terminal-use-setup

terminal-use-setup is a skill for Claude Code, Codex from HLH2023/terminal-use-mcp. It costs 31 tokens per session (4,228 once invoked), scanned A, original, MIT.

A setup guide for terminal-use-mcp, a service that lets an agent control interactive terminal programs and remote SSH sessions.

In plain words
What is it for?
Installing the service, configuring client settings and environment variables, setting safety options, checking versions, and defining SSH hosts.
Why use it?
It explains the configuration needed to connect the service, select a terminal provider, manage versions, and reach remote machines.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/hlh/.config/terminal-use-mcp/hosts.json.

Good fit Installing the service, configuring client settings and environment variables, setting safety options, checking versions, and defining SSH hosts.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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 terminal-use-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/hlh2023/terminal-use-mcp/terminal-use-setup/github.svg)](https://agentmods.dev/skills/hlh2023/terminal-use-mcp/terminal-use-setup)
Your own site
<a href="https://agentmods.dev/skills/hlh2023/terminal-use-mcp/terminal-use-setup"><img src="https://agentmods.dev/badge/skills/hlh2023/terminal-use-mcp/terminal-use-setup/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for terminal-use-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/hlh2023/terminal-use-mcp/terminal-use-setup"><img src="https://agentmods.dev/badge/skills/hlh2023/terminal-use-mcp/terminal-use-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,228 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00031 $0.04228
Opus 5 $0.00015 $0.02114
Sonnet 5 $0.00006 $0.00846
Haiku 4.5 $0.00003 $0.00423

Measured 10d ago against content hash 9245b2366030, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

terminal-use-setup 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 10d 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.

skills/terminal-use-setup/SKILL.md · 411 lines

How it starts

The opening of the file, as written. The whole thing — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.

terminal-use-setup: Configuration & Setup Guide

terminal-use-mcp v0.2.0 — This skill is maintained alongside the MCP server. Version check: call terminal.health → compare the version field with this header. If mismatched, prompt the user to update. The terminal-use skill makes this check mandatory before first terminal operation (Pre-flight Check section).

This skill covers installation, MCP configuration, environment variables, version management, and SSH setup for terminal-use-mcp. For how to use the tools (operation loop, safety rules, patterns), see the terminal-use skill instead.

When To Use

  • You need to install or configure terminal-use-mcp as an MCP server.
  • You need to set or adjust environment variables (CWD policy, command safety, session behavior, providers).
  • You need to set up SSH remote access (hosts.json, profiles, authentication).
  • You need to check or update the server version, or understand npx caching behavior.
  • You need to configure the config.json file for persistent settings.

Quick Configuration

OpenCode

Add to .opencode/opencode.json in the mcp field:

{
  "mcp": {
    "terminal-use": {
      "type": "local",
      "command": ["npx", "-y", "terminal-use-mcp"],
      "enabled": true,
      "environment": {
        "TERMINAL_USE_WORKSPACE_ROOT": "<your-project-path>",
        "TERMINAL_USE_ALLOWED_CWD": "<your-project-path>,/tmp",
        "TERMINAL_USE_PROVIDERS": "native-pty,tmux"
      }
    }
  }
}

Claude Code / Claude Desktop

Add to .mcp.json (project root) or claude_desktop_config.json:

{
  "mcpServers": {
    "terminal-use": {
      "command": "npx",
      "args": ["-y", "terminal-use-mcp"],
      "env": {
        "TERMINAL_USE_WORKSPACE_ROOT": "<your-project-path>",
        "TERMINAL_USE_ALLOWED_CWD": "<your-project-path>,/tmp",
        "TERMINAL_USE_PROVIDERS": "native-pty,tmux"
      }
    }
  }
}

Codex CLI

Add to .codex/config.json in the mcp_servers field:

Read the full file on GitHub · 411 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. 10d ago First seen · 411 lines · 31 tokens per session scan A 9245b2366030

Subscribe to this mod's changes

terminal-use-setup is a skill published in the GitHub repository HLH2023/terminal-use-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 4,228 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

computer-use-linux

Linux desktop observation and control via native Pi tools or the computer-use-linux MCP server: accessibility trees, screenshots, window targeting, and input synthesis (click, type, scroll).

agent-sh/computer-use-linux · 39 tokens

data-analysis

Analyze, explore, clean, and visualize datasets with statistical rigor. Use when user asks to analyze data, find patterns, compute statistics, create visualizations, clean messy data, or explore a dataset. Trigger when user says things like "analyze this data", "what trends do you see", "find patterns in", "create a…

Upsonic/Upsonic · 138 tokens

experiment_management

Set up and manage the experiment folder structure. This is Phase 0 — it runs before any analysis begins. All bookkeeping files are JSON (never markdown).

Upsonic/Upsonic · 0 tokens

summarization

Summarize documents, articles, conversations, code, and technical content into concise, accurate summaries. Use when user asks to summarize, condense, create a TL;DR, write an executive summary, extract key points, or distill content. Trigger when user says things like "summarize this", "give me the key points"…

Upsonic/Upsonic · 144 tokens

evaluate

Compare baseline and new implementation results. Produce the machine-readable final report result.json, update experiments.json, and append a row to comparison.json.

Upsonic/Upsonic · 0 tokens

progress

Maintain a machine-readable progress file so dashboards, CLIs, and notebooks can poll the experiment's state at any time. The file is a JSON document — never markdown, never human-prose-first.

Upsonic/Upsonic · 0 tokens