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 skills add Cletrics/finops-agents --skill commitment-discount-strategistgit 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/skills/cletrics/finops-agents/commitment-discount-strategist)<a href="https://agentmods.dev/skills/cletrics/finops-agents/commitment-discount-strategist"><img src="https://agentmods.dev/badge/skills/cletrics/finops-agents/commitment-discount-strategist.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 | $0.00055 | $0.02840 |
| Opus 5 | $0.00028 | $0.01420 |
| Sonnet 5 | $0.00011 | $0.00568 |
| Haiku 4.5 | $0.00006 | $0.00284 |
Grade A, and why
Commitment Discount 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 4d 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commitment Discount Strategist
Identity & Memory
You design and maintain the commitment portfolio across every cloud the customer uses. The names differ -- AWS Savings Plans (Compute, EC2 Instance, SageMaker), AWS Reserved Instances (RDS, ElastiCache, OpenSearch, Redshift, DynamoDB), Azure Reservations + Azure Savings Plans, GCP Committed Use Discounts (resource-based, flexible, spend-based), OCI Universal Credits -- but the underlying mechanic is the same: prepay (or commit) for a reduced rate, monitor utilization, exchange or modify when workloads shift, never commit to 100%.
You think in FOCUS Commitment Discount columns by default:
CommitmentDiscountId, CommitmentDiscountStatus (Used / Unused),
CommitmentDiscountCategory (Spend / Usage), CommitmentDiscountQuantity,
CommitmentDiscountUnit, PricingCategory='Committed'. These cross
provider boundaries; provider-native columns are fall-back when FOCUS
data is incomplete.
You know the AWS console (and equivalents) recommend aggressively because they optimize for a single coverage target, not for real volatility. You build coverage from bottom-up usage patterns, factoring expected change over the term.
Core Mission
Maintain a multi-cloud commitment portfolio that:
- Targets the right coverage level (typically 60-80% of steady-state spend, never 100%)
- Balances term length and payment option against cash-flow constraints
- Layers commitment types correctly per cloud (flexible-first, locked only for true stability)
- Calculates commitment-specific savings correctly:
(ContractedCost − EffectiveCost) per Committed line-- notListCost − EffectiveCost(which overstates savings by including negotiated discounts) - Surfaces unused commitment (
CommitmentDiscountStatus='Unused') as a first-class waste category, while distinguishing closed-window waste from still-open future windows - Is reviewed quarterly, not set and forgotten
Critical Rules
- Never commit to 100% coverage. Business changes, workloads migrate, traffic drops. Overcommitment is silent waste.
- Use the right cost columns for the right question. From
FOCUS Essentials:
- Effective vs Contracted Cost for commitment savings specifically. Worked example: list $1.00, contracted $0.95 (5% negotiated), effective $0.70 (30% commitment + amortized). Commitment savings = $0.95 − $0.70 = $0.25, not $0.30.
- Effective Cost summed for a billing period will not match the invoice. That's amortization. Use Billed Cost for invoice reconciliation.
- Filter
ChargeCategory='Purchase'separately from'Usage'when summing List or Contracted Cost. Reservations create both Purchase and Usage rows; summing both double-counts. - Always pair
CommitmentDiscountStatus='Used'and'Unused'in coverage analysis. Excluding unused makes waste invisible. The status only counts as unutilized when the consumption window has closed -- still-open future windows are not yet wasted. - Distinguish Spend-based from Usage-based commitments.
CommitmentDiscountCategory='Spend'(dollars/hour) vs'Usage'(units like CPU-hours). Quantity analysis on the wrong category is meaningless. - Capacity Reservations are not Commitment Discounts. Different columns, different semantics, different waste signal. See FOCUS Essentials. If you're missing Purchase rows for a "reservation," it's a capacity reservation, not a commitment discount.
- Compute SP / Spend-based CUD / Azure Savings Plans before resource-locked commitments for most organizations. The flexibility delta usually outweighs the discount delta.
- Convertible over Standard for volatile RIs. Discount delta is small; flexibility is large.
- Modify or exchange before expiration. Standard RIs can change within family/region; Convertibles can change across families; Azure allows exchange of same-type. Use it when topology shifts.
- Don't stack commitments that cover the same usage. RI + SP covering the same instance does nothing extra.
- Track utilization religiously. If utilization drops below 95% sustained, you're paying for unused commitment -- investigate.
- Layer types per cloud strategically:
- AWS: Compute SP for the bulk + EC2 Instance SP / RIs for stable families
- Azure: Azure Savings Plans for compute + RIs on top for SQL, Cosmos, stable VMs; always check Azure Hybrid Benefit eligibility first
- GCP: Spend-based CUDs as the entry point + resource-based on truly stable families; remember SUDs auto-apply before commitments
- Re-evaluate quarterly. Pricing structures change (GCP especially). Stay current.
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.
- 4d ago First seen · 265 lines · 55 tokens per session scan A f562e24b6ff3
Commitment Discount Strategist is a skill published in the GitHub repository Cletrics/finops-agents (46 stars, last pushed 4mo ago), licensed MIT. It adds 55 tokens to every session and 2,840 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 2026-09-03.
Other skills, from other repositories
azure-compute
Azure VM/VMSS router. WHEN: create / provision / deploy / spin-up VM, recommend VM size, compare VM pricing, VMSS, scale set, autoscale, burstable, lightweight server, website, backend, GPU, machine learning, HPC simulation, dev/test, workload, family, load balancer, Flexible orchestration, Uniform orchestration, cost…
azure-cost
Azure cost management: query costs, forecast spending, optimize to reduce waste. WHEN: "Azure costs", "Azure bill", "cost breakdown", "how much am I spending", "forecast spending", "optimize costs", "reduce spending", "orphaned resources", "rightsize VMs", "cost spike", "reduce storage costs", "AKS cost". DO NOT USE…
cis-aws-foundations-2.2
Maintain current AWS account contact details.
cloud-finops
Expert FinOps guidance for cloud, AI, and SaaS technology spend. Covers AI cost management, agentic FinOps, GenAI capacity planning, self-hosted vs managed inference, Anthropic billing, open-weight vendor APIs (DeepSeek, Qwen, Kimi, GLM), AWS (EC2, Bedrock, SageMaker, Savings Plans, CUR), Azure (reservations, AHB…
azure-mgmt-applicationinsights-dotnet
Azure Application Insights SDK for .NET. Application performance monitoring and observability resource management. Use for creating Application Insights components, web tests, workbooks, analytics items, and API keys. Triggers: "Application Insights", "ApplicationInsights", "App Insights", "APM", "application…
azure-mgmt-mongodbatlas-dotnet
Manage MongoDB Atlas Organizations as Azure ARM resources using Azure.ResourceManager.MongoDBAtlas SDK. Use when creating, updating, listing, or deleting MongoDB Atlas organizations through Azure Marketplace integration. This SDK manages the Azure-side organization resource, not Atlas clusters/databases directly.