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 skills/idea2realclaw/myagent/radxa-sshnpx skills add idea2realClaw/myAgent --skill radxa-sshgit clone --depth 1 https://github.com/idea2realClaw/myAgentWrote 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/idea2realclaw/myagent/radxa-ssh)<a href="https://agentmods.dev/skills/idea2realclaw/myagent/radxa-ssh"><img src="https://agentmods.dev/badge/skills/idea2realclaw/myagent/radxa-ssh.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 | $0.00079 | $0.01390 |
| Opus 5 | $0.00039 | $0.00695 |
| Sonnet 5 | $0.00016 | $0.00278 |
| Haiku 4.5 | $0.00008 | $0.00139 |
Grade D, and why
radxa-ssh scanned grade D with 3 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
### sudo 执行（密码自动传递） Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://get.docker.com | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://get.docker.com | sh How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Radxa SSH Skill v1（2026-04-18）
设备信息
| 项目 | 信息 |
|---|---|
| 设备名 | radxa-dragon-q6a |
| Tailscale IP | 100.92.193.86 |
| SSH 用户 | radxa |
| SSH 密码 | radxa |
| 系统 | Linux aarch64 |
前置条件
macOS 必须安装 sshpass
brew install sshpass
快速连接
连接设备
sshpass -p 'radxa' ssh [email protected]
执行单条命令
sshpass -p 'radxa' ssh [email protected] '<命令>'
sudo 执行（密码自动传递）
echo 'radxa' | sshpass -p 'radxa' ssh -T [email protected] 'sudo -S <命令>'
常用操作
系统信息
# 基本信息
sshpass -p 'radxa' ssh [email protected] 'hostname && uptime && df -h && free -h'
# CPU 信息
sshpass -p 'radxa' ssh [email protected] 'lscpu | grep -E "(Model name|CPU|Architecture)"'
# 网络状态
sshpass -p 'radxa' ssh [email protected] 'ip addr show | grep inet'
Tailscale 状态
sshpass -p 'radxa' ssh [email protected] 'tailscale status'
Docker 操作
# 查看 Docker 版本
sshpass -p 'radxa' ssh [email protected] 'docker --version'
# 查看运行中的容器
sshpass -p 'radxa' ssh [email protected] 'sudo docker ps'
# 查看所有容器
sshpass -p 'radxa' ssh [email protected] 'sudo docker ps -a'
# 查看镜像
sshpass -p 'radxa' ssh [email protected] 'sudo docker images'
# 运行 hello-world
echo 'radxa' | sshpass -p 'radxa' ssh -T [email protected] 'sudo -S docker run hello-world'
# 拉取镜像
echo 'radxa' | sshpass -p 'radxa' ssh -T [email protected] 'sudo -S docker pull ubuntu'
Docker 安装（首次）
如果设备上没有 Docker，执行以下命令安装：
# 登录到设备
sshpass -p 'radxa' ssh [email protected]
# 在设备上执行
curl -fsSL https://get.docker.com | sh
# 退出后配置当前用户（可选）
echo 'radxa' | sshpass -p 'radxa' ssh -T [email protected] 'sudo -S usermod -aG docker radxa'
注意：由于 sudo 密码交互问题，建议使用 echo 'password' | sudo -S command 方式执行 Docker 命令。
文件传输
从 Mac 传到 Radxa
sshpass -p 'radxa' scp ~/local/file.txt [email protected]:/home/radxa/
从 Radxa 传到 Mac
sshpass -p 'radxa' scp [email protected]:/home/radxa/file.txt ~/Downloads/
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 183 lines · 79 tokens per session scan D e60a4460a376
radxa-ssh is a skill published in the GitHub repository idea2realClaw/myAgent (2 stars, last pushed 15d ago), licensed MIT. It adds 79 tokens to every session and 1,390 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
dakota-image
OCI layer assembly, boot testing, installer boundaries, VM work, and local OTA verification for Dakota images.
together-kueue
Install and use the Kueue job-queueing controller on a Together AI Kubernetes GPU cluster to gate jobs on quota. Covers installing Kueue, defining ResourceFlavor, ClusterQueue, and LocalQueue quota, submitting jobs to a queue, and watching quota admit or suspend them. Reach for it when a Together cluster's GPU pool…
xpu-container-run
Launch a Docker container with Intel GPU access on Linux. Encodes the correct combination of --device /dev/dri, render-group access, --ipc=host, ZEAFFINITYMASK pinning, Hugging Face cache mount, and --entrypoint /bin/bash for interactive use. Use when running any Intel-XPU container (vLLM-XPU, sglang-xpu, torch-XPU…
deploy-frigate
Deploy Frigate open-source NVR with real-time TensorRT object detection on NVIDIA Jetson (Nano, Xavier NX, Orin). Uses Docker Compose with the Jetson-optimized Frigate image, YOLOv7 model, and RTSP IP camera streams. Requires JetPack 5.x and Docker.
routeros-container
RouterOS /container subsystem for running OCI containers on MikroTik devices. Use when: enabling containers on RouterOS, setting up VETH/bridge networking for containers, managing container lifecycle via CLI or REST API, building OCI images for RouterOS, configuring container environment variables, troubleshooting…
Infrastructure Development
Enterprise infrastructure patterns for AWS VPC, ECS, and PrivateLink deployments.