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 instructions/hydrocoderclaud/mcphydrossh/claude-mdgit clone --depth 1 https://github.com/hydroCoderClaud/mcpHydroSSHWrote 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/instructions/hydrocoderclaud/mcphydrossh/claude-md)<a href="https://agentmods.dev/instructions/hydrocoderclaud/mcphydrossh/claude-md"><img src="https://agentmods.dev/badge/instructions/hydrocoderclaud/mcphydrossh/claude-md.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 | $0.01419 | $0.01419 |
| Opus 5 | $0.00709 | $0.00709 |
| Sonnet 5 | $0.00284 | $0.00284 |
| Haiku 4.5 | $0.00142 | $0.00142 |
Grade A, and why
mcpHydroSSH CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
| Command | Description |
|---|---|
npm install |
Install dependencies |
npm run build |
Build the TypeScript project (output to dist/) |
npm run dev |
Run in development mode with tsx watch |
npm start |
Run the compiled server from dist/index.js |
npm test |
Run tests with Vitest |
npm run lint |
Run ESLint |
npm run format |
Format code with Prettier |
Project Overview
mcpHydroSSH is an MCP (Model Context Protocol) server that provides SSH capabilities to Claude Code. It allows connecting to remote servers, executing commands, and maintaining persistent SSH connections.
Published:
- npm: https://www.npmjs.com/package/mcp-hydrocoder-ssh
- GitHub: https://github.com/hydroCoderClaud/mcpHydroSSH
High-Level Architecture
Core Components
-
MCP Server Layer (
src/index.ts- 724 lines)- Exposes 10 MCP tools
- Uses
@modelcontextprotocol/sdkfor stdio transport - Entry point:
#! /usr/bin/env node
-
SSH Manager (
src/ssh-manager.ts- 349 lines)SSHManagerclass manages multiple SSH connections- Connection pool:
Map<connectionId, SSHConnection> - Tracks
lastConnectionIdfor default connection behavior - Handles connection lifecycle, command execution, timeouts
-
Config Layer (
src/config.ts- 203 lines)- Loads and validates config from
~/.claude/ssh-mcp-config.json - Uses Zod schema validation
- Provides server config lookup by ID
- Supports add/remove/update server operations
- Loads and validates config from
-
Type Definitions (
src/types.ts- 65 lines)ServerConfig: Server connection detailsConfig: Full config with servers and settingsSSHConnection: Active connection stateExecResult: Command execution resultConnectionStatus: Status info for MCP responses
MCP Tools (10)
| Tool | Parameters | Description |
|---|---|---|
ssh_list_servers |
None | List configured servers |
ssh_connect |
serverId, timeout? |
Connect to server |
ssh_exec |
command, connectionId?, timeout?, cwd? |
Execute command |
ssh_get_status |
connectionId? |
Get connection status |
ssh_disconnect |
connectionId? |
Disconnect from server |
ssh_view_config |
None | View config (filters sensitive info) |
ssh_help |
topic? |
Show help information |
ssh_add_server |
Server config fields | Add server configuration |
ssh_remove_server |
serverId |
Remove server configuration |
ssh_update_server |
serverId + fields |
Update server configuration |
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 · 154 lines · 1,419 tokens per session scan A 1f796a50758e
mcpHydroSSH CLAUDE.md is an instructions file published in the GitHub repository hydroCoderClaud/mcpHydroSSH (6 stars, last pushed 5mo ago), licensed MIT. It adds 1,419 tokens to every session, about $0.0071 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.
Other instructions, from other repositories
platform AGENTS.md
AGENTS.md instructions for doka-guide/platform, covering agents.md — как работать с платформой доки, 1. правила работы, сначала подумай, потом пиши, минимум кода and правки хирургические.
zapo CLAUDE.md
Instructions for vinikjkkj/zapo: The contributor handbook for this repository lives in AGENTS.md. Read that file and follow it as your primary source of project conventions, architecture rules, performance constraints, and review anti-patterns.
Silex AGENTS.md
AGENTS.md instructions for silexlabs/Silex, covering agents.md, tech stack, run it locally, building the desktop app and when writing code for silex (editing source).
SoDam-WikiMate AGENTS.md
AGENTS.md instructions for sodam-ai/SoDam-WikiMate, covering wikimate 작업 규칙 (크로스툴 — claude code · codex · gemini 공용), 문체, 자동 동작 (자연어 트리거 — 강제 호출 불필요), 접근 규칙 (자동 감지 — 특정 도구에 한정하지 않음) and obsidian 규칙.
hal-9000 AGENTS.md
Instructions for vinta/hal-9000, covering agents.md, commands, gotchas, external tool documentation and context7 library ids.
node-express-boilerplate typescript-assertions.instructions.md
Use when editing TypeScript in src to avoid assertion-related lint/type regressions after merges. Prefer narrowing, type guards, satisfies, and as const/typeof over unsafe casts.