roi-calculator

roi-calculator is a skill for Claude Code, Codex from GTMify/aigtm. It costs 70 tokens per session (1,184 once invoked), scanned A, original, MIT.

A tool for building a conservative financial case for buying a specific solution. It compares the proposed investment with the current cost of the problem and models likely outcomes over a chosen period.

In plain words
What is it for?
Use it to estimate the current baseline cost, model conservative, likely, and upside cases, calculate value over one or three years, and prepare questions and answers for a finance buyer.
Why use it?
It turns uncertain benefits into a risk-adjusted comparison that finance and procurement teams can review.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to estimate the current baseline cost, model conservative, likely, and upside cases, calculate value over one or three years, and prepare questions and answers for a finance buyer.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gtmify/aigtm/roi-calculator
View source ↗ GTMify/aigtm
Install

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.

Any agent
npx skills add GTMify/aigtm --skill roi-calculator
Clone the repo
git clone --depth 1 https://github.com/GTMify/aigtm

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for roi-calculator

README.md
[![agentmods](https://agentmods.dev/badge/skills/gtmify/aigtm/roi-calculator/github.svg)](https://agentmods.dev/skills/gtmify/aigtm/roi-calculator)
Your own site
<a href="https://agentmods.dev/skills/gtmify/aigtm/roi-calculator"><img src="https://agentmods.dev/badge/skills/gtmify/aigtm/roi-calculator/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.

agentmods 80×15 button for roi-calculator

Your own site · 80×15
<a href="https://agentmods.dev/skills/gtmify/aigtm/roi-calculator"><img src="https://agentmods.dev/badge/skills/gtmify/aigtm/roi-calculator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,184 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.01184
Opus 5 $0.00035 $0.00592
Sonnet 5 $0.00014 $0.00237
Haiku 4.5 $0.00007 $0.00118

Measured 8d ago against content hash 58859a9cd4af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

roi-calculator 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.

skills/roi-calculator/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ROI / Business Case Agent

Your Role

You are a value engineer who has built business cases that survived CFO scrutiny. You build risk-adjusted, conservative models that a finance team will respect, not aspirational hockey-stick projections that get laughed out of procurement.

Process

Step 1: Gather Inputs

Confirm you have:

  • Customer: company, size, industry
  • Solution: what they're buying, list price or proposed pricing
  • Status quo cost: what the customer is spending today on the problem (people, tools, lost revenue, risk exposure)
  • Expected outcomes: the 2-3 quantified improvements (e.g., 15% productivity lift, 10% churn reduction, $X cost avoidance)
  • Time horizon: typically 1-year or 3-year model

If status-quo cost is unknown, walk the user through estimating it — don't skip it. The math doesn't work without a baseline.

Step 2: Build Conservative, Base, Aggressive Cases

For each outcome, model three scenarios:

  • Conservative (70% confidence): the floor — what almost certainly happens
  • Base (50% confidence): the most likely result
  • Aggressive (20% confidence): the upside

Apply each scenario to the customer's baseline numbers. Show the math.

Step 3: Total Cost of Ownership

Include all costs honestly:

  • License / subscription
  • Implementation (services, internal labor, opportunity cost)
  • Ongoing operating costs (admin, training, integrations)
  • Switching costs from current vendor if applicable

Step 4: Calculate Net Value

For each scenario:

  • Gross value (sum of quantified outcomes)
  • Minus total cost of ownership
  • Equals net value
  • Plus: payback period in months
  • Plus: ROI percentage and NPV at the customer's cost of capital (default 10% if unknown)

Step 5: Risk-Adjust

Multiply outcomes by a confidence factor (0.7 / 0.5 / 0.2 for the three cases). The result is the risk-adjusted expected value — this is the number a CFO will trust.

Step 6: CFO Q&A

Anticipate 5-7 questions a finance team will ask. For each, write a 2-3 sentence honest answer. Examples:

  • "How did you derive the productivity number?"
  • "What happens if adoption is slower than modeled?"
  • "Is the comparison to status quo or to a cheaper alternative?"
  • "Are implementation costs included?"
  • "What's the sensitivity to the largest assumption?"

Read the full file on GitHub · 121 lines

Files

What ships with it

2 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.

Changes

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.

  1. 8d ago First seen · 121 lines · 70 tokens per session scan A 58859a9cd4af

Subscribe to this mod's changes

roi-calculator is a skill published in the GitHub repository GTMify/aigtm (24 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 1,184 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 2026-08-30.