladders, trials, payment plans, membership billing, or making acquisition self-funding. The unit of design is a sequence of offers, not a single price. A business with one offer isn't a business; it's a front end.
The procedure
Phase 0 — Baseline the cash math. Write down the current offer sequence as-is (most businesses have exactly one step). Compute 30-day gross profit per new customer vs. CAC + cost to serve. The governing constraint: 30-day gross profit per new customer must exceed acquisition + service cost — ideally 2x+, so one customer's profit funds the next on credit-card float. If the ratio is under 1, fix Phases 1–3 before touching continuity. Every decision below is a lever to hit this number.
Phase 1 — Attraction offer (strangers -> customers). Its job is to fund acquisition, not to be the profit. Pick ONE from the catalog below, matched to the business; advertise the benefit, not the features. "Free," "discount," and "$1" are interchangeable frames on one continuum — free is a 100% discount. Discounted offers get fewer leads but higher show-up rates than free; switch to paid-something when no-shows are costly.
Phase 2 — Upsell (spend more). Ask: what problem does the first purchase create? Sell that solution the moment the problem appears — wrong thing, wrong time, or wrong way is why upsells fail. Offer the highest-profit upsell first. BAMFAM: never end an interaction without booking the next one and its reason. Charge for guarantees/warranties (+5–50%) instead of gifting them. Hint at the next offer before selling it.
Phase 3 — Downsell (turn no into yes). A no is to this offer, not all offers. Two levers only: change what they get (feature downsell) or how they pay (payment plan) — never drop the price on the same thing; that reprices the product in public and destroys trust. Downsells are trades: give something, get something. Alternate feature and payment-plan downsells; temperature-check ("1–10, how bad do you want this?" — 8+ keep going, 7 or below ask "why not a 10?" and change the offer). Close each concession with "fair enough?"
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.
- 8d ago First seen · 80 lines · 76 tokens per session scan A f33cad394d4f
money-models is a skill published in the GitHub repository lucasheriques/shipmate (4 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 2,344 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 2026-08-31.
Other skills, from other repositories
solo-failures
Understand why startups fail — the most common failure modes, anti-patterns, and how to avoid them, backed by data from 101 founder interviews.
solo-roast
Get your startup plan roasted with data — Garry Tan style.
solo-analyze
Evaluate a startup idea against real patterns from 101 founder interviews.
solo-growth
Get data-backed growth and marketing recommendations for your business.
solo-patterns
Browse and search the startup pattern database (11 categories, 80+ patterns).
solo-playbook
Get a data-backed step-by-step playbook for any startup goal.