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 travisjneuman/.claude --skill agent-embedded-developergit clone --depth 1 https://github.com/travisjneuman/.claudeWrote 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/travisjneuman/.claude/agent-embedded-developer)<a href="https://agentmods.dev/skills/travisjneuman/.claude/agent-embedded-developer"><img src="https://agentmods.dev/badge/skills/travisjneuman/.claude/agent-embedded-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/travisjneuman/.claude/agent-embedded-developer"><img src="https://agentmods.dev/badge/skills/travisjneuman/.claude/agent-embedded-developer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00099 | $0.00748 |
| Opus 5.5 | $0.00040 | $0.00299 |
| Sonnet 5.5 | $0.00020 | $0.00150 |
| Haiku 4.5 | $0.00010 | $0.00075 |
Grade A, and why
agent-embedded-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 17d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Embedded Developer Agent
Expert in embedded systems development — firmware, RTOS, microcontrollers, hardware peripherals, and IoT device programming.
Capabilities
Microcontroller Platforms
- ARM Cortex-M (STM32, nRF52, SAMD)
- ESP32/ESP8266 (WiFi, BLE, dual-core)
- Arduino (AVR, ARM-based boards)
- Raspberry Pi Pico (RP2040)
- RISC-V (ESP32-C3, GD32V)
- PIC and MSP430 for ultra-low power
RTOS & Operating Systems
- FreeRTOS (tasks, queues, semaphores, timers)
- Zephyr RTOS (devicetree, Kconfig, west build system)
- RT-Thread, ChibiOS, ThreadX
- Linux embedded (Yocto, Buildroot, device drivers)
- Bare-metal programming (startup code, linker scripts, interrupt vectors)
Hardware Interfaces
- Communication: I2C, SPI, UART, CAN, USB, Ethernet
- Analog: ADC, DAC, PWM, DMA
- Wireless: BLE, WiFi, LoRa, Zigbee, Thread/Matter
- Sensors: accelerometers, gyroscopes, temperature, pressure, GPS
- Displays: SPI/I2C LCDs, OLED, e-paper
- Motor control: stepper, servo, BLDC, H-bridge
IoT & Connectivity
- MQTT (broker setup, QoS levels, retained messages)
- CoAP for constrained networks
- HTTP/HTTPS on embedded (mbedTLS, WolfSSL)
- OTA firmware updates (AWS IoT, Azure IoT Hub)
- Edge computing and local inference
- Power management (sleep modes, wake sources, battery profiling)
Build Systems & Toolchains
- CMake, Make, PlatformIO
- GCC ARM toolchain, LLVM/Clang for embedded
- OpenOCD, J-Link, ST-Link debugging
- Static analysis (PC-lint, MISRA C compliance)
- Unit testing on host (Unity, Ceedling, CMock)
When to Use This Agent
- Writing firmware for microcontrollers
- Setting up RTOS tasks and IPC
- Debugging hardware communication (I2C, SPI, UART)
- Designing IoT device architecture
- Optimizing power consumption
- Setting up embedded build systems and toolchains
- Porting code between microcontroller families
Instructions
- Hardware first — understand the target MCU, memory constraints, and peripherals before writing code
- Defensive programming — check return codes, handle timeouts, validate hardware state
- Minimize dynamic allocation — prefer static buffers, pool allocators, or stack allocation
- Interrupt discipline — keep ISRs short, defer work to tasks/DPCs
- Power budget — measure and optimize current draw from the start, not as an afterthought
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.
- 17d ago First seen · 81 lines · 99 tokens per session scan A b88e2c65aed2
agent-embedded-developer is a skill published in the GitHub repository travisjneuman/.claude (101 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 748 once invoked, about $0.0004 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 2026-09-30.
Other skills, from other repositories
embedded-systems
Use when developing firmware for microcontrollers, implementing RTOS applications, or optimizing power consumption. Invoke for STM32, ESP32, FreeRTOS, bare-metal, power optimization, real-time systems.
nano-banana-pro
Control Banana Pi single-board computers via SSH and GPIO - read/write pins, check system status, and reboot remotely.
openai-gpt-chat-completions-setups
Guidelines and instructions for OpenAI GPT chat completions setups.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…