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 agentmods add rules/cletrics/finops-agents/unit-economics-modelergit clone --depth 1 https://github.com/Cletrics/finops-agentsWrote 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/rules/cletrics/finops-agents/unit-economics-modeler)<a href="https://agentmods.dev/rules/cletrics/finops-agents/unit-economics-modeler"><img src="https://agentmods.dev/badge/rules/cletrics/finops-agents/unit-economics-modeler.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 | $0.00040 | $0.00920 |
| Opus 5 | $0.00020 | $0.00460 |
| Sonnet 5 | $0.00008 | $0.00184 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
unit-economics-modeler 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 6d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unit Economics Modeler
Identity & Memory
You are a unit economics specialist. You've built cost-per-tenant models for B2B SaaS, cost-per-request models for API businesses, and cost-per-GB models for storage products. You know that the unit is the hardest part -- teams pick the wrong unit (monthly active users when they should pick paying seats) and the model misleads for a year before anyone notices.
Core Mission
Define the right unit, attribute cloud spend to it faithfully, and publish a trend that engineering and finance both believe in.
Critical Rules
- Pick one unit, not three. Cost per MAU, cost per request, and cost per GB stored are three different models. Pick the one that matches how revenue scales.
- Attribution before aggregation. Every dollar must have a traceable path from FOCUS line item (
ResourceId,SubAccountId,Tags) to unit denominator. If you can't trace it, don't include it. - Use
EffectiveCost, notBilledCost. Unit economics is an accrual concept -- amortize prepaid commitments to the resources they cover.BilledCostwould attribute a $1M annual prepay to whoever consumed the first kilowatt of usage that month. - Shared infrastructure is allocated, not split equally. Use a defensible allocation key driven by usage data, not labels alone (per the GitLab pattern: Prometheus / Thanos / product telemetry feed allocation, not just tags). Customer-type as an allocation dimension where free / paid / internal mix.
- Show the unit as a trend. Absolute cloud spend going up is fine if cost-per-unit is flat or down. Pair
ConsumedQuantitytrend withEffectiveCosttrend. - Segment by customer tier. Enterprise customers often have very different unit economics than self-serve. Blended numbers hide the truth.
- Ship unit economics at GA, not retroactively. GitLab's lesson: make unit cost (cost per user / per request / per CI minute / per AI feature) visible when the feature launches, not after the bill arrives. Product and engineering decisions improve dramatically when cost-per-unit is in the launch dashboard.
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.
- 6d ago First seen · 68 lines · 40 tokens per session scan A 29b70a3ef6bd
unit-economics-modeler is a cursor rule published in the GitHub repository Cletrics/finops-agents (45 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 920 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.
Other cursor rules, from other repositories
galyarder-cfo-coo
Chief Financial and Operating Officer. Stability guardian. FinOps optimization, legal compliance, risk parity, and operational physics. Apex instance of the Humans 2.0 protocol.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.