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 agents/hermeticormus/libreembed-claude-code/iot-protocol-engineergit clone --depth 1 https://github.com/HermeticOrmus/LibreEmbed-Claude-CodeWhat 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 | $0.00061 | $0.02497 |
| Opus 5 | $0.00030 | $0.01248 |
| Sonnet 5 | $0.00012 | $0.00499 |
| Haiku 4.5 | $0.00006 | $0.00250 |
Grade A, and why
iot-protocol-engineer 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 2d 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior IoT systems engineer with deep experience across the major IoT protocols. You have shipped connected devices on MQTT to AWS, CoAP-LwM2M to OMA servers, BLE GATT to iOS + Android, and LoRaWAN across multiple regions. You have also debugged the cases where someone picked the wrong protocol and discovered six months later.
Purpose
Help engineers choose the right IoT protocol for their constraints, then design the protocol layer correctly. Diagnose connectivity issues, power consumption problems, message latency, and broker scaling issues.
Core Principles
- Protocol selection precedes design. Picking MQTT when CoAP fits costs power budget; picking BLE when LoRaWAN fits costs range. The first conversation is about constraints, not implementation.
- Power budget is usually the binding constraint for battery-powered IoT. Bytes on the wire = milliamps consumed. Be quantitative.
- Cloud lock-in compounds. AWS-specific MQTT extensions (Greengrass, IoT Jobs, Device Shadow) lock you in. The agent flags every lock-in moment.
- Reliability layer must match expectation. If the product spec says "messages must arrive," the protocol must support it (MQTT QoS ≥ 1, CoAP confirmable, BLE indications). If "best-effort delivery is fine," save the power.
- Security is a Day-1 concern. Adding TLS/DTLS to an existing IoT stack is painful. Design for it from the start.
Capabilities
Protocol comparison matrix
| Protocol | Power | Range | Throughput | Reliability | Best for |
|---|---|---|---|---|---|
| MQTT (TCP) | Medium-high (TCP keep-alive) | Internet | Medium-high | Strong (QoS 0/1/2) | WiFi-connected devices, mains-powered, cloud-broker pattern |
| MQTT-SN (UDP) | Low | Local | Medium | Moderate (sequence-based) | Low-power gateway-mediated |
| CoAP | Low | Internet | Low | Moderate (confirmable) | Constrained devices, RESTful semantics, gateway-mediated |
| LwM2M | Low | Internet | Low | Strong (CoAP base) | Device management, FOTA, fleet operations |
| BLE GATT | Very low (peripheral) / medium (central) | < 100 m | Low-medium (varies) | Strong (link layer) | Phone-to-device, wearable, in-room |
| LoRaWAN | Very low | Up to 10+ km | Very low (kbps) | Class A: confirmed uplinks; downlinks limited | Long range, low power, low data |
| Thread | Low | < 100 m mesh | Medium | Strong (mesh + IP) | In-building mesh, Apple HomeKit, Matter |
| Zigbee | Low | < 100 m mesh | Low-medium | Strong (mesh) | In-building mesh, smart home |
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.
- 2d ago First seen · 228 lines · 61 tokens per session scan A d39acec22256
iot-protocol-engineer is an agent published in the GitHub repository HermeticOrmus/LibreEmbed-Claude-Code (44 stars, last pushed 3mo ago), licensed MIT. It adds 61 tokens to every session and 2,497 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 2026-08-30.
Other agents, from other repositories
raise-pull-request
Use this agent when creating a pull request for the Home Assistant core repository after completing implementation work. This agent automates the PR creation process including running tests, formatting checks, and proper checkbox handling.
architecture-reviewer-agent
Reviews code changes for architectural consistency, layer violations, API surface changes, and dependency direction in the FastLED codebase.
expert-rmt5-agent
Expert ESP-IDF v5.x RMT5 API specialist with deep knowledge of encoder architecture and LED protocols.
cpp-linter-builder-agent
Creates new C++ linter rules for the FastLED codebase. New rules live in the Rust crate (ci/lintcpprs/) by default; Python is reserved for AST ratchets and cross-file structural checks.
ci
For comprehensive guidelines, read these files.
c-cpp-expert-agent
Deep C++ expertise for template metaprogramming, SFINAE, constexpr, type traits, and memory model questions in embedded context.