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.
curl -O https://raw.githubusercontent.com/smk-h/embedded-mcp-toolkit/main/.claude/skills/setup-file-utils-remote/SKILL.mdgit clone --depth 1 https://github.com/smk-h/embedded-mcp-toolkitWrote 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/smk-h/embedded-mcp-toolkit/setup-file-utils-remote)<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>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 | $0.00087 | $0.03290 |
| Opus 5 | $0.00044 | $0.01645 |
| Sonnet 5 | $0.00017 | $0.00658 |
| Haiku 4.5 | $0.00009 | $0.00329 |
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. 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 $device 由框架参数替换注入。若仍是占位符(用户未带参数),调 device_info_tool(device: "all")列出全部并询问。
调 device_info_tool(device: "$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 $device
调 ssh_shell_login(device: "$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。
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.
- 5d ago First seen · 244 lines · 87 tokens per session scan E c94d2f62346c
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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.
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…
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…