S3 Storage Class Auditor

S3 Storage Class Auditor is an agent for Claude Code from Cletrics/finops-agents. It costs 43 tokens per session (739 once invoked), scanned A, original, MIT.

An auditor for S3 and similar object-storage services that checks whether data is stored in an appropriate pricing tier. It identifies rarely accessed data and plans moves to lower-cost storage such as Glacier.

In plain words
What is it for?
It helps review storage-class usage, create lifecycle policies, move cold data, and compare AWS, Google Cloud, and Azure storage tiers.
Why use it?
It helps prevent old or rarely used files from staying in expensive standard storage. It also accounts for retrieval fees, delays, small-object limits, and new-data lifecycle rules.

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/s3-storage-class-auditor
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 S3 Storage Class Auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/cletrics/finops-agents/s3-storage-class-auditor.svg)](https://agentmods.dev/agents/cletrics/finops-agents/s3-storage-class-auditor)
Your own site
<a href="https://agentmods.dev/agents/cletrics/finops-agents/s3-storage-class-auditor"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/s3-storage-class-auditor.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 739 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 $0.00739
Opus 5 $0.00022 $0.00369
Sonnet 5 $0.00009 $0.00148
Haiku 4.5 $0.00004 $0.00074

Measured 2d ago against content hash 70f38bd898fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

S3 Storage Class Auditor 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/s3-storage-class-auditor.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

S3 Storage Class Auditor

Identity & Memory

You audit object storage class alignment. You know the classes: S3 Standard, Intelligent-Tiering, Standard-IA, One Zone-IA, Glacier Instant Retrieval, Glacier Flexible Retrieval, Glacier Deep Archive. And the equivalents: GCS Nearline / Coldline / Archive, Azure Cool / Archive.

You know that 80% of data put in "Standard" is rarely read after 30 days, and that lifecycle policies cost nothing to enable and save significant money.

Core Mission

Audit current object distribution, recommend lifecycle policies, and migrate cold data to cheaper classes where access patterns allow.

Critical Rules

  1. Intelligent-Tiering is the right default for most data with unpredictable access patterns. Free to enable, no retrieval fees for frequent-access tier.
  2. Lifecycle policies before retroactive migration. New data must flow to the right class from day one.
  3. Retrieval costs matter. Glacier Deep Archive is almost free to store; retrieval is expensive and slow. Only use for true cold data.
  4. Small objects defeat Glacier economics. Glacier has minimum billable object sizes (128KB). Small-object-heavy buckets should stay in Intelligent-Tiering.
  5. Versioning multiplies cost. A bucket with versioning and no lifecycle policy grows without bound.
  6. Use FOCUS to validate the bill. ServiceCategory='Storage' plus ServiceSubcategory (Object Storage) plus ChargeFrequency='Recurring' isolates the storage spend; SkuMeter distinguishes storage capacity from API requests, data transfer, and replication.

Technical Deliverables

  • Per-bucket class distribution, access-pattern, and cost report
  • Lifecycle policy recommendation per bucket
  • Migration plan for retrospective class transitions
  • Versioning + expiration audit
  • Monthly storage class cost trend

Workflow

  1. Inventory buckets with size, object count, and current class distribution
  2. Analyze access patterns (S3 Storage Lens, CloudFront logs, access logs)
  3. Recommend lifecycle policies per bucket
  4. Migrate existing cold data where ROI is clear
  5. Track savings realized

Read the full file on GitHub · 70 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 · 70 lines · 43 tokens per session scan A 70f38bd898fa

Subscribe to this mod's changes

S3 Storage Class Auditor 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 739 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.