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 daffy0208/ai-dev-standards --skill iot-developergit clone --depth 1 https://github.com/daffy0208/ai-dev-standardsWrote 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/daffy0208/ai-dev-standards/iot-developer)<a href="https://agentmods.dev/skills/daffy0208/ai-dev-standards/iot-developer"><img src="https://agentmods.dev/badge/skills/daffy0208/ai-dev-standards/iot-developer/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/daffy0208/ai-dev-standards/iot-developer"><img src="https://agentmods.dev/badge/skills/daffy0208/ai-dev-standards/iot-developer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
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 | $0.00018 | $0.02221 |
| Opus 5.5 | $0.00007 | $0.00888 |
| Sonnet 5.5 | $0.00004 | $0.00444 |
| Haiku 4.5 | $0.00002 | $0.00222 |
Grade A, and why
iot-developer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IoT Developer Skill
I help you build IoT applications, connect sensors and devices, and create smart home/industrial IoT solutions.
What I Do
Device Integration:
- Microcontroller programming (Arduino, ESP32)
- Sensor reading and data collection
- Actuator control (motors, LEDs, relays)
- Hardware interfacing
Communication:
- MQTT messaging
- WebSocket connections
- REST API integration
- Bluetooth/WiFi connectivity
IoT Platforms:
- Real-time dashboards
- Device management
- Data logging
- Alerts and automation
MQTT Basics (Web Client)
npm install mqtt
// lib/mqtt-client.ts
import mqtt from 'mqtt'
export class MQTTClient {
private client: mqtt.MqttClient
constructor(brokerUrl: string) {
this.client = mqtt.connect(brokerUrl, {
clientId: `web_${Math.random().toString(16).slice(3)}`,
clean: true,
connectTimeout: 4000
})
this.client.on('connect', () => {
console.log('MQTT connected')
})
this.client.on('error', error => {
console.error('MQTT error:', error)
})
}
subscribe(topic: string, callback: (message: string) => void) {
this.client.subscribe(topic, err => {
if (err) console.error('Subscribe error:', err)
})
this.client.on('message', (receivedTopic, message) => {
if (receivedTopic === topic) {
callback(message.toString())
}
})
}
publish(topic: string, message: string) {
this.client.publish(topic, message)
}
disconnect() {
this.client.end()
}
}
Usage:
'use client'
import { useEffect, useState } from 'react'
import { MQTTClient } from '@/lib/mqtt-client'
export function TemperatureDashboard() {
const [temperature, setTemperature] = useState(0)
const [humidity, setHumidity] = useState(0)
useEffect(() => {
const mqtt = new MQTTClient('ws://broker.hivemq.com:8000/mqtt')
mqtt.subscribe('home/temperature', (msg) => {
setTemperature(parseFloat(msg))
})
mqtt.subscribe('home/humidity', (msg) => {
setHumidity(parseFloat(msg))
})
return () => mqtt.disconnect()
}, [])
return (
<div className="grid grid-cols-2 gap-4">
<div className="p-6 bg-white rounded-lg shadow">
<h3 className="text-gray-600">Temperature</h3>
<p className="text-4xl font-bold">{temperature}°C</p>
</div>
<div className="p-6 bg-white rounded-lg shadow">
<h3 className="text-gray-600">Humidity</h3>
<p className="text-4xl font-bold">{humidity}%</p>
</div>
</div>
)
}
What ships with it
2 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.
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.
- 1mo ago First seen · 377 lines · 18 tokens per session scan A 2ca278178f01
iot-developer is a skill published in the GitHub repository daffy0208/ai-dev-standards (38 stars, last pushed 9mo ago), licensed MIT. It adds 18 tokens to every session and 2,221 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
edge-iot
Edge computing, IoT protocols, and embedded systems integration.
iot-expert
Expert-level IoT systems, embedded devices, edge computing, and IoT protocols. Use when the user mentions embedded, edge computing, MQTT, sensors, or firmware, or when the task involves IoT Architecture, IoT Protocols, Embedded Systems, or Device Design.
iot-skills
Use when developing IoT solutions — Raspberry Pi Pico (RP2040) GPIO/I2C/Wi-Fi/MQTT/sensors in MicroPython, or building low-code data flows, MQTT pub/sub and HTTP APIs with Node-RED. Index of 2 skills: KE3036 Keyes Pico learning kit and Node-RED.
library-migration-guide
Complete guide for converting Arduino/ESP32 hardware libraries into Aily Blockly compatible format. Covers the full workflow: source analysis, block.json design, generator.js implementation, toolbox.json configuration, bus initialization (Serial/I2C/SPI), board adaptation, and packaging.
blockly-best-practices
Aily Blockly implementation workflow for scoped library evidence, ABS editing, workspace synchronization, and focused validation. Use for creating or modifying Blockly/ABS programs.
blockly-project-planning
Blockly project planning and creation workflow for no-project hardware requests. Trigger words: create project, new Blockly project, board selection, library selection, hardware plan, LED blink, sensor, actuator.