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/arjunprabhulal/devops-skills/cloud-budgetingnpx skills add arjunprabhulal/devops-skills --skill cloud-budgetinggit clone --depth 1 https://github.com/arjunprabhulal/devops-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/arjunprabhulal/devops-skills/cloud-budgeting)<a href="https://agentmods.dev/skills/arjunprabhulal/devops-skills/cloud-budgeting"><img src="https://agentmods.dev/badge/skills/arjunprabhulal/devops-skills/cloud-budgeting.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 | $0.00123 | $0.01193 |
| Opus 5 | $0.00062 | $0.00596 |
| Sonnet 5 | $0.00025 | $0.00239 |
| Haiku 4.5 | $0.00012 | $0.00119 |
Grade A, and why
cloud-budgeting 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud Budgeting
A budget that exists only as a number in a spreadsheet, checked once a month, catches an overrun after the money is already spent. The point of budgeting isn't the forecast itself — it's the early-warning system that lets someone act while there's still spend left to prevent, not just spend left to explain after the fact.
Budgeting also has to answer a harder question than "are we over": whether the spend is proportionate to the value it's producing. A bill that doubles because usage doubled is healthy; a bill that doubles while usage is flat is not — and only unit economics can tell the two apart.
A budget's job is to give you time to act before the overrun, not a report after it.
1. Forecast from trend plus known changes, not last month's total
Last month's total is a lagging number — it says nothing about a migration, a new feature launch, or a customer onboarding that's about to change the trajectory. A forecast built from the recent trend line, adjusted for known upcoming changes (a launch date, a planned decommission, a seasonal pattern), is far more useful than an extrapolation of a single flat number.
- Use a rolling trend, not a single prior period, to smooth out one-off spikes.
- Adjust explicitly for known changes — don't let the model be blindsided by something already on the roadmap.
Done when: the forecast cites the trend window and the known changes it was adjusted for, not just last month's number carried forward.
2. Set budgets and alerts before the money is spent, not after
An alert that fires once the monthly bill is already final tells you what happened, not what to stop. Budget alerts tied to forecasted trajectory — "on pace to exceed budget by day 20" — give a team the runway to intervene mid-cycle instead of just explaining the overrun after close.
budget: $50,000/month
alert at 50% of budget consumed by day 10 -> informational
alert at forecasted-to-exceed by >10% -> page the budget owner
alert at 100% of budget consumed -> escalate, don't wait for month-end
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 · 101 lines · 123 tokens per session scan A 841fc386ee3c
cloud-budgeting is a skill published in the GitHub repository arjunprabhulal/devops-skills (3 stars, last pushed 11d ago), licensed MIT. It adds 123 tokens to every session and 1,193 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
google-cloud-solution-guided-gke-ai-migration
Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl. Use when the user has an existing AI inference workload (on Cloud Run, the Gemini API, Gemini Enterprise Agent Platform, or a custom VM) and wants to move it to…
agent-platform-deploy
Deploy open models or custom weights from Model Garden to Agent Platform endpoints, check the status of an in-progress deployment operation, or clean up resources by undeploying models and deleting endpoints. Use when asked to actively deploy a model, list the Model Garden CATALOG of available models, check if a…
cloud-logging-cross-project-configuration
Configure and troubleshoot Google Cloud cross-project centralized logging and read-time aggregation. Use when: - Setting up log routing from multiple projects/folders/organizations to a central log bucket. - Creating cross-project log sinks and configuring central log buckets. - Troubleshooting cross-project routing.…
gke-alert-configuration
Configures alerting policies in Terraform for Google Kubernetes Engine (GKE) clusters, workloads, and services using PromQL and Google Cloud Managed Service for Prometheus. Use when writing, analyzing, validating, or deploying Terraform alerting policies to monitor GKE service latency, traffic, error rates using…
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
google-cloud-recipe-foundation-builder
Deploys a baseline landing zone foundation for a Google Cloud Organization, establishing security guardrails using Organization Policies, resource hierarchy folders and projects, billing association, and centralized logging and monitoring. Deploys Google Cloud's recommended security controls and architecture. Use when…