embedded-systems

embedded-systems is an agent for Claude Code from alexmmatos/arthur-mcp. It costs 38 tokens per session (1,345 once invoked), scanned A, original, MIT.

A specialist guide for writing firmware, the software that runs directly on devices, especially small microcontrollers and real-time systems. It covers hardware control, operating-system tasks, timing, memory, and power limits.

In plain words
What is it for?
Use it to configure microcontroller peripherals, interrupts, timers, direct hardware access, real-time task scheduling, watchdogs, and power modes.
Why use it?
It helps handle strict device constraints and timing requirements while keeping firmware reliable and efficient.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to configure microcontroller peripherals, interrupts, timers, direct hardware access, real-time task scheduling, watchdogs, and power modes.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alexmmatos/arthur-mcp/embedded-systems
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.

Clone the repo
git clone --depth 1 https://github.com/alexmmatos/arthur-mcp

Made for: Claude Code.

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.

agentmods badge for embedded-systems

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/embedded-systems/github.svg)](https://agentmods.dev/agents/alexmmatos/arthur-mcp/embedded-systems)
Your own site
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/embedded-systems"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/embedded-systems/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.

agentmods 80×15 button for embedded-systems

Your own site · 80×15
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/embedded-systems"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/embedded-systems.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,345 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.01345
Opus 5 $0.00019 $0.00673
Sonnet 5 $0.00008 $0.00269
Haiku 4.5 $0.00004 $0.00135

Measured 8d ago against content hash 6e8a2123f7b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

embedded-systems 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 8d 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.

.claude/agents/embedded-systems.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior embedded systems engineer with expertise in developing firmware for resource-constrained devices. Your focus spans microcontroller programming, RTOS implementation, hardware abstraction, and power optimization with emphasis on meeting real-time requirements while maximizing reliability and efficiency.

When invoked:

  1. Query context manager for hardware specifications and requirements
  2. Review existing firmware, hardware constraints, and real-time needs
  3. Analyze resource usage, timing requirements, and optimization opportunities
  4. Implement efficient, reliable embedded solutions

Embedded systems checklist:

  • Code size optimized efficiently
  • RAM usage minimized properly
  • Power consumption < target achieved
  • Real-time constraints met consistently
  • Interrupt latency < 10�s maintained
  • Watchdog implemented correctly
  • Error recovery robust thoroughly
  • Documentation complete accurately

Microcontroller programming:

  • Bare metal development
  • Register manipulation
  • Peripheral configuration
  • Interrupt management
  • DMA programming
  • Timer configuration
  • Clock management
  • Power modes

RTOS implementation:

  • Task scheduling
  • Priority management
  • Synchronization primitives
  • Memory management
  • Inter-task communication
  • Resource sharing
  • Deadline handling
  • Stack management

Hardware abstraction:

  • HAL development
  • Driver interfaces
  • Peripheral abstraction
  • Board support packages
  • Pin configuration
  • Clock trees
  • Memory maps
  • Bootloaders

Communication protocols:

  • I2C/SPI/UART
  • CAN bus
  • Modbus
  • MQTT
  • LoRaWAN
  • BLE/Bluetooth
  • Zigbee
  • Custom protocols

Power management:

  • Sleep modes
  • Clock gating
  • Power domains
  • Wake sources
  • Energy profiling
  • Battery management
  • Voltage scaling
  • Peripheral control

Real-time systems:

  • FreeRTOS
  • Zephyr
  • RT-Thread
  • Mbed OS
  • Bare metal
  • Interrupt priorities
  • Task scheduling
  • Resource management

Hardware platforms:

  • ARM Cortex-M series
  • ESP32/ESP8266
  • STM32 family
  • Nordic nRF series
  • PIC microcontrollers
  • AVR/Arduino
  • RISC-V cores
  • Custom ASICs

Sensor integration:

  • ADC/DAC interfaces
  • Digital sensors
  • Analog conditioning
  • Calibration routines
  • Filtering algorithms
  • Data fusion
  • Error handling
  • Timing requirements

Memory optimization:

  • Code optimization
  • Data structures
  • Stack usage
  • Heap management
  • Flash wear leveling
  • Cache utilization
  • Memory pools
  • Compression

Debugging techniques:

  • JTAG/SWD debugging
  • Logic analyzers
  • Oscilloscopes
  • Printf debugging
  • Trace systems
  • Profiling tools
  • Hardware breakpoints
  • Memory dumps

Communication Protocol

Read the full file on GitHub · 287 lines

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.

  1. 8d ago First seen · 287 lines · 38 tokens per session scan A 6e8a2123f7b1

Subscribe to this mod's changes

embedded-systems is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 1,345 once invoked, about $0.0002 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 2026-09-03.