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 OptimNow/cloud-finops-skills --skill cloud-finopsgit clone --depth 1 https://github.com/OptimNow/cloud-finops-skillsWrote 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/optimnow/cloud-finops-skills/cloud-finops)<a href="https://agentmods.dev/skills/optimnow/cloud-finops-skills/cloud-finops"><img src="https://agentmods.dev/badge/skills/optimnow/cloud-finops-skills/cloud-finops/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/skills/optimnow/cloud-finops-skills/cloud-finops"><img src="https://agentmods.dev/badge/skills/optimnow/cloud-finops-skills/cloud-finops.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 | $0.00253 | $0.04150 |
| Opus 5.5 | $0.00101 | $0.01660 |
| Sonnet 5.5 | $0.00051 | $0.00830 |
| Haiku 4.5 | $0.00025 | $0.00415 |
Grade A, and why
cloud-finops 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.
The source is not reproduced here
Licensed CC-BY-SA-4.0
The repository is licensed CC-BY-SA-4.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- playbooks/aws-cross-az-egress.md 4.9 KB
- playbooks/aws-expiring-commitment-no-decision.md 4.8 KB
- playbooks/aws-gp2-to-gp3.md 4.4 KB
- playbooks/aws-gpu-for-cpu-bound-workload.md 5.1 KB
- playbooks/aws-gpu-instance-oversized.md 6.1 KB
- playbooks/aws-graviton-candidate.md 5.0 KB
- playbooks/aws-idle-load-balancer.md 3.7 KB
- playbooks/aws-kinesis-stream-no-consumers.md 6.4 KB
- playbooks/aws-mig-candidate.md 4.7 KB
- playbooks/aws-multi-gpu-underutilized.md 4.5 KB
- playbooks/aws-nat-gateway-endpoint-substitution.md 5.1 KB
- playbooks/aws-orphaned-ebs-volumes.md 4.4 KB
- playbooks/aws-outdated-gpu-generation.md 5.6 KB
- playbooks/aws-oversized-rds.md 3.5 KB
- playbooks/aws-s3-cold-data-in-standard.md 6.8 KB
- playbooks/aws-s3-incomplete-multipart-uploads.md 4.4 KB
- playbooks/aws-s3-noncurrent-version-sprawl.md 4.6 KB
- playbooks/aws-sagemaker-idle-endpoint.md 6.1 KB
- playbooks/aws-sagemaker-mme-consolidation.md 5.3 KB
- playbooks/aws-sagemaker-notebook-always-on.md 5.0 KB
- playbooks/aws-snapshot-sprawl.md 5.0 KB
- playbooks/aws-zombie-nat-gateway.md 5.7 KB
- playbooks/azure-app-service-overprovisioned.md 4.6 KB
- playbooks/azure-blob-cold-data-in-hot.md 7.5 KB
- playbooks/azure-blob-version-and-soft-delete-sprawl.md 8.0 KB
- playbooks/azure-idle-sql-database.md 4.7 KB
- playbooks/azure-idle-vm.md 4.6 KB
- playbooks/azure-log-analytics-sprawl.md 3.5 KB
- playbooks/azure-orphan-disks.md 3.8 KB
- playbooks/azure-orphaned-public-ips-and-nics.md 4.5 KB
- playbooks/azure-snapshot-sprawl.md 5.0 KB
- playbooks/azure-unused-reservation.md 5.4 KB
- playbooks/cross-cloud-agent-loop-burn.md 6.9 KB
- playbooks/cross-cloud-coding-agent-token-waste.md 7.8 KB
- playbooks/cross-cloud-schedule-blindness.md 4.7 KB
- playbooks/cross-cloud-untagged-spend-drift.md 5.0 KB
- playbooks/gcp-cloud-functions-cold-starts.md 4.9 KB
- playbooks/gcp-cud-mismatch.md 5.3 KB
- playbooks/gcp-gcs-cold-data-in-standard.md 7.8 KB
- playbooks/gcp-gcs-soft-delete-and-version-sprawl.md 7.0 KB
- playbooks/gcp-idle-gke-autopilot.md 4.5 KB
- playbooks/gcp-orphan-persistent-disks.md 4.0 KB
- playbooks/README.md 12 KB
- POWER.md 23 KB
- references/finops-agentic.md 18 KB
- references/finops-ai-dev-tools.md 41 KB
- references/finops-ai-self-hosted-vs-managed.md 24 KB
- references/finops-ai-value-management.md 27 KB
- references/finops-allocation-showback.md 21 KB
- references/finops-anomaly-management.md 18 KB
- references/finops-anthropic.md 30 KB
- references/finops-aws-commitments.md 35 KB
- references/finops-aws-patterns.md 105 KB
- references/finops-aws.md 84 KB
- references/finops-azure-commitments.md 73 KB
- references/finops-azure-openai.md 25 KB
- references/finops-azure-patterns.md 34 KB
- references/finops-azure.md 88 KB
- references/finops-bedrock.md 38 KB
- references/finops-chargeback.md 23 KB
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.
- 2d ago Changed · +1 lines dd6fd1070589
- 3d ago Changed d6a53a9298c5
- 5d ago Changed 45727c437500
- 7d ago Changed · +1 lines 50da9e4435d0
- 18d ago Changed · -3 lines d835f4615603
- 28d ago Changed e35f31869bbd
- 1mo ago Changed ee90bdbd0c57
- 1mo ago First seen · 164 lines · 253 tokens per session scan A 42c474836b47
cloud-finops is a skill published in the GitHub repository OptimNow/cloud-finops-skills (63 stars, last pushed today), licensed CC-BY-SA-4.0. It adds 253 tokens to every session and 4,150 once invoked, about $0.0010 per session on Opus 5.5. 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.
Other skills, from other repositories
cloud-costs
Use nable's cost tools when the user asks what something costs, why a cloud or AI bill went up, what their AI coding spend is, or before launching, resizing or destroying infrastructure. Also explains how to respond when the nable guard asks for confirmation before a command runs.
commitments-bounds
Use when asked about Savings Plans, Reserved Instances, committed use discounts or reservations, or before any command that would buy one.
credits-runway
Use before launching GPU or other large cloud resources at a startup running on cloud credits, or when asked how long the credits will last.
Commitment Discount Strategist
Cross-cloud commitment portfolio specialist. Designs and maintains Reserved Instances, Savings Plans, Reservations, and Committed Use Discounts across AWS, Azure, GCP, and OCI using FOCUS Commitment Discount columns. Maximizes effective discount without bleeding on unused commitment.
Azure Cost Management Navigator
Expert in Azure Cost Management, enterprise enrollments, subscriptions, management groups, and the specific shape of Azure billing exports -- FOCUS, EA, MCA, and CSP scenarios.
Idle & Orphaned Resource Hunter
Enumerates and decommissions idle compute, orphaned EBS snapshots, idle load balancers, and zombie NAT Gateways. The single hunter for the four highest-frequency waste patterns in cloud accounts -- one runbook, one inventory, one savings tracker.