cost-review

cost-review is a command for Claude Code from RoboFinSystems/robosystems. It costs 18 tokens per session (1,598 once invoked), scanned A, original, Apache-2.0.

A read-only review of AWS spending and usage that produces a cost report and savings plan ranked by potential dollar impact.

In plain words
What is it for?
Use it to inspect AWS billing and usage, calculate effective costs after credits or discounts, and identify savings opportunities for an account.
Why use it?
It shows where cloud money is going without changing resources, and separates cost analysis from actions such as deleting or resizing infrastructure.

Command for Claude Code

Written for Claude Code: installed under .claude/.

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 commands/robofinsystems/robosystems/cost-review
Clone the repo
git clone --depth 1 https://github.com/RoboFinSystems/robosystems

Made for: Claude Code.

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 cost-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/robofinsystems/robosystems/cost-review.svg)](https://agentmods.dev/commands/robofinsystems/robosystems/cost-review)
Your own site
<a href="https://agentmods.dev/commands/robofinsystems/robosystems/cost-review"><img src="https://agentmods.dev/badge/commands/robofinsystems/robosystems/cost-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,598 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 5.1 $0.00018 $0.01598
Opus 5 $0.00009 $0.00799
Sonnet 5 $0.00004 $0.00320
Haiku 4.5 $0.00002 $0.00160

Measured 6d ago against content hash 93965fe85900, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cost-review 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.

.claude/commands/cost-review.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.

Run a read-only AWS cost & usage review, then produce a cost report and a prioritized savings plan ranked by dollar impact. Pairs with the cost-analysis-cur-athena (the $ side) and prometheus-usage-amp-cli (the usage-driver side) runbooks in local/RoboSystems/runbooks/ for the account-specific query detail — read them alongside this file.

Scope & guardrails

  • Read-only. describe-* / list-* / get-*, Cost Explorer (ce), and Athena reads only; never get-secret-value. Any change (rightsizing, deleting an idle resource, buying a Savings Plan) needs explicit user confirmation, and destructive actions are the user's to run.
  • Output is business-confidential — never commit it. This skill (the methodology) is public-safe; its output is your unit economics and margins (effective cost net of SP/RI is literally the pricing number). Write reports to a git-ignored path (local/, scratchpad) or a private Artifact — never to the repo, and don't paste cost figures anywhere shareable.
  • Effective cost, not headline cost. Cost Explorer's AmortizedCost/NetAmortizedCost net out promotional credits, hiding structural cost. For unit economics, compute effective cost net of SP/RI discounts but BEFORE credits — via the CUR in Athena (see the runbook). CE is fine for a quick total; the CUR is the source of truth for structure.

Phase 1 — Cost overview & anomalies

aws ce get-cost-and-usage --time-period Start=<mo-start>,End=<mo-end> --granularity MONTHLY \
  --metrics UnblendedCost --group-by Type=DIMENSION,Key=SERVICE --region us-east-1
aws ce get-anomalies --date-interval StartDate=<start>,EndDate=<end> --region us-east-1

Then the effective-cost breakdown by component × environment from the CUR via Athena — port the canonical queries from the cost-analysis-cur-athena runbook (it holds the exact catalog/table/partitions).

Phase 2 — Rightsizing

Check enrollment first — every recommendation call returns OptInRequiredException when the account isn't registered, and that exception reads deceptively like "no opportunities found":

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. 6d ago First seen · 90 lines · 18 tokens per session scan A 93965fe85900

Subscribe to this mod's changes

cost-review is a command published in the GitHub repository RoboFinSystems/robosystems (24 stars, last pushed today), licensed Apache-2.0. It adds 18 tokens to every session and 1,598 once invoked, about $0.0001 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.