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 jonathan-vella/apex-accelerator --skill apex-azure-cost-optimizationgit clone --depth 1 https://github.com/jonathan-vella/apex-acceleratorWrote 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/jonathan-vella/apex-accelerator/apex-azure-cost-optimization)<a href="https://agentmods.dev/skills/jonathan-vella/apex-accelerator/apex-azure-cost-optimization"><img src="https://agentmods.dev/badge/skills/jonathan-vella/apex-accelerator/apex-azure-cost-optimization/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/jonathan-vella/apex-accelerator/apex-azure-cost-optimization"><img src="https://agentmods.dev/badge/skills/jonathan-vella/apex-accelerator/apex-azure-cost-optimization.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 | $0.00104 | $0.01662 |
| Opus 5.5 | $0.00042 | $0.00665 |
| Sonnet 5.5 | $0.00021 | $0.00332 |
| Haiku 4.5 | $0.00010 | $0.00166 |
Grade A, and why
apex-azure-cost-optimization 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 22d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure Cost Optimization Skill
Analyze Azure subscriptions to identify cost savings through orphaned resource cleanup, rightsizing, and optimization recommendations based on actual usage data.
Routing
| User intent | Workflow |
|---|---|
| Understand current or historical cost | Cost query (query_costs) |
| Reduce costs or find waste | Instructions below |
| Project future cost | Cost forecast (forecast_costs) |
Scope Reference (Shared Across All Workflows)
- Subscription:
/subscriptions/<id> - Resource group:
/subscriptions/<id>/resourceGroups/<name> - Management group:
/providers/Microsoft.Management/managementGroups/<id> - Billing account:
/providers/Microsoft.Billing/billingAccounts/<id>
When to Use This Skill
Use this skill when the user asks to:
- Optimize Azure costs or reduce spending
- Analyze Azure subscription for cost savings
- Generate cost optimization report
- Find orphaned or unused resources
- Rightsize Azure VMs, containers, or services
- Identify where they're overspending in Azure
- Optimize Redis costs specifically - See Azure Redis Cost Optimization for Redis-specific analysis
- Review storage tiers and lifecycle - See Azure Storage Cost Review
Rules
- Read-only analysis first — never delete or modify resources during the assessment phase; remediation is a separate user-approved step
- Validate prerequisites before starting (Azure CLI authenticated,
costmanagement+resource-graphextensions,azqrinstalled, Cost Management Reader + Monitoring Reader + Reader roles) - Use real data — recommendations must be grounded in actual cost queries and utilization metrics, not assumptions
- ARM MCP first — use API fallbacks only when an operation is unavailable, never to bypass invalid input, denied access, throttling or empty data (tool and safety guidance)
- Cite sources — every savings estimate must reference the underlying cost query or pricing API result (audit trail in
agent-output/{project}/cost-query-result<timestamp>.json) - Classify safely — mark recommendations as Safe / Review / Risky; never auto-apply destructive operations
- Show the total bill — present savings next to the scope's total actual cost for the same period, so each saving reads against the whole bill
- Redis-specific scope — when the user asks about Redis only, follow Azure Redis Cost Optimization instead of the general subscription workflow
- Save artifacts to
agent-output/{project}/costoptimizereport<timestamp>.mdand the audit trail JSON; without a project, ask for its name before writing - Out of scope: deploying resources (use
apex-azure-deploy), security issues (useapex-azure-compliance), general diagnostics (useapex-azure-diagnostics)
What ships with it
22 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.
- references/azure-quick-review.md 1.6 KB
- references/azure-redis.md 3.8 KB
- references/azure-resource-graph.md 2.8 KB
- references/azure-storage-tiers.md 6.6 KB
- references/best-practices-notes.md 1.7 KB
- references/cost-forecast/error-handling.md 1.4 KB
- references/cost-forecast/examples.md 772 B
- references/cost-forecast/guardrails.md 913 B
- references/cost-forecast/request-body-schema.md 1018 B
- references/cost-forecast/workflow.md 2.2 KB
- references/cost-query/dimensions-by-scope.md 1.5 KB
- references/cost-query/error-handling.md 1.5 KB
- references/cost-query/examples.md 1.3 KB
- references/cost-query/guardrails.md 1.7 KB
- references/cost-query/request-body-schema.md 1.4 KB
- references/cost-query/workflow.md 2.8 KB
- references/detailed-workflow-steps.md 6.8 KB
- references/sdk/azure-resource-manager-redis-dotnet.md 1.6 KB
- references/tools-and-safety.md 2.6 KB
- references/workflow-steps.md 4.8 KB
- templates/redis-detailed-cache-analysis.md 1.9 KB
- templates/redis-subscription-level-report.md 2.2 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.
- 22d ago Changed · +22 lines · +6 tokens per session ae4eb43eb9d7
- 23d ago First seen · 95 lines · 98 tokens per session scan A 427590e98970
apex-azure-cost-optimization is a skill published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed yesterday), licensed MIT. It adds 104 tokens to every session and 1,662 once invoked, about $0.0004 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 2026-09-23.
Other skills, from other repositories
chaos-experiment
Design and document chaos engineering experiments. Guide steady state baseline, hypothesis formation, failure injection plans, and results analysis. Use when you say "design a chaos experiment", "plan a game day", "failure injection", "test resilience", or "chaos engineering". Do NOT use for security threat analysis…
infrastructure-as-code
Domain: DevOps & Cloud Engineering.
cloud-solution-architect
Design well-architected Azure cloud systems — 10 design principles, 6 architecture styles, 44 design patterns, technology choices, WAF pillars.
bicep-avm-mastery
Azure Verified Modules (AVM), Bicep best practices, and MCP-powered infrastructure as code for Azure.
foundry-agent-platform
Microsoft Foundry agent deployment, orchestration, and cloud-native AI service patterns.
sse-streaming
POST-based Server-Sent Events streaming for Azure Functions — HTTP streaming, chunked response parsing, reconnection.