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 offer-designgit 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/offer-design)<a href="https://agentmods.dev/skills/lucasheriques/shipmate/offer-design"><img src="https://agentmods.dev/badge/skills/lucasheriques/shipmate/offer-design.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 | $0.00072 | $0.02108 |
| Opus 5 | $0.00036 | $0.01054 |
| Sonnet 5 | $0.00014 | $0.00422 |
| Haiku 4.5 | $0.00007 | $0.00211 |
Grade A, and why
offer-design 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 7d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Offer Design — Grand Slam Offer procedure
When to use
Run this when designing a new offer, repricing an existing one, or diagnosing why an offer isn't converting. The goal is an offer that cannot be price-compared — the buyer's decision becomes "this vs. nothing," not "this vs. the cheaper alternative." Work the phases in order; each depends on the previous.
The procedure
Phase 1 — Market check (before touching the offer)
Market > offer > persuasion. Verify all four before polishing anything:
- Massive pain — a desperate need, not a want. The pain is the pitch.
- Purchasing power — a separate test from pain; desperate-but-broke is not a market.
- Easy to target — the avatar gathers somewhere (lists, groups, channels, associations).
- Growing — tailwind, not headwind.
Then commit to one narrow avatar. Specificity alone multiplies acceptable price ("made exactly for me" raises perceived likelihood): the same substance addressed to a sharper niche supports ~5-100x pricing. Do not niche-hop; do not broaden until the niche is saturated.
Phase 2 — Value equation audit
Value = (Dream Outcome x Perceived Likelihood of Achievement) / (Time Delay x Effort & Sacrifice).
- Amateurs inflate the numerator (bigger claims). Pros crush the denominator: compress time-to-first-win and remove buyer effort before making any bigger promise.
- Engineer an emotional win as close to purchase as possible — the short-term experience keeps them in long enough to reach the long-term outcome.
- All four variables are perceived. Communicate every improvement or it doesn't exist (the dotted next-train map beat faster trains).
- Sell the vacation, not the flight: name and pitch the outcome, never the vehicle, membership, or feature list.
- If competing against free (open source, DIY, freemium): fast beats free — sell speed and certainty.
Phase 3 — Build the offer (five steps)
- Dream outcome. State the result the avatar actually wants, with a compressed timeframe.
- Problem list. Exhaustively list every problem they hit before, during, and after — in the sequence they'll meet them. For each activity, check four flavors: not worth it financially (dream outcome), won't work for me / can't stick with it / external factors (likelihood), too hard or confusing (effort), takes too long (time). Expect dozens. Any single unsolved perceived problem can kill the sale.
- Solutions. Reverse every problem into solution language: "how to X even if Y." Solve all of them — don't get romantic about how you want to solve them.
- Delivery vehicles. For each solution, brainstorm every possible delivery: 1-on-1 / small group / one-to-many; DIY / done-with-you / done-for-you; medium (live vs. recorded); response speed. Scoping tool: what would you deliver at 10x the price? How would you still guarantee success at 1/10th?
- Trim & stack. Score each vehicle cost-to-you vs. value-to-them. Kill high-cost/low-value and low-cost/low-value. Prioritize one-to-many assets (build once, deliver at ~zero marginal cost); reserve 1-on-1 for the biggest value adds. Bundle survivors into named mini-products, each with a justified value tag; the stack's total value must dwarf the price.
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.
- 7d ago First seen · 97 lines · 72 tokens per session scan A 1718f5c592e3
offer-design is a skill published in the GitHub repository lucasheriques/shipmate (4 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 2,108 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-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-roast
Get your startup plan roasted with data — Garry Tan style.
solo-playbook
Get a data-backed step-by-step playbook for any startup goal.