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/code-and-sorts/awesome-copilot-agents/az-clinpx skills add Code-and-Sorts/awesome-copilot-agents --skill az-cligit clone --depth 1 https://github.com/Code-and-Sorts/awesome-copilot-agentsWrote 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/code-and-sorts/awesome-copilot-agents/az-cli)<a href="https://agentmods.dev/skills/code-and-sorts/awesome-copilot-agents/az-cli"><img src="https://agentmods.dev/badge/skills/code-and-sorts/awesome-copilot-agents/az-cli.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 | $0.00079 | $0.08807 |
| Opus 5 | $0.00039 | $0.04404 |
| Sonnet 5 | $0.00016 | $0.01761 |
| Haiku 4.5 | $0.00008 | $0.00881 |
Grade A, and why
az-cli 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 — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Az CLI
Help users accomplish Azure tasks by identifying the right az commands, gathering required parameters, and executing them.
Workflow
When a user asks to do something with Azure:
- Identify the command — find the right
azsubcommand from the reference docs below. If the task spans multiple commands, plan the sequence. - Check for required parameters — read the relevant reference file to understand what the command needs. If the user hasn't provided required values (resource group, name, SKU, location, etc.), ask them before running anything.
- Construct and execute — build the command with the user's parameters and run it. If a command has optional flags that would be useful for the user's scenario, mention them.
- Verify the result — after running a command, check the output for errors. If something fails, diagnose and suggest fixes (common issues: wrong resource group, missing provider registration, quota limits).
When a user asks about Azure CLI syntax or wants to know what commands are available for a service, read the relevant reference file and summarize what's available.
Command Groups
Compute
| Command | Description | Status | Reference |
|---|---|---|---|
az aks |
Azure Kubernetes Service. | GA | ref |
az aksarc |
Manage provisioned clusters. | GA (ext) | ref |
az appservice |
Manage Appservice. | GA | ref |
az batch |
Manage Azure Batch. | GA | ref |
az capacity |
Manage capacity. | GA | ref |
az cloud-service |
Manage cloud service. | Experimental (ext) | ref |
az compute-fleet |
Manage for Azure Compute Fleet. | Preview | ref |
az compute-recommender |
Manage sku/zone/region recommender info for compute resources. | GA | ref |
az computeschedule |
Computeschedule batch virtual machine operations. | GA (ext) | ref |
az container |
Manage Azure Container Instances. | GA | ref |
az containerapp |
Manage Azure Container Apps. | GA | ref |
az disk |
Manage Azure Managed Disks. | GA | ref |
az disk-access |
Manage disk access resources. | GA | ref |
az disk-encryption-set |
Disk Encryption Set resource. | GA | ref |
az disk-pool |
Manage Azure disk pool. | GA (ext) | ref |
az functionapp |
Manage function apps. To install the Azure Functions Core tools, see the project repository. | GA | ref |
az image |
Manage custom virtual machine images. | GA | ref |
az logicapp |
Manage logic apps. | GA | ref |
az ppg |
Manage Proximity Placement Groups. | GA | ref |
az restore-point |
Manage restore point with res. | GA | ref |
az serial-console |
Connect to the Serial Console of a Linux/Windows Virtual Machine or VMSS Instance. | GA (ext) | ref |
az sf |
Manage and administer Azure Service Fabric clusters. | GA | ref |
az sig |
Manage shared image gallery. | GA | ref |
az snapshot |
Manage point-in-time copies of managed disks, native blobs, or other snapshots. | GA | ref |
az spring |
Commands to manage Azure Spring Apps. | Deprecated | ref |
az ssh |
SSH into resources (Azure VMs, Arc servers, etc) using AAD issued openssh certificates. | GA (ext) | ref |
az sshkey |
Manage ssh public key with vm. | GA | ref |
az staticwebapp |
Manage static apps. | GA | ref |
az vm |
Manage Linux or Windows virtual machines. | GA | ref |
az vmss |
Manage groupings of virtual machines in an Azure Virtual Machine Scale Set (VMSS). | GA | ref |
az webapp |
Manage web apps. | GA | ref |
What ships with it
60 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/acat.md 1.7 KB
- references/account.md 3.4 KB
- references/acr.md 14 KB
- references/ad.md 3.9 KB
- references/advisor.md 523 B
- references/afd.md 7.9 KB
- references/ai-examples.md 123 B
- references/aks.md 19 KB
- references/aksarc.md 1.8 KB
- references/alerts-management.md 527 B
- references/alias.md 528 B
- references/amlfs.md 2.0 KB
- references/ams.md 8.1 KB
- references/aosm.md 2.5 KB
- references/apic.md 3.6 KB
- references/apim.md 5.6 KB
- references/appconfig.md 3.3 KB
- references/appnet.md 1023 B
- references/appservice.md 4.2 KB
- references/arc-multicloud.md 1.6 KB
- references/arcappliance.md 5.9 KB
- references/arcgateway.md 472 B
- references/arize-ai.md 580 B
- references/aro.md 521 B
- references/artifact-signing.md 1.0 KB
- references/artifacts.md 145 B
- references/astronomer.md 719 B
- references/attestation.md 1.1 KB
- references/automanage.md 4.3 KB
- references/automation.md 6.2 KB
- references/backup.md 6.9 KB
- references/baremetalinstance.md 1004 B
- references/baremetalstorageinstance.md 824 B
- references/batch.md 8.7 KB
- references/bicep.md 826 B
- references/billing-benefits.md 1.4 KB
- references/billing.md 10.0 KB
- references/blueprint.md 2.5 KB
- references/boards.md 1.9 KB
- references/bot.md 2.8 KB
- references/cache.md 254 B
- references/capacity.md 1.6 KB
- references/carbon.md 200 B
- references/cdn.md 8.0 KB
- references/change-analysis.md 345 B
- references/cli-translator.md 159 B
- references/cloud-service.md 3.7 KB
- references/cloud.md 363 B
- references/cloudhsm.md 379 B
- references/cognitiveservices.md 5.2 KB
- references/command-change.md 199 B
- references/communication.md 7.1 KB
- references/compute-fleet.md 476 B
- references/compute-recommender.md 128 B
- references/computeschedule.md 1.6 KB
- references/confcom.md 701 B
- references/confidentialledger.md 1.1 KB
- references/config.md 400 B
- references/configure.md 167 B
- references/confluent.md 4.7 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 · 376 lines · 79 tokens per session scan A 769947028374
az-cli is a skill published in the GitHub repository Code-and-Sorts/awesome-copilot-agents (563 stars, last pushed 4mo ago), licensed CC0-1.0. It adds 79 tokens to every session and 8,807 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 2026-08-30.
Other skills, from other repositories
code-review
Use when user wants code reviewed for correctness, style, bugs, and maintainability. Triggers on: review code, code review, check PR, 審查程式碼, 檢查程式碼. Produces severity-classified findings with a verdict. Do NOT use for security-focused audit (prefer security-audit) or SQL-focused review (prefer sql-review).
plan
Use when user needs a phased implementation plan with requirements, file impact, risks, and alternatives before coding — including clarifying vague or ambiguous requirements first. Triggers on: plan, how should we build, unclear requirements, 規劃, 幫我想方案. Produces a structured plan document. Do NOT use for atomic task…
security-audit
Use when user needs an OWASP-focused security audit of Java web code — injection, auth, access control, and configuration review. Triggers on: security audit, OWASP, vulnerability check, 資安審查, 有沒有漏洞. Produces severity-classified security findings. Do NOT use for general code review (prefer code-review) or SQL-only…
sql-review
Use when user needs SQL reviewed — queries for injection risks, performance, and index strategy, or DDL/DML migration scripts for rollback safety, data-loss risk, lock impact, and backward compatibility. Triggers on: review SQL, slow query, review migration, SQL 審查, 看 migration. Produces severity-classified findings…
verify
Use when checking whether an implementation actually meets its acceptance criteria — derive the checks, bind each to a runnable command, execute, and gate pass/fail so a build loop has an objective exit condition. Triggers on: verify, does it pass, acceptance check, definition of done, test cases, what to test, 驗證…
debug
Use when user reports a bug, error, exception, or unexpected behavior needing root cause analysis and minimal fix. Triggers on: debug this, why does this fail, root-cause this, 除錯, 找 bug. Performs systematic isolation and minimal fix. Do NOT use for feature requests (prefer implement) or known simple typos (prefer…