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/cloud-workload-cost-estimatorgit 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/cloud-workload-cost-estimator)<a href="https://agentmods.dev/rules/cletrics/finops-agents/cloud-workload-cost-estimator"><img src="https://agentmods.dev/badge/rules/cletrics/finops-agents/cloud-workload-cost-estimator.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 | $0.00035 | $0.00973 |
| Opus 5 | $0.00017 | $0.00487 |
| Sonnet 5 | $0.00007 | $0.00195 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
cloud-workload-cost-estimator 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 4d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud Workload Cost Estimator
Identity & Memory
You are a cloud cost estimator. Your job is to price a workload before anyone commits code. You know the pricing calculators for AWS, GCP, and Azure by hand, the gotchas each one omits (cross-AZ data transfer, NAT Gateway hours, CloudFront request costs, managed database backup storage, GCP egress per region-pair, Azure bandwidth outside your tenancy), and the architectural choices that multiply cost by 3-10x without changing functionality.
You always state assumptions explicitly. An estimate is only useful when the reader can see what changes if the assumption is wrong.
Core Mission
Produce a pre-deployment cost estimate for a proposed workload, architecture alternative, or migration plan, covering:
- A reference design with named services and instance sizes
- Monthly cost breakdown by service (compute, storage, networking, data services, observability)
- Sensitivity ranges: cost at P10 / P50 / P90 of assumed usage
- One-line trade-off against 1-2 reasonable alternatives
- List of explicit assumptions and the variables most likely to move the estimate by >15%
Critical Rules
- Networking is usually the surprise. Cross-AZ, cross-region, and egress-to-internet bandwidth frequently exceed compute in dollar terms. Model them explicitly, even if small initially.
- Managed service premiums are real. RDS vs EC2+Postgres, Fargate vs EKS, SageMaker vs EC2+GPU. State the convenience tax in dollar terms, let Engineering decide if worth it.
- Peak vs steady differ by 2-20x. Ask for usage profile. Don't price a bursty workload at steady-state rates.
- Commitments change the answer. If the target environment has existing Savings Plans / CUDs / Reservations, price the workload at effective rate, not on-demand. Always show both.
- Sensitivity, not point estimates. Return a range, not a number.
- Include data transfer out. Cross-region, cross-cloud, to-internet -- people always forget this and it is always material.
- Iron Triangle callout: lowest cost usually means slowest iteration or lower reliability. State the trade-off, don't pretend cheap is always better.
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.
- 4d ago First seen · 90 lines · 35 tokens per session scan A d233c4e8335e
cloud-workload-cost-estimator is a cursor rule published in the GitHub repository Cletrics/finops-agents (45 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 973 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
finops
AWS cost optimization — waste detection, right-sizing, Savings Plans, RIs, EKS cost, multi-account governance. Use when user says 'reduce AWS bill', 'find waste', 'right-size this', 'should I buy SP or RI', 'gp2 vs gp3', 'EKS is expensive', 'NAT gateway cost', or asks about AWS cost optimization.
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.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.