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/nevaberry/nevaberry-plugins/azure-knowledge-patchnpx skills add Nevaberry/nevaberry-plugins --skill azure-knowledge-patchgit clone --depth 1 https://github.com/Nevaberry/nevaberry-pluginsWrote 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/nevaberry/nevaberry-plugins/azure-knowledge-patch)<a href="https://agentmods.dev/skills/nevaberry/nevaberry-plugins/azure-knowledge-patch"><img src="https://agentmods.dev/badge/skills/nevaberry/nevaberry-plugins/azure-knowledge-patch.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 | $0.00008 | $0.02178 |
| Opus 5 | $0.00004 | $0.01089 |
| Sonnet 5 | $0.00002 | $0.00436 |
| Haiku 4.5 | $0.00001 | $0.00218 |
Grade A, and why
azure-knowledge-patch 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 4d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft Azure Knowledge Patch
Use this skill for Azure infrastructure, Azure CLI, Azure PowerShell, Terraform AzureRM or AzAPI, Bicep, identity SDK, Microsoft Entra, networking, compute, containers, data services, storage, Key Vault, governance, and service lifecycle work.
Azure is a rolling multi-product platform. Inspect the project's pinned provider, CLI, module, API version, SDK, and resource SKU before applying version-dependent advice. Prefer manifests, state, schemas, live API metadata, command help, plans, and tests when they differ from this guidance.
Reference index
| Reference | Topics |
|---|---|
| Terraform providers | AzureRM 4.x and AzAPI 2.x migrations, HCL bodies, import, preflight, actions, state, and authentication |
| AKS and containers | AKS, Azure Container Registry, Container Apps, Container Instances, Service Fabric, and container storage |
| Compute and application platform | VMs, VMSS, disks, images, App Service, Functions, App Configuration, Batch, AI, and application services |
| Data, storage, and Key Vault | PostgreSQL, MySQL, SQL, Cosmos DB, Storage, Azure Files, NetApp Files, Backup, and Key Vault |
| Deployment, governance, and CLI | ARM, Bicep, provider registration, deployments, RBAC, monitoring, CLI packaging, API Management, and retirements |
| Identity, authentication, and Graph | Entra and Microsoft Graph, mandatory MFA, Azure Identity SDKs, Azure CLI, PowerShell, managed identity, and federation |
| Networking | Private VNets, outbound access, load balancers, public IPs, gateways, private endpoints, Application Gateway, and network appliances |
First-pass migration triage
- Identify every client surface: Azure CLI version, Az PowerShell modules, Terraform providers, Bicep CLI, SDK packages, and explicit ARM API versions.
- Resolve authentication type. Prefer workload identity, managed identity, or a service principal for automation; user-password flows cannot satisfy MFA.
- Run
terraform plan, deployment validation or what-if, and representative CLI queries without mutating production resources. - Check defaults that affect network exposure, egress, operating system, compute size, database version, storage redundancy, and access control.
- Validate JSON and table-output consumers against the installed CLI because several commands changed casing, fields, null representation, and shape.
- Query provider metadata for supported API versions and locations instead of copying one API version across a namespace.
- Inventory retirements separately; an interface can remain operational after retirement while losing support and SLA coverage.
What ships with it
8 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.
- coverage.json 3.7 KB
- references/aks-and-containers.md 10 KB
- references/compute-and-app-platform.md 12 KB
- references/data-and-storage.md 13 KB
- references/deployment-governance-and-cli.md 10 KB
- references/identity-authentication-and-graph.md 9.5 KB
- references/networking.md 6.9 KB
- references/terraform-providers.md 13 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.
- 4d ago First seen · 212 lines · 8 tokens per session scan A cd1f1635cdd6
azure-knowledge-patch is a skill published in the GitHub repository Nevaberry/nevaberry-plugins (24 stars, last pushed 7d ago), licensed MIT. It adds 8 tokens to every session and 2,178 once invoked, about $0.0000 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 2026-08-30.
Other skills, from other repositories
api-workers
Cloudflare Workers deployment using createWorkerHandler from @cyanheads/mcp-ts-core/worker. Covers the full handler signature, binding types, CloudflareBindings extensibility, runtime compatibility guards, and wrangler.toml requirements.
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…
api-testing
Testing patterns for MCP tool/resource handlers using createMockContext and Vitest. Covers mock context options, handler testing, McpError assertions, format testing, Vitest config setup, and test isolation conventions.
api-telemetry
Catalog of OpenTelemetry instrumentation built into framework @cyanheads/mcp-ts-core — spans, metrics, completion logs, env config, runtime caveats, custom instrumentation patterns, and cardinality rules. Use when enabling OTel export, adding custom spans or metrics in services, debugging missing telemetry, looking up…
add-test
Scaffold a test file for an existing tool, resource, or service. Use when the user asks to add tests, improve coverage, or when a definition exists without a matching test file.
polish-docs-meta
Finalize documentation and project metadata for a ship-ready MCP server. Use after implementation is complete, tests pass, and devcheck is clean. Safe to run at any stage — each step checks current state and only acts on what still needs work.