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 swan-gtm/gtm-skills --skill roi-business-casegit clone --depth 1 https://github.com/swan-gtm/gtm-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/swan-gtm/gtm-skills/roi-business-case)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/roi-business-case"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/roi-business-case/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/swan-gtm/gtm-skills/roi-business-case"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/roi-business-case.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 | $0.00140 | $0.01750 |
| Opus 5 | $0.00070 | $0.00875 |
| Sonnet 5 | $0.00028 | $0.00350 |
| Haiku 4.5 | $0.00014 | $0.00175 |
Grade A, and why
roi-business-case 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 9d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose & When to Use
Single-number ROI cases lose credibility the moment finance sees them. A seller who shows one big, optimistic figure looks exactly like what they are — a seller. The buyer's internal reviewers discount it on sight, and the champion is stuck defending a number they didn't build and don't believe. Gal's fix is to model a range: worst, average, and best case. Showing the downside is what makes the upside believable. It signals you're impartial, it survives a skeptical finance review, and it pre-handles the "you're inflating this" objection before anyone raises it.
This skill builds that case. It takes the buyer's root-cause problem and baselines, models three scenarios with explicit assumptions, and produces a one-page business case the champion can carry into procurement and finance and actually defend.
Run this skill when any of these are true:
- The deal is heading into procurement, finance, or exec sign-off.
- The champion needs an internal justification for the spend.
- You've been showing (or are tempted to show) a single optimistic ROI number.
- Finance or a skeptic is likely to challenge your numbers.
- You want the AE to look like an honest advisor, not a pitch.
Do not build this on a problem whose impact you can't ground in the buyer's own baselines. A 3-scenario model built on invented inputs is just three fantasies instead of one. If you have no real baseline, the first task is getting it — see Step 1.
Procedure
Inputs you need
Collect these before modeling. Where a baseline or assumption is missing, do not fabricate it —
mark it [CONFIRM WITH BUYER] and make confirming it part of building the case with the champion.
- Deal context: company, champion (name + role), deal stage, price/investment, contract term.
- The root-cause problem you're solving — the mechanism behind the pain, in the buyer's words, ideally validated in discovery.
- Baseline metrics tied to that problem — current volume, time, headcount, cycle length, conversion, churn, cost — whatever the ROI hinges on. Use the buyer's numbers, not industry averages.
- The mechanism of improvement — how your solution changes each baseline metric.
- The investment — total cost over the term, so ROI and payback are real, not gross "value created."
- Who will scrutinize the case — finance, procurement, exec — and what they care about.
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.
- 9d ago First seen · 146 lines · 140 tokens per session scan A 015eeef4e7db
roi-business-case is a skill published in the GitHub repository swan-gtm/gtm-skills (150 stars, last pushed 2d ago), licensed MIT. It adds 140 tokens to every session and 1,750 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
financial-modeling
SaaS financial modeling for founders — operating model, runway, headcount, DCF valuation, consumption-based pricing models, cohort analysis, unit economics by segment, ARR bridge/build, 3-scenario forecasting, and board-ready financials. Use when building financial model, projecting runway, modeling fundraising…
fundraising-strategy
Complete fundraising strategy for B2B SaaS founders. Use when preparing to raise seed/Series A, deciding VC vs bootstrapped path, building pitch deck, running a fundraise process, evaluating term sheets, or planning fundraising timeline. Covers SAFE, priced rounds, and bootstrapper alternatives.
saas-metrics-calculator
Calculate and interpret SaaS metrics for founders: MRR, ARR, NRR, GRR, churn, CAC payback, LTV:CAC, burn multiple, Rule of 40, cohort retention, and scenario models. Use when building investor updates, dashboards, board materials, pricing decisions, or growth diagnostics.
roi-calculator
Build ROI calculators and business cases — 3-scenario projections (conservative, moderate, aggressive), payback period analysis, TCO comparison, assumption documentation, MEDDICC integration, value driver identification. Use when building ROI models, creating business cases, quantifying value for prospects, or…
business-insurance
Complete business insurance guide for SaaS founders — Errors & Omissions (E&O/Tech E&O), Cyber Liability, Directors & Officers (D&O), General Liability, Workers Compensation, Key Person, Employment Practices Liability (EPLI), and when each becomes necessary. Covers what triggers insurance needs (first enterprise…
equity-management
Complete equity management for SaaS founders — cap tables, 409A valuations, option pools (ISO vs NSO vs RSU), 83(b) elections, equity grants for employees/advisors/contractors, dilution modeling, secondary sales, and equity tools (Carta, Pulley, AngelList Equity). Use when setting up equity, granting options, planning…