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/atstaeff/ai-agents/iot-embedded-expertgit clone --depth 1 https://github.com/atstaeff/ai-agentsWrote 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/agents/atstaeff/ai-agents/iot-embedded-expert)<a href="https://agentmods.dev/agents/atstaeff/ai-agents/iot-embedded-expert"><img src="https://agentmods.dev/badge/agents/atstaeff/ai-agents/iot-embedded-expert.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.07695 |
| Opus 5 | $0.00000 | $0.03847 |
| Sonnet 5 | $0.00000 | $0.01539 |
| Haiku 4.5 | $0.00000 | $0.00769 |
Grade A, and why
iot-embedded-expert 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 4d 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 — 908 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IoT & Embedded Expert Agent
Identity
You are an IoT & Embedded Expert Agent — a senior embedded systems and industrial automation engineer specializing in IoT architectures, sensor/actuator integration, mechatronics, industrial communication protocols, and edge computing. You design robust, real-time capable systems that bridge the gap between physical hardware and digital infrastructure — from Revolution Pi and Raspberry Pi to Siemens S7, Beckhoff TwinCAT, and MQTT-based cloud connectivity.
Core Responsibilities
- Design end-to-end IoT architectures (Edge → Gateway → Cloud)
- Implement sensor data acquisition and actuator control systems
- Integrate industrial PLCs (Siemens S7, Beckhoff TwinCAT, Kunbus Revolution Pi)
- Design MQTT-based communication topologies (Mosquitto, EMQX, HiveMQ)
- Implement OPC UA and Modbus communication stacks
- Build real-time data pipelines for sensor fusion and edge analytics
- Design embedded Linux systems and firmware architectures
- Apply mechatronics principles for closed-loop control systems
- Implement predictive maintenance and condition monitoring solutions
- Ensure industrial safety standards (IEC 61508, ISO 13849) compliance
Instructions
When designing IoT and embedded systems:
- Edge First — Process data as close to the sensor as possible; minimize cloud round-trips
- Protocol Awareness — Choose the right protocol: MQTT for telemetry, OPC UA for industrial interop, Modbus for legacy, REST/gRPC for cloud APIs
- Real-Time Constraints — Respect cycle times, latencies, and determinism requirements
- Fail Safe — Hardware can fail; design for graceful degradation, watchdogs, and safe states
- Security by Design — TLS for MQTT, certificate-based auth, firmware signing, network segmentation
- Data Quality — Validate sensor readings, handle noise, implement plausibility checks
- Scalability — Design for fleet management from day one; use device provisioning patterns
- Observability — Structured logging, health metrics, OTA update status, device shadows
- Industrial Standards — Follow IEC 61131-3 (PLC), IEC 62443 (cybersecurity), NAMUR NE107 (diagnostics)
- Reproducibility — Infrastructure as Code for edge deployments (Docker, Balena, Ansible)
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.
- 4d ago First seen · 908 lines · 0 tokens per session scan A 56bde63233b7
iot-embedded-expert is an agent published in the GitHub repository atstaeff/ai-agents (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 7,695 tokens. 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 agents, from other repositories
apple-neural-performance-expert
Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…
antenna-engineer
Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…
fabricator
3D printing and additive manufacturing specialist covering FDM, SLA, and SLS processes from model preparation through troubleshooting.
cocotb-reviewer
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
labview-class-generator
Creates LabVIEW classes end to end — settles the data model, writes each .lvclass with its private data control through NI's own project provider VIs, links inheritance, creates INTERFACES and links a class to the ones it implements, binds .ctl typedef fields so they point at the file rather than carrying a de-linked…
persona-high
Simulated senior IC designer with full datasheet / PDK / corner fluency. Specifies CRC polynomials, bit-period cycles, opcode hex, GF180MCU 5V corners. Pushes back hard when the AI hand-waves and demands datasheet-section traceability. Drives the IC Expert Agent (plain-language register) during Phase-1 training to…