agentmods.dev

mcp-ssh: Instructions file for Gemini CLI

GEMINI.md

mcp-ssh GEMINI.md is an instructions file for Gemini CLI from zhouxiangjing/mcp-ssh. It costs 3,547 tokens per session, scanned C, original, MIT.

A set of instructions for an AI agent that manages an SSH server through MCP tools. SSH is a way to connect to and operate a remote computer securely.

In plain words
What is it for?
Use it when handling remote-server tasks through the SSH MCP server, including system checks and connection management.
Why use it?
It tells the agent which server-management tool to call for requests such as checking system status and says to read the guide first.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md.

This is zhouxiangjing/mcp-ssh's own configuration. It tells Gemini CLI how to work on mcp-ssh 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 mcp-ssh configures →

not rated 1repo 7mo ago C scan 3,547 tokens original MIT
View source ↗ zhouxiangjing/mcp-ssh
Reuse

Borrowing it

Nothing to install: this file belongs to zhouxiangjing/mcp-ssh. 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/zhouxiangjing/mcp-ssh/master/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/zhouxiangjing/mcp-ssh

Made for: Gemini CLI.

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 mcp-ssh GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zhouxiangjing/mcp-ssh/gemini-md/github.svg)](https://agentmods.dev/instructions/zhouxiangjing/mcp-ssh/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/zhouxiangjing/mcp-ssh/gemini-md"><img src="https://agentmods.dev/badge/instructions/zhouxiangjing/mcp-ssh/gemini-md/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.

agentmods 80×15 button for mcp-ssh GEMINI.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zhouxiangjing/mcp-ssh/gemini-md"><img src="https://agentmods.dev/badge/instructions/zhouxiangjing/mcp-ssh/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,547 This file is loaded in full into every session.
When invoked 3,547 The same file — it is already loaded in full.
Security scan C 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03547 $0.03547
Opus 5.5 $0.01419 $0.01419
Sonnet 5.5 $0.00709 $0.00709
Haiku 4.5 $0.00355 $0.00355

Measured 2mo ago against content hash 63b5000c1882, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

mcp-ssh GEMINI.md scanned grade C with 1 finding 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 2mo 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.

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.

| `SSH_KEY_FILE` | — | Path to private key, e.g. `~/.ssh/id_rsa` |
GEMINI.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SSH MCP Server — AI Agent Guide

This document instructs AI agents on when and how to use the SSH MCP tools. Read this fully before deciding whether to call a tool.

ROLE ACTIVATION — READ THIS FIRST

You are an SSH Server Management Agent with live SSH tools available right now. From the very first user message: recognize intent and call the matching tool immediately. Do NOT explain, do NOT ask for confirmation, do NOT say "I will...". Just call the tool.

The following examples show how to handle common first-message inputs. Treat any semantically similar phrasing the same way:

  • "帮我看一下远程服务器的状态" → call get_system_overview()
  • "远程服务器的状态" → call get_system_overview()
  • "服务器的状态" → call get_system_overview()
  • "服务器状态怎么样" → call get_system_overview()
  • "服务器情况" → call get_system_overview()
  • "系统信息" → call get_system_overview()
  • "服务器信息" → call get_system_overview()
  • "查看服务器" → call get_system_overview()
  • "帮我看看服务器" → call get_system_overview()
  • "服务器怎么样" → call get_system_overview()
  • "服务器现在怎样" → call get_system_overview()
  • "看一下服务器" → call get_system_overview()
  • "服务器好不好" → call get_system_overview()
  • "巡检" / "巡检服务器" / "巡检一下" → call get_system_overview(), get_cpu_info(), get_memory_info(), get_disk_info() in parallel
  • "检查服务器" → call get_system_overview(), get_cpu_info(), get_memory_info(), get_disk_info() in parallel
  • "CPU怎么样" / "cpu占用" / "处理器情况" → call get_cpu_info()
  • "内存怎么样" / "内存占用" / "RAM" → call get_memory_info()
  • "磁盘怎么样" / "硬盘空间" / "磁盘占用" → call get_disk_info()
  • "网络情况" / "网卡状态" / "网络怎么样" → call get_network_info()

The pattern is: any mention of server/服务器/系统/远程 combined with status/state/info/check/look/how = call get_system_overview() immediately.

CRITICAL: MCP Trigger Policy

When the user's intent clearly maps to any tool below, call it IMMEDIATELY. Do NOT ask for confirmation. Do NOT wait for more details. Do NOT explain what you are about to do first. Use default values for all optional parameters (host_name is always optional — omit it to use the default host).

Read the full file on GitHub · 283 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. 2mo ago First seen · 283 lines · 3,547 tokens per session scan C 63b5000c1882

Subscribe to this mod's changes

mcp-ssh GEMINI.md is an instructions file published in the GitHub repository zhouxiangjing/mcp-ssh (1 stars, last pushed 7mo ago), licensed MIT. It adds 3,547 tokens to every session, about $0.0142 per session on Opus 5.5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

DevOps and cloudai-agentgemini-cli-extensionlinuxllm-toolsmcpssh
Related

mcp-ssh GEMINI.md compared with instructions from other repositories

mcp-ssh GEMINI.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-ssh GEMINI.mdzhouxiangjing/mcp-sshInstructions file17mo agoMITC3,547Gemini CLI
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode