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 azure-defaultsgit 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/azure-defaults)<a href="https://agentmods.dev/skills/jonathan-vella/apex-accelerator/azure-defaults"><img src="https://agentmods.dev/badge/skills/jonathan-vella/apex-accelerator/azure-defaults/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/azure-defaults"><img src="https://agentmods.dev/badge/skills/jonathan-vella/apex-accelerator/azure-defaults.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00086 | $0.01191 |
| Opus 5 | $0.00043 | $0.00596 |
| Sonnet 5 | $0.00017 | $0.00238 |
| Haiku 4.5 | $0.00009 | $0.00119 |
Grade A, and why
azure-defaults 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure Defaults
Apply the canonical defaults from
.github/copilot-instructions.md
without duplicating them here. Live governance discovered for the target scope
always overrides repository defaults.
Prerequisites
- Read the canonical Azure Defaults section once per session.
- Read
04-governance-constraints.jsonwhen it exists. - Read
sku-manifest.jsonfor creative SKU decisions; do not derive SKUs from artifact prose. - Load only the reference needed for the current decision.
IaC Workflow
- Resolve governance precedence — apply live policy constraints before fallback regions, tags, networking, cost, or security defaults.
- Generate one stable suffix — derive it once from deployment scope and pass it to every globally unique resource name.
- Apply CAF naming — use resource-specific abbreviations and length limits; load naming examples when constraints differ by service.
- Resolve AVM modules live — prefer AVM, pin the latest stable version at plan time, and record justified stale-pin exceptions in the IaC contract.
- Apply canonical security defaults — use the canonical baseline and load AVM pitfalls only when module parameters or lifecycle constraints require detail.
- Run conditional planning gates — apply VNet and cost-monitoring workflows when their triggers hold; governance remains authoritative.
- Check service lifecycle — use the latest supported GA LTS runtime and reject retired, classic, preview, or short-lifecycle choices for durable production workloads unless explicitly approved.
- Validate the output — run the stack validator and the security, AVM pin, SKU coverage, and governance checks relevant to the produced IaC.
IaC-Specific Invariants
- Unique suffix: generate one deterministic suffix per deployment scope and pass it into modules rather than recomputing it independently.
- AVM-first: do not hand-roll a resource with an applicable stable AVM module.
- Live pins: resolve module versions at plan time; training-data pins are not evidence of currency.
- Governance wins: discovered policy overrides every fallback in the canonical defaults and this workflow.
- VNet planning is interactive: confirm CIDRs when a workload requires VNet integration, private endpoints, or a VNet-attached service. Production cannot defer the gate.
- Cost monitoring is explicit: production requires the governed budget, notification, and anomaly-monitoring contract; non-production exceptions must use a documented mode.
- Lifecycle is verified live: selectable engine and runtime versions require current support-policy evidence.
What ships with it
26 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/adversarial-checklists.md 21 KB
- references/adversarial-review-deep.md 4.2 KB
- references/adversarial-review-protocol.md 27 KB
- references/artifact-type-categories.md 2.1 KB
- references/avm-modules.md 4.8 KB
- references/azure-cli-auth-validation.md 2.3 KB
- references/cost-alerts-baseline.md 8.5 KB
- references/cost-alerts-bicep.md 9.1 KB
- references/cost-alerts-terraform.md 6.3 KB
- references/cost-estimate-parent-contract.md 3.5 KB
- references/deprecated-services.md 1.3 KB
- references/governance-discovery.md 4.0 KB
- references/identity-resolution.md 5.8 KB
- references/naming-full-examples.md 1.9 KB
- references/plan-design-decisions.md 5.3 KB
- references/policy-effect-decision-tree.md 1.6 KB
- references/pricing-guidance.md 6.2 KB
- references/research-workflow.md 2.0 KB
- references/security-baseline-full.md 4.5 KB
- references/service-class-menu.md 9.4 KB
- references/service-matrices.md 3.0 KB
- references/tag-strategy.md 5.4 KB
- references/terraform-conventions.md 1.7 KB
- references/vnet-planning.md 18 KB
- references/waf-criteria.md 1.4 KB
- references/workflow-gates.md 12 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.
- 5d ago First seen · 93 lines · 86 tokens per session scan A 3a6b1029fd84
azure-defaults is a skill published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed yesterday), licensed MIT. It adds 86 tokens to every session and 1,191 once invoked, about $0.0004 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
Cloud Security & Container Hardening
AWS/Azure/GCP security auditing, container and Kubernetes hardening, Infrastructure as Code scanning, and cloud compliance assessment.
enumerating-cloud-with-cloudfox
Map AWS and Azure attack paths and find exploitable misconfigurations with CloudFox.
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.