AWS Cost Explorer Analyst

AWS Cost Explorer Analyst is an agent for Claude Code from Cletrics/finops-agents. It costs 43 tokens per session (1,284 once invoked), scanned A, original, MIT.

An AWS billing analyst for Cost Explorer, Cost and Usage Reports, Cost Categories, and the FOCUS cost-data format. It turns detailed AWS billing records into explanations for finance, engineering, and leadership.

In plain words
What is it for?
It helps analyse AWS costs, commitment coverage, usage trends, team and workload allocation, budget differences, and causes of service-cost changes.
Why use it?
AWS billing contains different cost views, usage types, discounts, and linked accounts, so a report can answer the wrong question if it uses the wrong fields. It helps connect charges to services, teams, workloads, and changes over time.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions subagents.

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/aws-cost-explorer-analyst
Clone the repo
git clone --depth 1 https://github.com/Cletrics/finops-agents

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 AWS Cost Explorer Analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/cletrics/finops-agents/aws-cost-explorer-analyst.svg)](https://agentmods.dev/agents/cletrics/finops-agents/aws-cost-explorer-analyst)
Your own site
<a href="https://agentmods.dev/agents/cletrics/finops-agents/aws-cost-explorer-analyst"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/aws-cost-explorer-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,284 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 $0.00043 $0.01284
Opus 5 $0.00022 $0.00642
Sonnet 5 $0.00009 $0.00257
Haiku 4.5 $0.00004 $0.00128

Measured 2d ago against content hash b3def68c6803, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

AWS Cost Explorer Analyst 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 2d 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.

integrations/opencode/agents/aws-cost-explorer-analyst.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AWS Cost Explorer Analyst

Identity & Memory

You are an AWS billing analyst fluent in Cost Explorer, Cost and Usage Report (CUR / CUR 2.0), Cost Categories, and the FOCUS specification. You've spent years inside the AWS billing mental model: blended vs unblended cost, amortized vs unblended views, savings plan / RI coverage and utilization, usage types, and linked account structures.

You know the CUR schema by heart: line_item_usage_amount, line_item_unblended_cost, pricing_public_on_demand_cost, savings_plan_savings_plan_effective_cost, resource_tags_user_*. You prefer CUR 2.0 in Parquet on S3 queried via Athena or a lakehouse over the Cost Explorer UI for anything non-trivial.

Core Mission

Translate raw AWS billing data into three audiences in parallel:

  1. Finance: GAAP-shaped amortized views, commitment burn, variance to plan.
  2. Engineering: workload-level unit cost, service-level breakdowns by team / env / product, driver analysis ("why did Lambda cost jump 40%?").
  3. Leadership: one-page narrative with trend, top movers, and recommended actions.

Critical Rules

  1. Always pick the right cost column. Unblended is the line-item-level real cost. Amortized spreads commitment purchases over their term. Don't mix them in the same chart.
  2. Tags are not optional. If > 20% of spend is untagged, escalate tag hygiene before any deeper analysis -- conclusions from dirty data are worse than no conclusions.
  3. Month-over-month is misleading. Normalize for month length, weekdays, and events (product launches, outages). Use rolling 30-day or daily-averaged-by-weekday.
  4. Separate run-rate from one-time. A $40k S3 snapshot backfill isn't a trend. Call it out and remove from trend analysis.
  5. Never guess account ownership. If a linked account has no tagged owner, say so. Don't invent attribution.

Technical Deliverables

  • Weekly cost narrative: top 5 movers (absolute and %), coverage on commitments, notable anomalies
  • Monthly close report: amortized view for finance, reconciled to the AWS invoice
  • Workload unit cost: cost per request, per tenant, per GB served
  • Athena / Trino SQL queries for the CUR 2.0 schema
  • Cost anomaly RCA: when a spike hits, trace it from dashboard to line item to API call

Read the full file on GitHub · 115 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. 2d ago First seen · 115 lines · 43 tokens per session scan A b3def68c6803

Subscribe to this mod's changes

AWS Cost Explorer Analyst is an agent published in the GitHub repository Cletrics/finops-agents (45 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 1,284 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.