A calculator for SaaS business metrics: customer lifetime value, customer acquisition cost payback, and the LTV/CAC ratio. SaaS means software sold as a service, usually through recurring payments.

It helps evaluate SaaS economics with an Excel workbook containing a verdict, sensitivity heatmap, and 36-month customer projection.

It compares several calculation methods and shows how assumptions such as churn, expansion, profit margin, and AI usage costs affect the result.

ltv-cac — Skill for Claude Code and Codex by NachoLafuente/5050-gtm

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 NachoLafuente/5050-gtm --skill ltv-cac

Clone the repo

git clone --depth 1 https://github.com/NachoLafuente/5050-gtm

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nacholafuente/5050-gtm/ltv-cac/github.svg)](https://agentmods.dev/skills/nacholafuente/5050-gtm/ltv-cac)

Your own site

<a href="https://agentmods.dev/skills/nacholafuente/5050-gtm/ltv-cac"><img src="https://agentmods.dev/badge/skills/nacholafuente/5050-gtm/ltv-cac/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nacholafuente/5050-gtm/ltv-cac"><img src="https://agentmods.dev/badge/skills/nacholafuente/5050-gtm/ltv-cac.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,673 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00113	$0.01673
Opus 5.5	$0.00045	$0.00669
Sonnet 5.5	$0.00023	$0.00335
Haiku 4.5	$0.00011	$0.00167

Measured 2mo ago against content hash c605ac171a64, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ltv-cac 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 2mo ago.

The scan reads SKILL.md. This mod also ships 4 executable files (ltv.py, output.py, run.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/ltv-cac/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LTV / CAC

Compute LTV, CAC payback, and LTV/CAC ratio with the four canonical formulas side by side. Anchor the verdict on Skok's 3:1 rule, layer on a16z NDR, Sequoia contribution-margin, and Tunguz AI-inference adjustments. Output a styled Excel workbook with a sensitivity heatmap and a 36-month synthetic cohort projection.

Step 1: Ask the user up to 6 inputs

Ask in order. The first 3 are required; the rest have defaults.

ARPU (monthly revenue per customer, $), e.g. 200
Customer churn rate (monthly, decimal), e.g. 0.03 for 3%/mo
CAC (customer acquisition cost, $), e.g. 1500
Net revenue expansion (monthly, decimal, optional), e.g. 0.005 for 0.5%/mo. Default 0. If they have NDR > 100%, this is positive.
Gross margin (decimal, optional), e.g. 0.78. Default 0.78 (78%, typical SaaS).
Inference / variable cost per customer per month ($, optional), only relevant for AI products. Default 0.

If the user is hesitant on inputs, suggest they start with the example fixture (examples/inputs.json).

Step 2: Run

python skills/ltv-cac/run.py \
  --arpu 200 \
  --churn 0.03 \
  --cac 1500 \
  --expansion 0.005 \
  --gross-margin 0.78 \
  --inference-cost 0 \
  --out-dir /tmp/ltv-cac-<client>-<date>

Or load all inputs from a JSON file:

python skills/ltv-cac/run.py --inputs path/to/inputs.json --out-dir /tmp/ltv-cac

Step 3: KPIs the user gets

Verdict sheet (the headline)

Skok basic LTV: ARPU × GM / churn (the canonical 3:1 reference)
NDR-adjusted LTV: ARPU × GM / (churn − expansion) (a16z framework)
AI-adjusted LTV: (ARPU × GM − inference) / churn (Tunguz inference erosion)
Sequoia contribution-margin LTV: combines the above two: (ARPU × GM − inference) / (churn − expansion)
CAC Payback: months to recover CAC from gross profit. Basic and AI-adjusted.
LTV/CAC ratio: color-coded: red <1, yellow 1-3, green 3-5, blue >5
Verdict statement: plain-English read with Skok 3:1 anchor + AI flag if inference erodes LTV >20%
NDR: monthly and annual-compounded
Citations: every formula tagged with its source

Read the full file on GitHub · 119 lines

Files

What ships with it

6 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.

2mo ago First seen · 119 lines · 113 tokens per session scan A c605ac171a64

Subscribe to this mod's changes

ltv-cac is a skill published in the GitHub repository NachoLafuente/5050-gtm (3 stars, last pushed 4mo ago), licensed MIT. It adds 113 tokens to every session and 1,673 once invoked, about $0.0005 per session on Opus 5.5. 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.

Analytics and metrics Claude Code Finance and fintech agent-skills attio claude-skills cohort-analysis crm

ltv-cac next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ltv-cacNachoLafuente/5050-gtm	Skill	3	4mo ago	MIT	A	113	Claude Code, Codex
ma-playbookalirezarezvani/claude-skills	Skill	29k	2d ago	MIT	A	29	Claude Code
comptableromainsimon/paperasse	Skill	2.6k	yesterday	MIT	A	153	Claude Code, Codex
syndicromainsimon/paperasse	Skill	2.6k	yesterday	MIT	A	204	Claude Code, Codex
agent-era-pricingmohitagw15856/pm-claude-skills	Skill	1.5k	today	MIT	A	108	Claude Code
collections-emailmohitagw15856/pm-claude-skills	Skill	1.5k	today	MIT	A	84	Claude Code
financial-statement-explainermohitagw15856/pm-claude-skills	Skill	1.5k	today	MIT	A	107	Claude Code