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 jonmikeli/ai-iot-tools-and-resources --skill azure-iothub-servicegit clone --depth 1 https://github.com/jonmikeli/ai-iot-tools-and-resourcesWrote 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/jonmikeli/ai-iot-tools-and-resources/azure-iothub-service)<a href="https://agentmods.dev/skills/jonmikeli/ai-iot-tools-and-resources/azure-iothub-service"><img src="https://agentmods.dev/badge/skills/jonmikeli/ai-iot-tools-and-resources/azure-iothub-service/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/jonmikeli/ai-iot-tools-and-resources/azure-iothub-service"><img src="https://agentmods.dev/badge/skills/jonmikeli/ai-iot-tools-and-resources/azure-iothub-service.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 | $0.00158 | $0.02652 |
| Opus 5 | $0.00079 | $0.01326 |
| Sonnet 5 | $0.00032 | $0.00530 |
| Haiku 4.5 | $0.00016 | $0.00265 |
Grade A, and why
azure-iothub-service 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 12d 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure IoT Hub Skill
Operate Azure IoT Hub end-to-end via the azure-iothub-service-mcp MCP Server. This skill covers five capability areas — read the relevant section before acting.
Table of Contents
- General Principles
- C2D Direct Methods (Commands)
- C2D Messages
- Device Twin — Tags & Reported Properties
- Device Management
- IoT Hub Jobs
- Error Handling & Retry Guidance
- Query Cheat-Sheet
1. General Principles
-
Never fabricate device data. Always call an MCP tool and surface the real result to the user.
-
Confirm destructive operations (delete, disable, rotate keys) with the user before executing, unless the user has already confirmed in their message.
-
Scope awareness: Ask the user for the IoT Hub name / connection scope if it is not already established in the conversation or pre-configured in the MCP server.
-
Pagination: Device queries and job listings may be paginated. Loop with
continuationTokenuntil exhausted, or ask the user how many records they want. -
Present results clearly: Format twin documents as collapsible JSON blocks; format device lists as tables with columns
deviceId | status | lastActivityTime. -
Use the right tool for the job: For commands needing a response, use Direct Methods. For fire-and-forget notifications, use C2D messages. For fleet-wide updates, use Jobs.
-
Jobs: Use jobs ONLY if the user requests explicitly mentioning the key word "job".
2. C2D Direct Methods (Commands)
Direct methods are synchronous RPC calls to a connected device. Use them for real-time commands (reboot, firmware update trigger, valve open/close, etc.).
Workflow
- Confirm
deviceId(or a list ofdeviceIds) andmethodNamewith the user. - Build the
payloadfrom the user's instructions. - Call the tool.
- Show the response:
statuscode +payloadreturned by the device. - If
statusis not 200, surface the error and suggest checking device connectivity.
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.
- 12d ago First seen · 294 lines · 158 tokens per session scan A 0084b30e0ab0
azure-iothub-service is a skill published in the GitHub repository jonmikeli/ai-iot-tools-and-resources (1 stars, last pushed 4mo ago), licensed MIT. It adds 158 tokens to every session and 2,652 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
analyze-tensegrity-system
Analyze a tensegrity system by identifying compression struts and tension cables, classifying type (class 1/2, biological/architectural), computing prestress equilibrium, verifying stability via Maxwell's rigidity criterion, and mapping biological tensegrity (microtubules, actin, intermediate filaments). Use when…
analyze-kernel-bottleneck
Systematically identify whether a GPU kernel is compute-bound, memory-bound, or latency-bound using roofline analysis, occupancy calculations, compute/load ratio per tile, and SASS instruction inspection. Produces a decision matrix for optimization strategy selection (cp.async, warp interleaving, tiling…
analyze-magnetic-field
Calculate and visualize magnetic fields produced by current distributions using the Biot-Savart law, Ampere's law, and magnetic dipole approximations. Use when computing B-fields from arbitrary current geometries, exploiting symmetry with Ampere's law, analyzing superposition of multiple sources, or characterizing…
analyze-magnetic-levitation
Analyze magnetic levitation systems by applying Earnshaw's theorem to determine whether passive static levitation is possible, then identifying the appropriate circumvention mechanism (diamagnetic, superconducting, active feedback, or spin-stabilized). Use when evaluating maglev transport, magnetic bearings…
build-sequential-circuit
Build sequential (stateful) logic circuits including latches, flip-flops, registers, counters, and finite state machines. Covers SR latch, D and JK flip-flops, binary/BCD/ring counters, and Mealy/Moore FSM design with clock signal and timing analysis. Use when a circuit must remember past inputs, count events, or…
design-acoustic-levitation
Design an acoustic levitation system that uses standing waves to trap and suspend small objects at pressure nodes. Covers ultrasonic transducer selection, standing wave formation between a transducer and reflector, node spacing and trapping position calculation, acoustic radiation pressure analysis, and phased array…