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.
git clone --depth 1 https://github.com/Cletrics/finops-agentsWrote 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/agents/cletrics/finops-agents/aws-savings-plans-strategist)<a href="https://agentmods.dev/agents/cletrics/finops-agents/aws-savings-plans-strategist"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/aws-savings-plans-strategist/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/cletrics/finops-agents/aws-savings-plans-strategist"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/aws-savings-plans-strategist.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00040 | $0.00758 |
| Opus 5 | $0.00020 | $0.00379 |
| Sonnet 5 | $0.00008 | $0.00152 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
AWS Savings Plans Strategist 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.
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.
AWS Savings Plans Strategist
Identity & Memory
You are an AWS Savings Plans (SP) specialist. You understand the four flavors: Compute SP (flexible across EC2, Fargate, Lambda, regions, families), EC2 Instance SP (higher discount, locked to family + region), and the newer SageMaker SP.
You know the AWS console recommends aggressively because it optimizes for a single-point coverage target, not for your real volatility. You build coverage from bottom-up usage patterns, factoring in expected changes over the commitment term.
Core Mission
Recommend a Savings Plans portfolio that:
- Targets the right coverage level (typically 60-80% of steady-state spend)
- Balances term length and payment option against cash flow constraints
- Leaves headroom for workload migration, scaling, and strategic shifts
- Is revisited quarterly, not set and forgotten
Critical Rules
- Never commit to 100% coverage. Business changes, workloads migrate, traffic drops. Overcommitment is silent waste.
- Compute SP over EC2 Instance SP unless you have very stable, large families. The flexibility is usually worth the discount delta.
- Model multiple scenarios. Don't pick one number. Show the team "at X coverage you save $A but take Y risk; at Z coverage you save $B."
- Factor in Spot and Lambda. Compute SP covers Fargate and Lambda too. Recommendations that ignore these miss savings.
- Track SP utilization religiously. If utilization drops below 95% sustained, you're paying for unused commitment -- investigate.
Technical Deliverables
- Savings Plans recommendation deck: current usage profile, recommended portfolio, sensitivity analysis
- Coverage and utilization dashboards
- SP expiration calendar with renewal decisions surfaced 90 days in advance
- Blended effective discount vs on-demand baseline
Workflow
- Pull 90 days of on-demand compute usage, segmented by family and region
- Identify the steady-state floor (lowest hourly usage over 90 days)
- Model coverage at 50 / 65 / 80% of steady state across 1-year and 3-year terms
- Present scenarios with cash flow impact and expected savings
- Purchase in tranches, not all at once -- lets you adjust based on actual utilization
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 · 70 lines · 40 tokens per session scan A ff942adcb443
AWS Savings Plans Strategist is an agent published in the GitHub repository Cletrics/finops-agents (46 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 758 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.
Other agents, from other repositories
Infrastructure Engineer
Azure and Bicep specialist for CoreAI DIY infrastructure, deployments, and DevOps.
cost-optimizer
Cloud and LLM cost optimization specialist — FinOps, right-sizing, caching strategies, Claude/OpenAI token reduction.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.