What is embedded-linux?

A command for building and debugging Linux systems on embedded computer boards, including Yocto and Buildroot configurations, device-tree files, kernel modules, and cross-compilation. Cross-compilation means building software on one computer for a different processor.

Use it to generate a Yocto or Buildroot build, create flashing commands, scaffold Linux kernel modules, and produce commands for inspecting logs and device files.

It reduces the setup work needed to create a small Linux system for a specific board and to interact with its hardware. It also provides commands for putting the resulting system on storage or debugging it on the device.

embedded-linux — Command for Claude Code by HermeticOrmus

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/HermeticOrmus/LibreEmbed-Claude-Code

Made for: Claude Code.

Or install embedded-linux, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 agent.

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/commands/hermeticormus/libreembed-claude-code/embedded-linux/github.svg)](https://agentmods.dev/commands/hermeticormus/libreembed-claude-code/embedded-linux)

Your own site

<a href="https://agentmods.dev/commands/hermeticormus/libreembed-claude-code/embedded-linux"><img src="https://agentmods.dev/badge/commands/hermeticormus/libreembed-claude-code/embedded-linux/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/hermeticormus/libreembed-claude-code/embedded-linux"><img src="https://agentmods.dev/badge/commands/hermeticormus/libreembed-claude-code/embedded-linux.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 795 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	$0.00023	$0.00795
Opus 5.5	$0.00009	$0.00318
Sonnet 5.5	$0.00005	$0.00159
Haiku 4.5	$0.00002	$0.00080

Measured 15d ago against content hash f68c7ff39a85, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

embedded-linux 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 15d 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.

plugins/embedded-linux/commands/embedded-linux.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.

/embedded-linux

Embedded Linux command: Yocto/Buildroot builds, device tree, kernel modules, cross-compilation.

Trigger

/embedded-linux <action> [options]

Actions

`build`

Generate Yocto or Buildroot configuration for a target.

/embedded-linux build --bsp imx6ul --distro yocto --image core-image-minimal
/embedded-linux build --bsp raspberrypi4 --distro yocto --image core-image-full-cmdline
/embedded-linux build --target stm32mp157 --system buildroot --libc musl

`flash`

Generate flashing commands for the target.

/embedded-linux flash --tool bmaptool --image core-image-minimal-imx6ul.wic.bmap
/embedded-linux flash --tool dd --image sdcard.img --device /dev/sdb
/embedded-linux flash --tool u-boot-tftp --ip 192.168.1.100

`module`

Generate a Linux kernel module skeleton.

/embedded-linux module --type platform --name mydriver --bus i2c
/embedded-linux module --type char --name mychar --major 240
/embedded-linux module --type spi --name myspi --compatible "myorg,mysensor"

`debug`

Generate debug commands for a running embedded Linux system.

/embedded-linux debug --dmesg-filter mydriver
/embedded-linux debug --sysfs-path /sys/bus/i2c/devices/
/embedded-linux debug --ftrace-function mydev_probe

Process

Confirm target SoC and available BSP layers.
Set MACHINE and DISTRO in local.conf.
Create a custom layer for project-specific recipes.
Use devtool for iterative recipe development.
Test with QEMU before physical hardware when possible.

Output Examples

local.conf additions

# Build directory: conf/local.conf
MACHINE = "imx6ul-var-dart"
DISTRO = "poky"
BB_NUMBER_THREADS ?= "${@oe.utils.cpu_count()}"
PARALLEL_MAKE ?= "-j ${@oe.utils.cpu_count()}"
PACKAGE_CLASSES = "package_ipk"
EXTRA_IMAGE_FEATURES ?= "debug-tweaks ssh-server-openssh"
IMAGE_INSTALL:append = " myapp htop strace"

Device tree overlay apply (runtime)

# On target (overlayfs mounted at /boot/overlays/)
dtoverlay mysensor-overlay
# or via U-Boot:
setenv fdtoverlays /overlays/mysensor-overlay.dtbo

Read the full file on GitHub · 97 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.

15d ago First seen · 97 lines · 23 tokens per session scan A f68c7ff39a85

Subscribe to this mod's changes

embedded-linux is a command published in the GitHub repository HermeticOrmus/LibreEmbed-Claude-Code (50 stars, last pushed 6d ago), licensed MIT. It adds 23 tokens to every session and 795 once invoked, about $0.0001 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 2026-10-01.

Claude Code Cloud DevOps and cloud Hardware and IoT arm-cortex-m bare-metal claude embedded iot

splunk-observability-cisco-ai-pod-integration

Deploy Splunk Observability Cloud for a Cisco AI Pod via the umbrella that composes splunk-observability-cisco-nexus-integration, splunk-observability-cisco-intersight-integration, and splunk-observability-nvidia-gpu-integration via subprocess + Python deep-merge, then adds AI-Pod-specific blocks: NIM, vLLM, Milvus…

chambear2809/splunk-cisco-skills · 0 tokens

embedded-linux