ssh-remote

ssh-remote is a skill for Claude Code, Codex from JansenAnalytics/claudex. It costs 29 tokens per session (1,218 once invoked), scanned B, original, MIT.

A guide for connecting to another computer over SSH, a secure way to run commands and move files between machines. It also covers SSH keys, port forwarding, and tunnels.

In plain words
What is it for?
Use it to manage VPS instances, execute remote commands, copy files with SCP or rsync, and create SSH tunnels.
Why use it?
It removes the need to work directly at a remote server and provides repeatable ways to deploy, administer, and access remote services.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash scripts/ssh-config-gen.sh myserver 1.2.3.4 root --key ~/.ssh/myserver --port 22.

Good fit Use it to manage VPS instances, execute remote commands, copy files with SCP or rsync, and create SSH tunnels.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/JansenAnalytics/claudex
agentmods
npx agentmods add skills/jansenanalytics/claudex/ssh-remote

Made for: Claude Code, Codex.

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 ssh-remote

README.md
[![agentmods](https://agentmods.dev/badge/skills/jansenanalytics/claudex/ssh-remote.svg)](https://agentmods.dev/skills/jansenanalytics/claudex/ssh-remote)
Your own site
<a href="https://agentmods.dev/skills/jansenanalytics/claudex/ssh-remote"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/ssh-remote.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,218 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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 $0.00029 $0.01218
Opus 5 $0.00015 $0.00609
Sonnet 5 $0.00006 $0.00244
Haiku 4.5 $0.00003 $0.00122

Measured 4d ago against content hash cdbc3b0b5ab8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

ssh-remote 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 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

| Permission denied (publickey) | Check key permissions: `chmod 600 ~/.ssh/key`, `chmod 700 ~/.ssh` |
skills/ssh-remote/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ssh-remote

SSH into remote servers, execute commands, transfer files via SCP/rsync, manage SSH keys and configs, tunnel ports.

When to Use

  • Deploying to remote servers
  • Managing VPS instances
  • Transferring files (SCP/rsync)
  • Setting up SSH tunnels or port forwarding
  • Configuring SSH keys and agent forwarding
  • Running remote commands or scripts

Quick Reference

Connect to a Server

ssh user@host
ssh -i ~/.ssh/mykey user@host -p 2222

Execute Remote Command

ssh user@host 'command here'
ssh user@host 'bash -s' < local-script.sh

File Transfer

# SCP
scp local-file user@host:/remote/path
scp user@host:/remote/file ./local-path
scp -r local-dir/ user@host:/remote/path/

# Rsync (preferred for large transfers)
rsync -avz --progress local-dir/ user@host:/remote/path/
rsync -avz --delete local-dir/ user@host:/remote/path/  # mirror
rsync -avz -e 'ssh -p 2222' local/ user@host:/remote/

SSH Tunnels

# Local forward: access remote:3306 via localhost:3306
ssh -L 3306:localhost:3306 user@host

# Remote forward: expose local:8080 on remote:9090
ssh -R 9090:localhost:8080 user@host

# SOCKS proxy
ssh -D 1080 user@host

# Background tunnel
ssh -fNL 3306:localhost:3306 user@host

Key Management

# Generate key
ssh-keygen -t ed25519 -C "comment" -f ~/.ssh/keyname

# Copy key to server
ssh-copy-id -i ~/.ssh/keyname.pub user@host

# Add to agent
eval $(ssh-agent)
ssh-add ~/.ssh/keyname

# Test connection
ssh -T user@host

Scripts

Script Purpose
scripts/ssh-config-gen.sh Generate/update SSH config entries
scripts/key-rotation.sh Rotate SSH keys on remote hosts
scripts/tunnel-manager.sh Manage persistent SSH tunnels
scripts/rsync-deploy.sh Deploy files via rsync with backup

Workflows

1. Set Up New Server Access

Read the full file on GitHub · 200 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. 4d ago First seen · 200 lines · 29 tokens per session scan B cdbc3b0b5ab8

Subscribe to this mod's changes

ssh-remote is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 1,218 once invoked, about $0.0001 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 2026-09-03.