Agent skill

Ssh Skill

by badseal in badseal/ssh-skill

A skill your agent uses when a task requires SSH or SCP/SFTP behavior, a remote server, server alias/IP/hostname/user@host, bastion or jump-host access, remote command execution, upload/download…

No licenceAuto-check: notesDevOps & Cloud

Install Ssh Skill

skills CLI
$ npx skills add badseal/ssh-skill --skill ssh-skill -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install badseal/ssh-skill ssh-skill --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ssh-skill
GitHub stars
536
Token cost
~2.4k tokens
SKILL.md length
1,201 words
Files
91 (incl. scripts, references)
Skills in repo
1
Repo updated
First seen
Licence
None found

At a glance

A skill your agent uses when a task requires SSH or SCP/SFTP behavior, a remote server, server alias/IP/hostname/user@host, bastion or jump-host access, remote command execution, upload/download…

  • Works in 8 steps: Resolve the root containing this loaded… → Invoke /scripts/ssh_skill.py; do not… → Pass arguments as discrete process… → …
  • A task requires SSH
  • SKILL.md covers Purpose, Scope, Hard Rules and Resolve The Skill Root Once, plus 11 more sections
  • Runs Python scripts from its folder

What it does

Ssh Skill is an agent skill from badseal/ssh-skill. Use when a task requires SSH or SCP/SFTP behavior, a remote server, server alias/IP/hostname/user@host, bastion or jump-host access, remote command execution, upload/download, server transfer, deployment, tunnels, port forwarding, or remote internal services; Chinese triggers include 服务器, 远程, 连接, 登录, 上传, 下载, 部署, 跳板机, 隧道. DO NOT use for local shell commands, localhost/current-machine work, local Docker, browser downloads, Git remotes, or direct non-SSH database access.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 94 other files, including scripts and reference files (for example `.github/workflows/ci.yml`, `README.md` and `README_EN.md`).

It sits in DevOps & Cloud, covering Containers and Git workflow. It works with Docker and Git. The repository describes itself as: 面向 Codex 和 Claude Code 的跨平台 SSH 工作流 Skill,支持 Windows、macOS、Linux.

When your agent uses it

  • A task requires SSH
  • SCP/SFTP behavior
  • A remote server
  • Server alias/IP/hostname/user@host

Example prompts

  • “/ssh-skill”

Requirements

  • Python 3
  • Docker
  • Pre-approved tools (allowed-tools): Bash, Read, Write, Glob

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Resolve the root containing this loaded SKILL.md; call it
  2. Invoke /scripts/ssh_skill.py; do not construct raw
  3. Pass arguments as discrete process arguments. Never add a local shell
  4. Parse the one JSON document on stdout before deciding the next action.
  5. Treat outcome_unknown as a stop condition. Report its request ID and do
  6. Do not retry authentication failures, destructive commands, or partially
  7. Never expose passwords, private-key content, tokens, or askpass data.
  8. Preview multi-host and irreversible operations before applying them.

What it can do on your machine

Read from SKILL.md and the folder at commit c6c8a18. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Write
    • Glob

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python, from the files we listed), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ssh Skill loads about 2.4k tokens when it runs, and up to ~5k if it reads all its reference files. Until then it costs about 121 tokens; SKILL.md has 1,201 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~121
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Write, Glob

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,201 words (~2,416 tokens).

“Use this contract for SSH-mediated work in Codex and Claude Code on Windows, macOS, and Linux. The deterministic Python CLI owns transport, retries, output limits, host-key policy, and compatibility behavior.”

— opening of SKILL.md by badseal
name
ssh-skill
allowed-tools
Bash, Read, Write, Glob
version
4.0.0
keywords
SSH,SCP,SFTP,server,remote,bastion,jump-host,upload,download,transfer,tunnel,deploy,服务器,远程,连接,登录,上传,下载,部署,跳板机,隧道

Read the full SKILL.md on GitHub

Files

SKILL.md and 90 other files (scripts, references) in the repository root of badseal/ssh-skill.

  • SKILL.md
  • .github/workflows/ci.yml
  • .gitignore
  • README.md
  • README_EN.md
  • evals/workflows.json
  • examples/README.md
  • examples/basic_usage.py
  • examples/concurrency_examples.py
  • examples/config_env_development.json
  • examples/config_env_production.json
  • examples/config_jump_double.json
  • examples/config_jump_password.json
  • examples/config_jump_simple.json
  • examples/config_jump_single_key.json
  • examples/config_key_with_passphrase.json
  • examples/config_multi_servers.json
  • … and 74 more

Open the folder on GitHubat commit c6c8a18

Compare with similar skills

Ssh Skill next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ssh Skill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ssh Skill this skillbadseal/ssh-skill536—~2.4kAutomated safety check: NotesNone
Rtk Skillsopaco/deepwiki-rs3.1k—~1.4kAutomated safety check: PassMIT
Pluggedin Stack OpsVeriTeknik/pluggedin-app103—~1.3kAutomated safety check: NotesMIT
Deploy Playgroundobjeck/objeck-lang165—~2.1kAutomated safety check: WarnCustom licence
Polyphonyalinaqi/maggy707—~980Automated safety check: PassMIT
Crabbox Quickstartopenclaw/crabbox1.5k—~1.6kAutomated safety check: NotesMIT

Similar skills

  • Rtk Skill

    sopaco/deepwiki-rs

    A skill your agent uses when running shell commands that produce verbose output (git, test, build, lint, package managers, docker).

    3.1k GitHub stars~1.4k tokensUpdated 23 days ago
    DevOps & CloudAuto-check passed
  • Pluggedin Stack Ops

    VeriTeknik/pluggedin-app

    A skill your agent uses when deploying, restarting, verifying or rolling back the containerised plugged.in production stack, when the site returns 404 or 5xx after a deploy or git operation, or when…

    103 GitHub stars~1.3k tokensUpdated yesterday
    DevOps & CloudAuto-check: notes
  • Deploy Playground

    objeck/objeck-lang

    Deploy/refresh the Objeck web playground (playground.objeck.org) on its VPS over SSH — git pull, rebuild the sandbox Docker image, restart the service, health-check.

    165 GitHub stars~2.1k tokensUpdated today
    DevOps & CloudAuto-check: warnings
  • Polyphony

    alinaqi/maggy

    Multi-agent orchestration with container-isolated workspaces — each agent session runs in its own Docker container with independent git branches

    707 GitHub stars~980 tokensUpdated 14 days ago
    DevelopmentAuto-check passed
  • Crabbox Quickstart

    openclaw/crabbox

    Gets you running your repository's tests in a disposable Docker or Podman container on your own machine with Crabbox, with no account and no cloud spend.

    1.5k GitHub stars~1.6k tokensUpdated today
    DevOps & CloudAuto-check: notes
  • Install Check

    RLinf/RLinf

    Check, fix, or extend requirements/install.sh and its docker/Dockerfile coverage when adding a new embodied model or environment in RLinf, so the install logic reuses common utilities, keeps system…

    5.5k GitHub stars~2.3k tokensUpdated today
    DevOps & CloudAuto-check passed

Works with

Categories

Questions about Ssh Skill

What does Ssh Skill do?

A skill your agent uses when a task requires SSH or SCP/SFTP behavior, a remote server, server alias/IP/hostname/user@host, bastion or jump-host access, remote command execution, upload/download…. Ssh Skill is an agent skill from badseal/ssh-skill. Use when a task requires SSH or SCP/SFTP behavior, a remote server, server alias/IP/hostname/user@host, bastion or jump-host access, remote command execution, upload/download, server transfer, deployment, tunnels, port forwarding, or remote internal services; Chinese triggers include 服务器, 远程, 连接, 登录, 上传, 下载, 部署, 跳板机, 隧道.

When should I use Ssh Skill?

Ssh Skill fits situations like: A task requires SSH; SCP/SFTP behavior; A remote server; server alias/IP/hostname/user@host.

How do I install Ssh Skill in Claude Code?

Run `npx skills add badseal/ssh-skill --skill ssh-skill -a claude-code`. Or copy the skill folder (the badseal/ssh-skill repository) into .claude/skills/ssh-skill in your project. Claude Code loads it when a task matches its description.

How do I install Ssh Skill in Codex?

Run `npx skills add badseal/ssh-skill --skill ssh-skill -a codex`. Or copy the skill folder (the badseal/ssh-skill repository) into .agents/skills/ssh-skill in your project. Codex loads it when a task matches its description.

Can I use Ssh Skill in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add badseal/ssh-skill --skill ssh-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ssh-skill, .gemini/skills/ssh-skill, .github/skills/ssh-skill and .opencode/skills/ssh-skill in your project.

What does Ssh Skill need to run?

Going by SKILL.md and its folder, Ssh Skill needs Python for the scripts in its folder. Our summary lists: Python 3; Docker. Its frontmatter pre-approves these tools: Bash, Read, Write, Glob.

Does Ssh Skill access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ssh Skill safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Ssh Skill use?

No licence was found for Ssh Skill or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Ssh Skill use?

About 2.4k tokens (SKILL.md is roughly 9.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.6k tokens, read only when the agent opens those files.

What are the alternatives to Ssh Skill?

Skills that share tags, products or a category with Ssh Skill: Rtk Skill (sopaco/deepwiki-rs, 3.1k stars), Pluggedin Stack Ops (VeriTeknik/pluggedin-app, 103 stars), Deploy Playground (objeck/objeck-lang, 165 stars) and Polyphony (alinaqi/maggy, 707 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ssh Skill?

badseal (a GitHub user) maintains it in badseal/ssh-skill, which has 536 GitHub stars. The repository was last updated on August 24, 2026.

Source: badseal/ssh-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.