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 j4flmao/agent-skills --skill azure-functionsgit clone --depth 1 https://github.com/j4flmao/agent-skillsWrote 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/j4flmao/agent-skills/azure-functions)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/azure-functions"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/azure-functions/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/j4flmao/agent-skills/azure-functions"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/azure-functions.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 | $0.00124 | $0.01694 |
| Opus 5.5 | $0.00050 | $0.00678 |
| Sonnet 5.5 | $0.00025 | $0.00339 |
| Haiku 4.5 | $0.00012 | $0.00169 |
Grade A, and why
cloud-native-azure-functions 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 today.
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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure Functions and Durable Functions
Purpose
Build event-driven Azure Functions and stateful Durable Functions workflows correctly. The key mechanics are the Durable Task Framework's event-sourced replay (which dictates strict orchestrator coding rules) and Event Grid's push delivery with retries (which dictates idempotent handlers).
Agent Protocol
Trigger
"azure functions", "durable functions", "orchestrator function", "activity function", "durable entities", "event grid trigger", "flex consumption", "hosting plan", "fan-out fan-in".
Input Context
- Language/worker model (.NET isolated worker, Node.js v4 model, Python v2 model, Java, PowerShell).
- Trigger sources (HTTP, Queue, Service Bus, Event Grid, Event Hubs, Timer, Blob).
- Execution length, VNet needs, cold-start tolerance, expected scale.
Output Artifact
Function code and host/plan configuration. No file unless requested.
Response Format
Hosting plan: {Flex Consumption|Premium|Dedicated|Container Apps} (why)
Pattern: {function chaining|fan-out/fan-in|async HTTP API|monitor|human interaction|aggregator}
Durable backend: {Azure Storage|Netherite|MSSQL|Durable Task Scheduler}
Idempotency: {how duplicates are handled}
Completion Criteria
- Orchestrator code is deterministic (no I/O, no
DateTime.Now, no random, no direct HTTP). - Hosting plan matches duration, networking, and cold-start needs.
- Event handlers idempotent; dead-lettering configured for Event Grid subscriptions.
Durable Functions Mechanics
- Event sourcing + replay. Every orchestration action (activity scheduled, completed, timer fired, external event received) is appended to a history. When the orchestrator awaits something, it unloads. When the result arrives, the orchestrator function re-executes from the top, and completed awaits return immediately from history.
- Default backend (Azure Storage): history and instance state in Azure Table Storage, work items via Azure Storage queues, large payloads in blobs. Alternative backends: Netherite, Microsoft SQL Server, and the managed Durable Task Scheduler.
- Function types: client (starts/queries instances), orchestrator (workflow logic), activity (the real work, may do I/O), entity (small durable state objects addressed by ID).
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.
- today Changed · +115 lines · +124 tokens per session eba87117ab57
- 1mo ago First seen · 18 lines · 0 tokens per session scan A 1a3e73156e3d
cloud-native-azure-functions is a skill published in the GitHub repository j4flmao/agent-skills (34 stars, last pushed today), licensed MIT. It adds 124 tokens to every session and 1,694 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
serverless-expert
Design and implement production-grade serverless applications with optimal performance, cost efficiency, and scalability. Use when the user mentions serverless or FaaS, AWS Lambda, Azure Functions, Cloud Functions, cold starts, event-driven architecture, or API Gateway-fronted workloads.
deploying-fc1-flex-consumption-functions
Deploys standalone Azure Function Apps on Flex Consumption (FC1) for workloads SWA managed functions can't handle — timer triggers, queue triggers, AI workloads, long-running operations, or when you need managed identity / Key Vault references (SWA managed functions support neither). Provisions via Bicep or ARM REST…
serverless
Skill "serverless" from williamzujkowski/standards, covering serverless computing, level 1: quick reference, serverless benefits and tradeoffs, common serverless patterns and essential serverless checklist.
azure-eventhub-dotnet
Azure Event Hubs SDK for .NET. Use for high-throughput event streaming: sending events (EventHubProducerClient, EventHubBufferedProducerClient), receiving events (EventProcessorClient with checkpointing), partition management, and real-time data ingestion. Triggers: "Event Hubs", "event streaming"…
azure-mgmt-apimanagement-dotnet
Azure Resource Manager SDK for API Management in .NET. Use for MANAGEMENT PLANE operations: creating/managing APIM services, APIs, products, subscriptions, policies, users, groups, gateways, and backends via Azure Resource Manager. Triggers: "API Management", "APIM service", "create APIM", "manage APIs"…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".