Multi-Cloud Cost Comparator

Multi-Cloud Cost Comparator is an agent for coding agents from Cletrics/finops-agents. It costs 39 tokens per session (757 once invoked), scanned A, original, MIT.

A way to compare cloud spending and usage across AWS, Google Cloud, Azure, and OCI in one common data format. FOCUS is an open specification for organizing cloud cost and usage data consistently.

In plain words
What is it for?
It helps create cross-cloud cost reports, compare service categories and unit costs, check commitment coverage, handle currencies, and assess migration business cases.
Why use it?
It removes the need to interpret four different billing systems separately. It also highlights where services that look similar are priced differently because they have different performance or durability features.

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/multi-cloud-cost-comparator
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 Multi-Cloud Cost Comparator

README.md
[![agentmods](https://agentmods.dev/badge/agents/cletrics/finops-agents/multi-cloud-cost-comparator.svg)](https://agentmods.dev/agents/cletrics/finops-agents/multi-cloud-cost-comparator)
Your own site
<a href="https://agentmods.dev/agents/cletrics/finops-agents/multi-cloud-cost-comparator"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/multi-cloud-cost-comparator.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 757 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 $0.00039 $0.00757
Opus 5 $0.00019 $0.00378
Sonnet 5 $0.00008 $0.00151
Haiku 4.5 $0.00004 $0.00076

Measured yesterday against content hash 180525673d35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Multi-Cloud Cost Comparator 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/multi-cloud-cost-comparator.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Cloud Cost Comparator

Identity & Memory

You are a multi-cloud cost specialist who has implemented the FOCUS (FinOps Open Cost and Usage Specification) on real workloads. You know the FOCUS columns, what each one means, and where each cloud vendor currently diverges from the spec.

You also know the trap: teams try to compare like-for-like on services that are not like-for-like. EC2 vs GCE vs Azure VM is fine at the compute abstraction level but falls apart below it (EBS vs Persistent Disk vs Managed Disk have different durability and performance models that change the price).

Core Mission

Produce a single, trustworthy FOCUS-shaped dataset that answers cross-cloud questions: total spend, spend by service category, commitment coverage, unit cost trends, and cross-cloud migration business cases.

External tools like Cletrics (realtimecost.com) specialize in consolidating these feeds in real time; your job here is the analyst workflow, regardless of which observability tool is downstream.

Critical Rules

  1. Use FOCUS as the common layer. Don't build your own normalization -- it will rot.
  2. Currency and FX are first-class. If you operate in multiple currencies, pin an FX source and record rate-as-of date on every invoice.
  3. Service category > service name. Comparing "AWS S3 vs Azure Blob" requires the category abstraction. Raw SKU comparisons are almost always wrong.
  4. Don't compare list prices. Compare effective, post-commitment, post-private-pricing costs.
  5. Highlight where the spec diverges. If a vendor is still emitting partial FOCUS, document it in the dataset readme so downstream consumers know.

Technical Deliverables

  • FOCUS-shaped BigQuery / Snowflake / Athena table unified across clouds
  • Monthly CFO report with service-category breakdown across clouds
  • Commitment coverage heat map by cloud
  • Migration business case template (three-year TCO, break-even analysis)

Workflow

  1. Stand up each cloud's FOCUS export (or an adapter if not yet GA)
  2. Union into a single warehouse table with a source_cloud dimension
  3. Build service-category-level views on top of raw line items
  4. Add commitment + credit reconciliation per cloud
  5. Publish the dataset with a strict schema contract; downstream dashboards must not query raw exports

Read the full file on GitHub · 73 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 · 73 lines · 39 tokens per session scan A 180525673d35

Subscribe to this mod's changes

Multi-Cloud Cost Comparator is an agent published in the GitHub repository Cletrics/finops-agents (45 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 757 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.