dev-upgrade

dev-upgrade is a skill for Claude Code, Codex from smk-h/embedded-mcp-toolkit. It costs 123 tokens per session (2,278 once invoked), scanned A, original, MIT.

A workflow for updating a device board’s Linux kernel or firmware. It compiles the kernel on one board while connecting to another board over a serial connection and preparing its U-Boot startup console.

In plain words
What is it for?
Use it when rebuilding and flashing a kernel or firmware update to board-b, including compiling on board-ubuntu, checking U-Boot information, and restarting the target after a successful build.
Why use it?
Kernel compilation can take a long time, while the target board can be prepared at the same time. If compilation fails, the board stays in U-Boot so the problem can be investigated manually.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/smk-h/embedded-mcp-toolkit/dev-upgrade
Any agent
npx skills add smk-h/embedded-mcp-toolkit --skill dev-upgrade
Clone the repo
git clone --depth 1 https://github.com/smk-h/embedded-mcp-toolkit

Made for: Claude Code, Codex.

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 dev-upgrade

README.md
[![agentmods](https://agentmods.dev/badge/skills/smk-h/embedded-mcp-toolkit/dev-upgrade.svg)](https://agentmods.dev/skills/smk-h/embedded-mcp-toolkit/dev-upgrade)
Your own site
<a href="https://agentmods.dev/skills/smk-h/embedded-mcp-toolkit/dev-upgrade"><img src="https://agentmods.dev/badge/skills/smk-h/embedded-mcp-toolkit/dev-upgrade.svg" alt="Measured on agentmods" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,278 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00123 $0.02278
Opus 5 $0.00062 $0.01139
Sonnet 5 $0.00025 $0.00456
Haiku 4.5 $0.00012 $0.00228

Measured 4d ago against content hash 97ad6c1ec3cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

dev-upgrade 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.

.claude/skills/dev-upgrade/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

任务

在 board-ubuntu 上编译内核的同时,在 board-b 上通过串口登录并进入 U-Boot 命令行。编译完成后根据结果决定后续操作:成功则在 U-Boot 下获取信息并重启,失败则保持 U-Boot 状态。

背景

内核编译是耗时操作。利用 code-build 子 agent 在 board-ubuntu 上后台执行编译,与此同时主 agent 在 board-b 串口上并行完成登录、系统信息采集和 U-Boot 进入,从而最大化并行效率。

步骤

并行原理(核心):Claude Code 的 Agent 工具默认是阻塞的——会同步等待子 agent 执行完才返回。要实现"编译与串口操作并行",启动 code-build 时必须传 run_in_background: true:它调用后立即返回一个 task_id,子 agent 在后台编译,主 agent 转身去做串口的活。编译完成后系统自动发 task-notification 通知主 agent,再用 TaskOutput 取回结果。

第一步:启动编译子 agent(后台异步)

  1. 单独调用 Agent 工具启动 code-build 子 agent,并设 run_in_background: true

    参数:

    • description"编译 board-ubuntu 内核"
    • subagent_type"code-build"
    • run_in_backgroundtrue
    • prompt(将以下内容整体作为 prompt 参数传入):
    请登录 board-ubuntu 并在 ~/workspace/Alpha/kernel 目录下执行编译:
    1. 使用 ssh_shell_login 登录 board-ubuntu(device: "board-ubuntu")
    2. 使用 ssh_build 在 ~/workspace/Alpha/kernel 目录执行命令:./build.sh alpha -a -c
       - cwd 设为 "~/workspace/Alpha/kernel"
       - command 设为 "./build.sh alpha -a -c"
       - maxWait 设为 1800000(30 分钟,内核编译可能很久)
    3. 编译结束后,使用 ssh_shell_close 关闭会话
    4. 返回编译结果(成功/失败),如果有错误请列出关键错误信息,如果有警告请列出警告摘要
    

    调用后 Agent 立即返回一个 task_id(务必记下它),子 agent 在后台开始编译。不要同步等待结果,继续执行下一步。

第二步:串口登录 board-b(编译在后台进行中)

  1. 单独调用 serial_shell_login 登录 board-b
    • device 设为 "board-b"
    • 从返回结果中获取 session_id(如 serial_1

第三步:获取系统信息并进入 U-Boot(编译仍在后台进行)

  1. 获取 board-b 系统信息

    • 单独调用 serial_exec,使用步骤 2 的 session_id,执行以下命令(delay 设为 3000):
    echo "=== Hostname ===" && hostname && echo "=== Kernel ===" && uname -a && echo "=== Uptime ===" && uptime && echo "=== Memory ===" && free -h && echo "=== Disk ===" && df -h /
    
    • 记录并格式化输出系统信息
  2. 进入 U-Boot

    • 单独调用 serial_enter_uboot,使用步骤 2 的 session_id
    • timeout 设为 120(秒)
    • 确认已进入 U-Boot 命令行(出现 =>U-Boot> 提示符)

第四步:等待编译结果并处理

  1. 取回后台编译结果
    • 此时主 agent 已完成串口端的所有准备工作(已进入 U-Boot)
    • 调用 TaskOutput 取回第一步的 task_id 对应的结果:task_id 传入后台任务 id,block 设为 true 阻塞等待编译完成,timeout 设为 600000(10 分钟)。
    • 若一次 TaskOutput 返回任务仍未结束(编译超 10 分钟),再次调用 TaskOutput 继续等待,直到拿到 code-build 的最终汇报文本。
    • 也可在收到该 task_id 的 task-notification 通知后,再调用一次 TaskOutputblock 可为 false)取回完整结果。

Read the full file on GitHub · 134 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. 4d ago First seen · 134 lines · 123 tokens per session scan A 97ad6c1ec3cf

Subscribe to this mod's changes

dev-upgrade is a skill published in the GitHub repository smk-h/embedded-mcp-toolkit (0 stars, last pushed yesterday), licensed MIT. It adds 123 tokens to every session and 2,278 once invoked, about $0.0006 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 2026-08-31.

Related

Other skills, from other repositories

integrated-browser

Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.

microsoft/vscode · 68 tokens

gke-compute-classes

Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…

google/skills · 83 tokens

jetson-diagnostic

Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.

NVIDIA/skills · 30 tokens

doca-socket-relay

Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…

NVIDIA/skills · 236 tokens

offensive-z-wave

Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…

SnailSploit/Claude-Red · 113 tokens

hsb-flash

Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…

NVIDIA/skills · 94 tokens