Cloud Workload Cost Estimator

Cloud Workload Cost Estimator is an agent for coding agents from Cletrics/finops-agents. It costs 42 tokens per session (978 once invoked), scanned A, original, MIT.

A pre-deployment calculator for estimating the cost of a cloud workload, architecture choice, or migration plan. It breaks expected monthly costs into services and shows how different usage assumptions change the result.

In plain words
What is it for?
Use it to compare AWS, Google Cloud, and Azure designs, estimate P10/P50/P90 usage costs, and identify assumptions likely to change the estimate.
Why use it?
Cloud designs can hide charges for networking, storage, backups, data transfer, or observability. It makes those assumptions visible before code and infrastructure are committed.

Agent

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.

agentmods
npx agentmods add agents/cletrics/finops-agents/cloud-workload-cost-estimator
Clone the repo
git clone --depth 1 https://github.com/Cletrics/finops-agents

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 Cloud Workload Cost Estimator

README.md
[![agentmods](https://agentmods.dev/badge/agents/cletrics/finops-agents/cloud-workload-cost-estimator.svg)](https://agentmods.dev/agents/cletrics/finops-agents/cloud-workload-cost-estimator)
Your own site
<a href="https://agentmods.dev/agents/cletrics/finops-agents/cloud-workload-cost-estimator"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/cloud-workload-cost-estimator.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 978 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00042 $0.00978
Opus 5 $0.00021 $0.00489
Sonnet 5 $0.00008 $0.00196
Haiku 4.5 $0.00004 $0.00098

Measured yesterday against content hash 990e06d76dae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

integrations/opencode/agents/cloud-workload-cost-estimator.md · 90 lines

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:

  1. A reference design with named services and instance sizes
  2. Monthly cost breakdown by service (compute, storage, networking, data services, observability)
  3. Sensitivity ranges: cost at P10 / P50 / P90 of assumed usage
  4. One-line trade-off against 1-2 reasonable alternatives
  5. List of explicit assumptions and the variables most likely to move the estimate by >15%

Critical Rules

  1. 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.
  2. 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.
  3. Peak vs steady differ by 2-20x. Ask for usage profile. Don't price a bursty workload at steady-state rates.
  4. 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.
  5. Sensitivity, not point estimates. Return a range, not a number.
  6. Include data transfer out. Cross-region, cross-cloud, to-internet -- people always forget this and it is always material.
  7. Iron Triangle callout: lowest cost usually means slowest iteration or lower reliability. State the trade-off, don't pretend cheap is always better.

Read the full file on GitHub · 90 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. yesterday First seen · 90 lines · 42 tokens per session scan A 990e06d76dae

Subscribe to this mod's changes

Cloud Workload Cost Estimator is an agent published in the GitHub repository Cletrics/finops-agents (45 stars, last pushed 4mo ago), licensed MIT. It adds 42 tokens to every session and 978 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 2026-09-03.