embedded-mcp-toolkit: Skill for Claude Code

.claude/skills/setup-file-utils-remote/SKILL.md

setup-file-utils-remote is a skill for Claude Code from smk-h/embedded-mcp-toolkit. It costs 87 tokens per session (3,290 once invoked), scanned E, original, MIT.

A setup procedure for connecting a build server to a remote file-operation MCP service without repeatedly entering an SSH password. MCP is a standard way for an AI agent to call external tools.

In plain words
What is it for?
Use it to configure a named device, create or reuse a dedicated SSH key, install the remote file tool, find its path, and write the MCP client configuration.
Why use it?
MCP clients use standard input and output for their messages, so they cannot pause to ask for an interactive SSH password. The procedure prepares key-based access and installs and configures the remote tool.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions OpenCode.

This is smk-h/embedded-mcp-toolkit's own configuration. It tells Claude Code how to work on embedded-mcp-toolkit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything embedded-mcp-toolkit configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is mkdir -p /tmp/fum-install && tar -xzf /tmp/file-utils-mcp-toolkit-1.0.0-linux-x64-offline.tar.gz -C /tmp/fum-install && bash /tmp/fum-install/offline_install.sh.

Reuse

Borrowing it

Nothing to install: this file belongs to smk-h/embedded-mcp-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/smk-h/embedded-mcp-toolkit/main/.claude/skills/setup-file-utils-remote/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/smk-h/embedded-mcp-toolkit

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 setup-file-utils-remote

README.md
[![agentmods](https://agentmods.dev/badge/skills/smk-h/embedded-mcp-toolkit/setup-file-utils-remote.svg)](https://agentmods.dev/skills/smk-h/embedded-mcp-toolkit/setup-file-utils-remote)
Your own site
<a href="https://agentmods.dev/skills/smk-h/embedded-mcp-toolkit/setup-file-utils-remote"><img src="https://agentmods.dev/badge/skills/smk-h/embedded-mcp-toolkit/setup-file-utils-remote.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,290 The whole file, excluding the scripts and references it only reads on demand.
Security scan E 3 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 $0.00087 $0.03290
Opus 5 $0.00044 $0.01645
Sonnet 5 $0.00017 $0.00658
Haiku 4.5 $0.00009 $0.00329

Measured 5d ago against content hash c94d2f62346c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade E, and why

setup-file-utils-remote scanned grade E 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 5d 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.

> 脚本内置权限检查:`npm prefix -g` 不可写时报错并提示用 `sudo bash offline_install.sh`。

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

mkdir -p ~/.ssh && chmod 700 ~/.ssh && echo '<PUBKEY>' >> ~/.ssh/authorized_keys && chmod 600 ~/.ssh/authorized_keys && sort -u ~/.ssh/authorized_keys -o ~/.ssh/authorized_keys && echo PUBKEY_OK

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

mkdir -p /tmp/fum-install && tar -xzf /tmp/file-utils-mcp-toolkit-1.0.0-linux-x64-offline.tar.gz -C /tmp/fum-install && bash /tmp/fum-install/offline_install.sh && rm -rf /tmp/fum-install /tmp/file-utils-mcp-toolkit-1.0.
.claude/skills/setup-file-utils-remote/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

配置 file_utils_remote 远程文件 MCP

核心思路

两层 SSH 各司其职:用嵌入式 MCP(ssh_shell_login,密码登录,带 PTY)一次性引导配好密钥免密 + 顺带查 bin 路径;之后系统 ssh(密钥免密,无 PTY)才是 MCP client 的长期通道。MCP client spawn ssh 时不分配 PTY、stdin/stdout 被 JSON-RPC 占用,无法交互输密码,必须提前配好免密。

动态值收集

全流程收集以下值,第六步写配置时一次性替换占位符,之前各步只拿值不写配置:

  • <USER>@<HOST>:第一步从 device_info_tool 解析(连接目标)。
  • <BIN_DIR_REL>:第四步从嵌入式 session(带 PTY)查到的 bin 目录相对家目录的路径,如 .npm-global/bin
  • <INSTALL_FAILED>:第四步安装失败时置 true(初始 false),用于第七步末尾提示。

专用密钥路径固定 ~/.ssh/id_file_utils_remote(非动态值)。

步骤

第一步:解析设备连接信息

设备名 $device 由框架参数替换注入。若仍是占位符(用户未带参数),调 device_info_tooldevice: "all")列出全部并询问。

device_info_tooldevice: "$device")取 SSH 配置,记录 <HOST>(ssh.host)、<USER>(ssh.username),派生 <USER>@<HOST>

第二步:检查本地密钥对(无则生成)

ls ~/.ssh/id_file_utils_remote ~/.ssh/id_file_utils_remote.pub 2>/dev/null
  • 已存在 → 复用,绝不覆盖(会破坏已配好的免密信任)。不存在 → 生成(passphrase 留空):
ssh-keygen -t ed25519 -f ~/.ssh/id_file_utils_remote -N "" -C "file-utils-remote"

读取公钥内容备用(cat ~/.ssh/id_file_utils_remote.pub)。

第三步:用嵌入式 MCP 登录 $device

ssh_shell_logindevice: "$device", timeout: 30),取 session_id

此 session 带 PTY,PATH 已加载全局 bin——第四步要趁它开着查 bin 路径,关闭后用系统 ssh 无 PTY 查会落空。

第四步:推送公钥 + 查 bin 路径(同一 session)

先推送公钥ssh_shell_exec<PUBKEY> 替换为第二步读到的公钥,单引号包裹):

mkdir -p ~/.ssh && chmod 700 ~/.ssh && echo '<PUBKEY>' >> ~/.ssh/authorized_keys && chmod 600 ~/.ssh/authorized_keys && sort -u ~/.ssh/authorized_keys -o ~/.ssh/authorized_keys && echo PUBKEY_OK

查 bin 路径(同一 session):

which file-utils-mcp-toolkit; echo "---"; echo $HOME
  • which 命中 → bin 路径去掉文件名、再去掉 $HOME 前缀,得 <BIN_DIR_REL>(如 .npm-global/bin);bin 不在家目录下则用绝对目录。
  • which 无输出 → 远端未安装,走 4a/4b,装完重查。

第四步分支:远端未安装时自动安装(不中断)

优先用本地离线包(SFTP 上传 + offline_install.sh),离线包不存在才 npm i -g 在线兜底。安装失败只记 <INSTALL_FAILED>=true、不中断——免密与配置不依赖远端是否已装好,第五~七步照走。

离线包路径(固定):.embedded/file-utils-mcp-toolkit-1.0.0-linux-x64-offline.tar.gz

Read the full file on GitHub · 244 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. 5d ago First seen · 244 lines · 87 tokens per session scan E c94d2f62346c

Subscribe to this mod's changes

setup-file-utils-remote is a skill published in the GitHub repository smk-h/embedded-mcp-toolkit (0 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 3,290 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it E with 3 findings (asks for root, reaches for credential files, recursive force delete). 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens