A set of skills for reading cloud and AI spending, explaining changes in a bill, estimating proposed infrastructure changes, and checking action policies. It uses the user's connected accounts and does not change resources.

It is for finding cost totals and drivers, investigating spikes, checking coding-agent or AI spend, estimating Terraform or Helm changes, and checking connected providers.

It replaces guesses about costs with figures from the connected cost tools and shows whether a proposed action needs review or is blocked.

cloud-costs — Skill for Claude Code by getnable/finopsmcp

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.

Any agent

npx skills add getnable/finopsmcp --skill cloud-costs

Clone the repo

git clone --depth 1 https://github.com/getnable/finopsmcp

Made for: Claude Code.

Or install nable, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 2 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/getnable/finopsmcp/cloud-costs/github.svg)](https://agentmods.dev/skills/getnable/finopsmcp/cloud-costs)

Your own site

<a href="https://agentmods.dev/skills/getnable/finopsmcp/cloud-costs"><img src="https://agentmods.dev/badge/skills/getnable/finopsmcp/cloud-costs/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/getnable/finopsmcp/cloud-costs"><img src="https://agentmods.dev/badge/skills/getnable/finopsmcp/cloud-costs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 633 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.

Model	Per session	Once invoked
Fable 5.1	$0.00061	$0.00633
Opus 5.5	$0.00024	$0.00253
Sonnet 5.5	$0.00012	$0.00127
Haiku 4.5	$0.00006	$0.00063

Measured 18d ago against content hash b836a58213aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cloud-costs 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 18d 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.

plugins/nable/skills/cloud-costs/SKILL.md · 32 lines

How it starts

The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cloud and AI costs with nable

nable is this plugin's local MCP server. It reads cost data with the user's own credentials and changes nothing. Answer with the numbers its tools return; never estimate a figure a tool could give you, and never invent one.

Which tool

What are we spending, and on what: get_cost_summary (total, top services, trend), get_top_cost_drivers.
Why the bill went up: explain_recent_cost_drivers (what moved in the last N days; root_cause: true for the deeper read), get_anomalies for spikes.
AI and LLM spend: get_llm_costs, get_llm_cost_by_model, get_ai_cost_attribution (by team, project or model).
Your own coding-agent budget: get_ai_budget_status (where this agent stands now), check_ai_budget (before a large task).
Before a change: estimate_terraform_cost or estimate_change_cost for a Terraform plan or helm diff, and check_action_policy to see whether the user's policy lets it proceed, needs review, or blocks it.
Nothing connected: list_connected_providers and check_connector_health, then point the user to /nable:connect.

Before you run anything that launches, resizes or deletes cloud resources, price it first and tell the user the monthly figure.

When the guard asks

This plugin also installs the nable guard, a hook that checks your Bash and MCP tool calls before they run. It stays silent on ordinary commands. On a costly launch, a destroy, a commitment purchase, or a change over budget, it pauses the call and shows the user a reason with the price, for example "~$X/mo at list" or "It cannot be undone".

When that happens:

Tell the user plainly what the command does and what it costs, using the guard's reason. Do not argue with it or play it down.
Let the user decide. If they decline, propose a cheaper or reversible alternative (a smaller instance, a plan before an apply, a stop instead of a terminate).
If the guard denies a command, it says why. Report that, and do not retry the same command.

Read the full file on GitHub · 32 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.

18d ago First seen · 32 lines · 61 tokens per session scan A b836a58213aa

Subscribe to this mod's changes

cloud-costs is a skill published in the GitHub repository getnable/finopsmcp (19 stars, last pushed 12d ago), licensed Apache-2.0. It adds 61 tokens to every session and 633 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-28.

Cloud Cost Optimization DevOps and cloud Finance and fintech ai aws azure claude cost

cloud-finops

Expert FinOps guidance for cloud, AI, and SaaS technology spend. Covers AI cost management, agentic FinOps, GenAI capacity planning, self-hosted vs managed inference, Anthropic billing, open-weight vendor APIs (DeepSeek, Qwen, Kimi, GLM), AWS (EC2, Bedrock, SageMaker, Savings Plans, CUR), Azure (reservations, AHB…

OptimNow/cloud-finops-skills · 253 tokens

cloud-cost-agent

Use when analyzing cloud spend, running a cost audit, or finding savings across AWS, Google Cloud, and Azure — rightsizing, idle resources, and commitment/reservation recommendations, per-provider or cross-cloud. Uses only native CLIs and recommendation services (Cost Explorer/Compute Optimizer/Cost Optimization Hub…

dautovri/cloud-cost-agent · 83 tokens

Commitment Discount Strategist

Cross-cloud commitment portfolio specialist. Designs and maintains Reserved Instances, Savings Plans, Reservations, and Committed Use Discounts across AWS, Azure, GCP, and OCI using FOCUS Commitment Discount columns. Maximizes effective discount without bleeding on unused commitment.

Cletrics/finops-agents · 55 tokens

cloud-costs