Ssh Ops

Organization

SpecterOps

ssh-ops

Establish and operate scoped SSH sessions for authorized remote command execution with full evidence capture. Use when the operator provides SSH-accessible targets/credentials and Codex must execute commands on a remote host as an interactive user while enforcing OPSEC gating and safe-check behavior.

Overview

Publisher	SpecterOps
Repository	`skills`
Skill name	`ssh-ops`
Stars	706
Forks	80
Bundled files	3
License	Apache-2.0
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
3 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by SpecterOps on GitHub. Read the source before you install it.

Installation

Install the Ssh Ops AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/SpecterOps/skills/tree/main/plugins/ops-infrastructure/skills/ssh-ops
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/SpecterOps/skills/tree/main/plugins/ops-infrastructure/skills/ssh-ops

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/SpecterOps/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/plugins/ops-infrastructure/skills/ssh-ops .claude/skills/ssh-ops

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ssh Ops in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ssh Ops on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ssh Ops is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

SSH Ops

Use controlled SSH workflows to execute remote commands, keep session state stable, and return exact command/output evidence.

Input Contract

Accept input as: HOST USER [MODE] [NOISE]

Mode:

plan: produce command sequence and expected outcomes only
execute (default): establish session and run commands

Noise:

low (default): read-only validation and bounded enumeration
medium: broader but still non-destructive enumeration
high: disruptive or high-telemetry operations; explicit approval required

Session Ownership Rule

When multiple agents are active, route SSH execution through the dedicated ssh_operator agent only.

Do not allow multiple agents to write to the same SSH session concurrently.
Keep one owner per session and serialize command execution.

Default Workflow

Validate scope and auth assumptions.
Run safe connectivity check first:

bash
ssh -o BatchMode=yes -o ConnectTimeout=10 -o StrictHostKeyChecking=accept-new <user>@<host> 'hostname; id; date -u'

Run bounded read-only commands before any escalation.
If interactive state is required, open one interactive session and execute command batches sequentially.
Capture full stdout/stderr and exit status for each command.
Return findings, blockers, and next safe step.

Authentication Handling

Prefer SSH keys and ssh-agent.
Do not log raw credentials in output.
Do not run brute-force or repeated auth guessing when login fails.

OPSEC Gate

Require explicit operator confirmation before:

destructive commands (rm, service stop/restart, system reconfiguration),
high-noise discovery across many hosts from the remote session,
actions likely to disrupt availability.

Before requesting confirmation, provide:

exact action,
security objective,
expected impact,
prerequisites/assumptions,
likely telemetry and blast radius.

Refusal and Safe-Check Handling

Treat failed auth, access denied, host-key errors, and policy blocks as safe-check outcomes.
Do not auto-escalate after refusal or failure.
Report refusal/failure cause and propose the lowest-noise alternative next command.
Only retry blocked operations after operator approval.

Evidence Requirements

For each command executed, record:

UTC timestamp,
host/user/session context,
exact command string,
stdout/stderr and exit status,
interpretation and confidence.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Ssh Ops AI skill do?

Why use Ssh Ops on TypingMind?

Because you install it once and use it with any model. Ssh Ops is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ssh Ops in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/SpecterOps/skills/tree/main/plugins/ops-infrastructure/skills/ssh-ops. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Ssh Ops?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ssh Ops?

As many as you like. As long as a model supports skills, you can use Ssh Ops with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ssh Ops AI skill free?

Yes. It is published on GitHub by SpecterOps under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Release Openclaw Announcement

openclaw

OrganizationPopular

Draft or post OpenClaw beta, stable, or extended-stable Discord release announcements from changelog, tag, registry, and validation evidence. Use when announcing a release, release candidate, or…

Security Triage

Triage OpenClaw security advisories, drafts, and GHSA reports with shipped-tag and trust-model proof.

Add Model Provider

Add and live-prove a model provider with non-interactive config one-liners, without exposing credentials.

Diagnose Gateway

Diagnose Gateway, config, secrets, channels, and port failures with read-only one-liners.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

SSH Ops

Input Contract

Session Ownership Rule

Default Workflow

Authentication Handling

OPSEC Gate

Refusal and Safe-Check Handling

Evidence Requirements

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now