A set of instructions for building applications that use AetherEdge, an AI-oriented edge runtime for connected devices. It covers device and topology clients, operations interfaces, MCP integration, and governed device commands.

Use it to onboard AetherEdge, connect applications or AI tools to it, build read-only operations UIs, create Domain Packs, and handle controlled IoT commands.

It helps keep generated applications aligned with verified runtime contracts and safety rules when they interact with physical devices.

aether-iot — Skill for Codex by EvanL1

Install

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.

Any agent

npx skills add EvanL1/AetherEdge --skill aether-iot

Clone the repo

git clone --depth 1 https://github.com/EvanL1/AetherEdge

Made for: Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/evanl1/aetheredge/aether-iot.svg)](https://agentmods.dev/skills/evanl1/aetheredge/aether-iot)

Your own site

<a href="https://agentmods.dev/skills/evanl1/aetheredge/aether-iot"><img src="https://agentmods.dev/badge/skills/evanl1/aetheredge/aether-iot.svg" alt="Measured on agentmods" height="20"></a>

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,181 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00068	$0.01181
Opus 5	$0.00034	$0.00590
Sonnet 5	$0.00014	$0.00236
Haiku 4.5	$0.00007	$0.00118

Measured 7d ago against content hash e0b1e2a0c641, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

aether-iot 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 7d 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.

skills/aether-iot/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AetherEdge

The Skill identifier remains aether-iot during the repository rename for downstream compatibility. Treat AetherEdge as a headless edge runtime with machine-readable contracts. Use its documentation for reasoning, OpenAPI and manifests for exact schemas, and MCP for live capabilities. Treat every generated application as an untrusted client of the application boundary.

Establish context

In an AetherEdge checkout, read AGENTS.md before changing files.
Outside a checkout, fetch https://docs.aetheriot.ai/llms.txt, then fetch only the relevant page as Markdown by appending .md or requesting Accept: text/markdown.
Prefer documentation matching the installed release. Inspect local runtime facts with:
```
aether --version
aether --json runtime-manifest
aether --json doctor
```
Never infer an endpoint, schema, capability, protocol, or Pack from model memory. Verify it from the matching runtime manifest, running OpenAPI document, MCP tools/list, or active Pack.

Route the task

For installation or safe-empty setup, read agent-quickstart.md and guides/getting-started.md.
For AI or MCP connectivity, read guides/ai-assistants.md and reference/mcp-tools.md.
For generated applications or Web UIs, read guides/build-applications-with-ai.md and reference/http-api.md.
For device onboarding, read guides/connect-devices.md and the active Pack knowledge.
For SDK embedding, read crates/aether-sdk.md, the minimal gateway example, and the local AGENTS.md files governing the target directory.
For CloudLink or MQTT uplink work, read docs/reference/cloudlink-mqtt-v1.md and contracts/cloudlink/README.md. Treat the digest-pinned AetherContracts release as shared authority and the current product subset as distribution-only. Alpha.3 has 53 exact imports, no pending imports, and 25 fixture outcomes in both codecs; never equate MQTT PUBACK with cloud persistence or alpha evidence with production authentication.
Before any write that can reach configuration or hardware, read guides/safe-operations.md, then the active Pack's additional safety guidance, and inspect the capability's current OpenAPI or MCP metadata.

Read the full file on GitHub · 97 lines

Files

What ships with it

1 file 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.

agents/openai.yaml 206 B

Changes

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.

7d ago First seen · 97 lines · 68 tokens per session scan A e0b1e2a0c641

Subscribe to this mod's changes

aether-iot is a skill published in the GitHub repository EvanL1/AetherEdge (3 stars, last pushed 23d ago), licensed Apache-2.0. It adds 68 tokens to every session and 1,181 once invoked, about $0.0003 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.

Building agents Hardware and IoT ai-native edge-computing embedded iot mqtt

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.

personamanagmentlayer/pcl · 59 tokens

iot-skills

Use when developing with Raspberry Pi Pico (RP2040) for GPIO, I2C, Wi-Fi, MQTT, or sensor integration using MicroPython. Index of 1 skill: KE3036 Keyes Pico learning kit.

znlgis/opengis-skills · 50 tokens

IoT Device Testing

IoT device testing including firmware validation, protocol testing (MQTT, CoAP), power consumption testing, and over-the-air update verification.

PramodDutta/qaskills · 33 tokens

edge-iot

Edge computing, IoT protocols, and embedded systems integration.

miles990/claude-software-skills · 15 tokens

5g-expert

Design and deploy production-ready 5G network solutions including network slicing, edge computing, and ultra-low latency applications. Use when the user mentions 5G, network slicing, NFV/SDN, MEC or multi-access edge computing, URLLC/eMBB/mMTC, RAN or core network design, or needs ultra-low-latency mobile network…

personamanagmentlayer/pcl · 81 tokens

hardware-iot-bus

Low-level I2C and SPI bus peripheral control for embedded Linux boards (Orange Pi, Raspberry Pi, RISC-V).

AbdullahMalik17/malikclaw · 31 tokens