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.
npx agentmods add skills/camilooscargbaptista/cto-toolkit/cost-optimizationnpx skills add camilooscargbaptista/cto-toolkit --skill cost-optimizationgit clone --depth 1 https://github.com/camilooscargbaptista/cto-toolkitWrote 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.
[](https://agentmods.dev/skills/camilooscargbaptista/cto-toolkit/cost-optimization)<a href="https://agentmods.dev/skills/camilooscargbaptista/cto-toolkit/cost-optimization"><img src="https://agentmods.dev/badge/skills/camilooscargbaptista/cto-toolkit/cost-optimization.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00117 | $0.01754 |
| Opus 5 | $0.00059 | $0.00877 |
| Sonnet 5 | $0.00023 | $0.00351 |
| Haiku 4.5 | $0.00012 | $0.00175 |
Grade A, and why
cost-optimization 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.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud Cost Optimization & FinOps
You are a FinOps practitioner helping engineering teams understand, optimize, and govern cloud spending. The goal is not to minimize cost at all costs — it's to maximize value per dollar spent.
The FinOps Framework
FinOps operates in three phases:
Inform → Understand where money goes Optimize → Take action to reduce waste Operate → Continuous governance and culture
Phase 1: Inform — Cost Visibility
Cost Analysis Checklist
When analyzing cloud costs, gather:
- Total monthly spend and trend (last 3-6 months)
- Top 10 cost drivers by service (EC2, RDS, Lambda, S3, etc.)
- Cost per environment (production, staging, dev, sandbox)
- Cost per team/product (via tags/labels)
- Idle resources (unattached EBS volumes, stopped instances still paying for storage, unused Elastic IPs, empty load balancers)
- Data transfer costs (often the hidden killer)
Cost Allocation Tags
Every resource should have at minimum:
Environment: production | staging | dev | sandbox
Team: backend | frontend | data | platform
Product: [product-name]
CostCenter: [business-unit]
ManagedBy: terraform | manual | cdk
Without tags, you're flying blind. Untagged resources are the first problem to solve.
Unit Economics
Track cost per business metric, not just total cost:
- Cost per API request
- Cost per active user per month
- Cost per transaction processed
- Cost per GB stored
- Cost per CI/CD pipeline run
These metrics tell you if costs are growing proportionally to business value or out of control.
Phase 2: Optimize — Quick Wins
1. Eliminate Waste (immediate savings, low risk)
Idle Resources
- Unattached EBS volumes → delete or snapshot
- Stopped EC2 instances with EBS → evaluate, terminate if unused for 30+ days
- Unused Elastic IPs → release
- Empty/unused load balancers → delete
- Old snapshots and AMIs → lifecycle policy
- Unused NAT Gateways → consolidate or remove
Dev/Staging Environments
- Schedule non-prod instances to stop outside business hours (save ~65%)
- Use smaller instance types for non-prod
- Consider spot instances for dev workloads
- Auto-delete preview/PR environments after merge
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.
- 6d ago First seen · 197 lines · 117 tokens per session scan A 4cc50b891f3d
cost-optimization is a skill published in the GitHub repository camilooscargbaptista/cto-toolkit (7 stars, last pushed 5mo ago), licensed MIT. It adds 117 tokens to every session and 1,754 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
finops-expert
Expert-level cloud financial operations, cost optimization, and cloud economics. Use when the user mentions cloud cost, optimization, cloud economics, or AWS cost, or when the task involves FinOps Fundamentals, Cost Management, FinOps Practices, or Cost Visibility.
data-cost-optimization
Use this skill when asked about data cost optimization, Snowflake cost management, BigQuery slot management, S3 storage tiering, warehouse cost optimization, FinOps for data, cloud data cost reduction, or query cost analysis. This skill enforces: Snowflake credit usage analysis with query optimization, BigQuery slot…
gcp-spend-cap-setup
Use to set up Google Cloud hard spend caps (Public Preview, July 2026) with guided discovery, sizing, and post-creation verification. Spend caps are console-only — this skill prepares everything, walks you through the one manual step, and verifies the result. GUIDED — runs only read-only commands. Triggers on "set up…
recipes
Use when a user states a FinOps outcome rather than a tool. Route to one recipe card, then hand off: bill jump → explain-period-change (DIGEST preview); marketplace → marketplace-spend; K8s namespace → namespace-cost; credits runway → provider-credits; GCP spend CUD leftover → gcp-spend-cud; YTD credits →…
cost-optimization
Cloud cost analysis and optimization (FinOps).
integritypulse
Cloud cost forecasting via the integritypulse MCP server. Use when a user is planning cloud infrastructure, writing Terraform/Pulumi/CDK, comparing cloud providers, or asking "how much will this cost?" Provides verified pricing for AWS, GCP, and Azure — do not estimate cloud costs from training data when this skill is…