strategy-os: Skill for Claude Code

.claude/skills/stg-calculating-economics/SKILL.md

stg-calculating-economics is a skill for Claude Code from LeanOS-Technologies/strategy-os. It costs 48 tokens per session (2,293 once invoked), scanned A, original, MIT.

A unit-economics calculation method for estimating the financial performance of one customer or account. It covers customer lifetime value (LTV), acquisition cost (CAC), payback time, profit margins, operating costs, and different scenarios.

In plain words
What is it for?
Use it to combine pricing, market, competitor, solution, and channel assumptions; estimate revenue and costs; compare scenarios; and identify how long it takes to recover the cost of acquiring a customer.
Why use it?
It shows whether the proposed pricing and growth plan can make money, while keeping uncertain inputs as ranges instead of false precision. It also connects marketing spend and product costs to expected customer value.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

This is LeanOS-Technologies/strategy-os's own configuration. It tells Claude Code how to work on strategy-os itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything strategy-os configures →

Reuse

Borrowing it

Nothing to install: this file belongs to LeanOS-Technologies/strategy-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/LeanOS-Technologies/strategy-os/main/.claude/skills/stg-calculating-economics/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/LeanOS-Technologies/strategy-os

Made for: Claude Code.

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 stg-calculating-economics

README.md
[![agentmods](https://agentmods.dev/badge/skills/leanos-technologies/strategy-os/stg-calculating-economics/github.svg)](https://agentmods.dev/skills/leanos-technologies/strategy-os/stg-calculating-economics)
Your own site
<a href="https://agentmods.dev/skills/leanos-technologies/strategy-os/stg-calculating-economics"><img src="https://agentmods.dev/badge/skills/leanos-technologies/strategy-os/stg-calculating-economics/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 stg-calculating-economics

Your own site · 80×15
<a href="https://agentmods.dev/skills/leanos-technologies/strategy-os/stg-calculating-economics"><img src="https://agentmods.dev/badge/skills/leanos-technologies/strategy-os/stg-calculating-economics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,293 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.02293
Opus 5 $0.00024 $0.01146
Sonnet 5 $0.00010 $0.00459
Haiku 4.5 $0.00005 $0.00229

Measured 11d ago against content hash 53ec2553b4a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

stg-calculating-economics 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 11d 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.

.claude/skills/stg-calculating-economics/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Economics Calculation

Calculate unit economics with range-based estimates, integrated cost structure, and scenario analysis. Every input carries tier label; output inherits highest (weakest) tier. Merged from old str-calculating-economics and str-structuring-costs.

Procedure

Step 1: Gather Inputs with Tier Labels [S]

Read: pricing inputs (from stg-designing-pricing), market sizing (from stg-sizing-markets), competitive data (from stg-analyzing-competition), solution design (growth architecture).

Assemble input table:

Input Source Tier Value
ARPU Pricing tiers T2 (hypothesis) {range}
Gross margin Category benchmark, adjusted for COGS T2 {range}
Churn rate Benchmark for category + ACV range T2 (no customer data) {range}
S&M spend Channel strategy (stg-designing-channels) or cost structure estimate T2 {range}
Growth model Solution design T1 (a choice, not a prediction) {model}

Produce: input table with tier labels and source citations.

If channel strategy outputs are available (from stg-designing-channels), use per-channel CAC estimates and investment splits as the primary source for S&M spend and blended CAC inputs. This provides more rigorous CAC decomposition than freestanding S&M estimation.

Gate: inputs_gathered: bool -- all 5 inputs have values, tier labels, and sources.

  • Pass: Step 2.
  • Fail: For missing inputs, use category benchmarks with T2 label. If no benchmarks available, use SaaS median with T3 label and wide range.

Step 2: Calculate Core Metrics as Ranges [S]

Calculate for optimistic, base, and pessimistic input sets:

LTV = ARPU x Gross Margin x (1 / Monthly Churn Rate)

CAC = (S&M Spend + Allocated Overhead) / New Customers Acquired

LTV:CAC = LTV / CAC

Payback = CAC / (ARPU x Gross Margin)

Output tier = max(input tiers). If any input is T3, output is T3. If all inputs are T2, output is T2.

Produce: metric ranges across three scenarios.

Read the full file on GitHub · 198 lines

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. 11d ago First seen · 198 lines · 48 tokens per session scan A 53ec2553b4a2

Subscribe to this mod's changes

stg-calculating-economics is a skill published in the GitHub repository LeanOS-Technologies/strategy-os (37 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 2,293 once invoked, about $0.0002 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.

Related

Other skills, from other repositories