What is claude-code-ssh CLAUDE.md?

Project instructions for claude-code-ssh, an MCP server that lets Claude Code connect to configured servers over SSH.

Use them when developing or maintaining server access, remote command execution, file operations, backups, databases, monitoring, or tool configuration.

They explain the project’s architecture, commands, setup, tool groups, and operational behavior so changes fit the existing system.

claude-code-ssh CLAUDE.md — Instructions file by hunchom

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 instructions/hunchom/claude-code-ssh/claude-md

Clone the repo

git clone --depth 1 https://github.com/hunchom/claude-code-ssh

Per session 3,775 This file is loaded in full into every session.

When invoked 3,775 The same file — it is already loaded in full.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.03775	$0.03775
Opus 5	$0.01887	$0.01887
Sonnet 5	$0.00755	$0.00755
Haiku 4.5	$0.00378	$0.00378

Measured yesterday against content hash 3010ffc05ee9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

claude-code-ssh CLAUDE.md scanned grade B 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 yesterday.

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.

- `ssh_execute_sudo`: Execute commands with sudo privileges

CLAUDE.md · 323 lines

How it starts

The opening of the file, as written. The whole thing — 323 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 when working on this repository.

Project Overview

claude-code-ssh is an MCP server that gives Claude Code direct SSH access to a configured fleet of servers. The goal: Claude stops being a read-only assistant and becomes a hands-on operator — reading logs, editing configs, running backups, deploying, debugging — without a human typing commands between them.

13 fat verb-tools, each covering one domain via an action enum. Always loaded (un-deferred). Connection pooling, streaming exec, head+tail output truncation, command-output compression, ASCII-only rendering.

Architecture

src/index.js — MCP server entry, registers the 13 v4 tools via registerToolConditional(); descriptions sourced from src/tool-descriptions.js
src/tools/*.js — 17 modular handler files, one per logical tool area (exec, files, backup, db, etc.)
src/tool-registry.js — tool metadata + group membership (core, sessions, monitoring, backup, database, advanced, gamechanger)
src/tool-config-manager.js — per-user enablement via ~/.ssh-manager/tools-config.json
src/stream-exec.js — streaming SSH exec with backpressure and UTF-8 boundary-safe chunking
src/output-formatter.js — ASCII markdown tables with head+tail truncation
src/logger.js — [info]/[warn]/[err]/[dbg] tagged stderr + file log
src/profile-loader.js — project-type profiles (default, devops, database, security, deployment)
cli/ssh-manager — bash CLI for server/tool/codex management

Commands

Setup

npm install
./scripts/setup-hooks.sh         # optional: pre-commit hooks

Server Management (Bash CLI)

ssh-manager server add                        # Add a new server
ssh-manager server list                       # List configured servers
ssh-manager server test SERVER                # Test connection to specific server
ssh-manager server remove SERVER              # Remove a server
ssh-manager server show SERVER                # Show server details

Read the full file on GitHub · 323 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.

yesterday First seen · 323 lines · 3,775 tokens per session scan B 3010ffc05ee9

Subscribe to this mod's changes

claude-code-ssh CLAUDE.md is an instructions file published in the GitHub repository hunchom/claude-code-ssh (2 stars, last pushed 1mo ago), licensed MIT. It adds 3,775 tokens to every session, about $0.0189 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AI Planning Productivity anthropic automation claude claude-code mcp

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

claude-code-ssh CLAUDE.md