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/agenticpawan/fullstack-pilot/azure-cost-finopsnpx skills add AgenticPawan/FullStack-Pilot --skill azure-cost-finopsgit clone --depth 1 https://github.com/AgenticPawan/FullStack-PilotWrote 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/agenticpawan/fullstack-pilot/azure-cost-finops)<a href="https://agentmods.dev/skills/agenticpawan/fullstack-pilot/azure-cost-finops"><img src="https://agentmods.dev/badge/skills/agenticpawan/fullstack-pilot/azure-cost-finops.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 | $0.00092 | $0.01386 |
| Opus 5 | $0.00046 | $0.00693 |
| Sonnet 5 | $0.00018 | $0.00277 |
| Haiku 4.5 | $0.00009 | $0.00139 |
Grade A, and why
azure-cost-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 5d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Standard IDs
| ID | Severity | What it checks |
|---|---|---|
| FIN-001 | P1 | No Azure Budget resource with action-group alerting |
| FIN-002 | P2 | Autoscale rules with no documented right-sizing review cadence |
| FIN-003 | P2 | No cost-anomaly detection/alerts configured |
| FIN-004 | P2 | Orphaned/unused resources with no automated cleanup policy |
Check A — No Budget resource with alerting (FIN-001)
Detection
Grep Bicep for Microsoft.Consumption/budgets. This goes beyond azure-waf-review's
WAF-COST pillar (which flags missing cost tags) by checking for an actual spend ceiling
with alert thresholds — without one, a runaway resource (an autoscale misconfiguration, a
forgotten test environment) accumulates cost with nobody notified until the monthly bill
arrives.
BAD — no budget defined anywhere
// No Microsoft.Consumption/budgets resource in any template — spend is unmonitored
// until someone happens to check the Cost Management blade.
GOOD — budget with staged alert thresholds tied to the on-call action group
resource budget 'Microsoft.Consumption/budgets@2023-05-01' = {
name: 'budget-orders-prod-monthly'
properties: {
category: 'Cost'
amount: 5000
timeGrain: 'Monthly'
notifications: {
actual_80pct: {
enabled: true
operator: 'GreaterThan'
threshold: 80
contactGroups: [actionGroup.id] // same action group as azure-observability AOBS-003
}
forecasted_100pct: {
enabled: true
operator: 'GreaterThan'
threshold: 100
thresholdType: 'Forecasted'
contactGroups: [actionGroup.id]
}
}
}
}
Check B — Autoscale rules with no right-sizing review cadence (FIN-002)
Detection
Check whether autoscale rules (Microsoft.Insights/autoscaleSettings, Container Apps
scale rules) have a documented review cadence — min/max replica counts and scale
thresholds set once at launch and never revisited drift out of sync with actual traffic
patterns over time, typically erring toward over-provisioned minimums "just to be safe."
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.
- 5d ago First seen · 158 lines · 92 tokens per session scan A 420d4a81c75d
azure-cost-finops is a skill published in the GitHub repository AgenticPawan/FullStack-Pilot (2 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 1,386 once invoked, about $0.0005 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
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…
contabo-live-instance-lifecycle-guard
Live-guard skill for Contabo VPS and VDS lifecycle operations including instance creation with product selection and region, reinstallation with image and Cloud-Init userData, and cancellation. Requires mandatory contract period acknowledgment (1, 3, 6, or 12 months), billing impact confirmation, and a rollback plan…
alibaba-cost-anomaly-watch-coordinator
Detect and coordinate response to Alibaba Cloud cost anomalies — MaxCompute CU vs on-demand billing mismatch, ECS spot instance interruption cascades, CDN traffic spike billing, OSS API request cost explosions, budget alert → DingTalk notification → remediation playbook.
alibaba-cost-finops-analyst
Analyze Alibaba Cloud spend via Cost Manager, optimize Savings Plans and Reserved Instance coverage, design resource tagging strategy, investigate budget drift, and right-size over-provisioned ECS, RDS, and MaxCompute resources.
azure-live-cost-budget-action-guard
Gate Azure budget action changes and GPU/HPC SKU provisioning against approved spend limits, with quota audits and emergency spend-stop playbooks.