What is cost-optimizer?

A cloud-spend review skill for AWS, Azure, or Google Cloud billing data. It produces a report identifying resources that may be idle, oversized, unnecessarily reserved, or wasting money through data transfer.

Use it for quarterly cloud-cost reviews, unexplained bill increases, reservation checks, or post-architecture cost validation.

It turns billing exports and usage data into a ranked list of possible savings, helping explain spending increases and validate architecture changes.

cost-optimizer — Skill for Claude Code and Codex by tahirraufkeeyu

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 tahirraufkeeyu/software-development-agent-stack--sdas --skill cost-optimizer

Clone the repo

git clone --depth 1 https://github.com/tahirraufkeeyu/software-development-agent-stack--sdas

Made for: Claude Code, Codex.

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/tahirraufkeeyu/software-development-agent-stack--sdas/cost-optimizer.svg)](https://agentmods.dev/skills/tahirraufkeeyu/software-development-agent-stack--sdas/cost-optimizer)

Your own site

<a href="https://agentmods.dev/skills/tahirraufkeeyu/software-development-agent-stack--sdas/cost-optimizer"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/cost-optimizer.svg" alt="Measured on agentmods" height="20"></a>

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,760 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	$0.00063	$0.02760
Opus 5	$0.00032	$0.01380
Sonnet 5	$0.00013	$0.00552
Haiku 4.5	$0.00006	$0.00276

Measured 8d ago against content hash 52bd3e6daf4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cost-optimizer 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 8d 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.

departments/devops/skills/cost-optimizer/SKILL.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to use

Quarterly finance review of cloud spend.
Finance flags a month-over-month jump and the owner is unknown.
Before renewing a reserved capacity commitment, to validate the shape is right.
After a significant architecture change, to confirm expected savings materialized.

Do not use for real-time cost alerting; that's a budget alarm, not this skill.

Inputs

cloud — aws | azure | gcp.
billing_export — path or URL to the billing export:
- AWS: Cost and Usage Report (CUR) in S3 (Parquet preferred).
- Azure: Cost Management export in storage (CSV/Parquet).
- GCP: BigQuery billing export dataset.
window — analysis window, typically last 30 or 90 days.
account_filter — optional list of account IDs / subscription IDs / project IDs.
tag_filter — optional filters (e.g. Env=prod, Owner=team-checkout).
min_savings_usd — threshold below which recommendations are skipped (default $50/mo).
utilization_source — where to pull CPU/memory/network: CloudWatch, Azure Monitor, GCP Cloud Monitoring, or Prometheus.

Outputs

A Markdown report with:
- Top-line spend and trend.
- Breakdown by service, env, and owner (when tags allow).
- Ranked recommendations table: resource, action, current $/mo, projected $/mo, effort.
- Quick-win section (anything recoverable within a day).
- Structural section (anything requiring refactor/capacity planning).
A CSV recommendations.csv for import into a ticketing system.
Optional: draft Jira/Linear tickets per recommendation.

Tool dependencies

AWS: aws CLI + Athena (or DuckDB over the CUR), aws ce for quick queries.
Azure: az CLI + Cost Management REST API, Azure Advisor REST API.
GCP: gcloud + BigQuery CLI, Recommender API.
duckdb for local analysis of Parquet/CSV exports.
jq, csvkit for post-processing.

Procedure

1. Snapshot current spend

AWS (Cost Explorer + CUR):

# Top-level trend
aws ce get-cost-and-usage \
  --time-period Start=2026-01-19,End=2026-04-19 \
  --granularity MONTHLY \
  --metrics UnblendedCost \
  --group-by Type=DIMENSION,Key=SERVICE \
  --output table

# CUR in Athena
athena-cli -d cur -q "
SELECT line_item_product_code, SUM(line_item_unblended_cost) AS cost
FROM cur.cur
WHERE line_item_usage_start_date >= DATE '2026-01-19'
GROUP BY 1 ORDER BY cost DESC LIMIT 20;"

Read the full file on GitHub · 241 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.

8d ago First seen · 241 lines · 63 tokens per session scan A 52bd3e6daf4a

Subscribe to this mod's changes

cost-optimizer is a skill published in the GitHub repository tahirraufkeeyu/software-development-agent-stack--sdas (18 stars, last pushed 4mo ago), licensed MIT. It adds 63 tokens to every session and 2,760 once invoked, about $0.0003 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.

Analytics and metrics Finance and fintech

sector-rotation

An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.

HKUDS/Vibe-Trading · 39 tokens

strategy-pivot-designer

Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.

tradermonty/claude-trading-skills · 28 tokens

twitter-reader

Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…

himself65/finance-skills · 161 tokens

cost-optimizer