terminal-mcp: Instructions file for Claude Code

CLAUDE.md

terminal-mcp CLAUDE.md is an instructions file for Claude Code from elleryfamilia/terminal-mcp. It costs 1,109 tokens per session, scanned A, original, MIT.

A project instruction file for Terminal MCP, a headless terminal emulator that lets an AI tool interact with shell sessions. It documents installation, build commands, architecture, and its headless and interactive modes.

In plain words
What is it for?
Use it when changing Terminal MCP, choosing how to run it in CI or containers, or understanding its shell, socket, and MCP server setup.
Why use it?
It gives coding agents the repository-specific information needed to build, run, and understand the project. This reduces guesswork about commands and how terminal access works.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is elleryfamilia/terminal-mcp's own configuration. It tells Claude Code how to work on terminal-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything terminal-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to elleryfamilia/terminal-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/elleryfamilia/terminal-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/elleryfamilia/terminal-mcp

Made for: Claude Code.

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-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/elleryfamilia/terminal-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/elleryfamilia/terminal-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/elleryfamilia/terminal-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/elleryfamilia/terminal-mcp/claude-md/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-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/elleryfamilia/terminal-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/elleryfamilia/terminal-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,109 This file is loaded in full into every session.
When invoked 1,109 The same file — it is already loaded in full.
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 $0.01109 $0.01109
Opus 5.5 $0.00444 $0.00444
Sonnet 5.5 $0.00222 $0.00222
Haiku 4.5 $0.00111 $0.00111

Measured 2mo ago against content hash 33cc16ce2d81, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

terminal-mcp CLAUDE.md 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 2mo 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.

CLAUDE.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 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 (claude.ai/code) when working with code in this repository.

Build Commands

npm install        # Install dependencies (includes native node-pty compilation)
npm run build      # Compile TypeScript to dist/
npm run dev        # Run directly with tsx (no build needed)

Architecture Overview

Terminal MCP is a headless terminal emulator exposed via Model Context Protocol (MCP). It has three operating modes:

Tri-Mode Architecture

  1. Headless Mode (--headless flag): Self-contained MCP server with embedded PTY

    • Spawns PTY internally, serves MCP directly over stdio
    • No TTY, socket, or separate interactive session needed
    • src/index.ts → startServer() from src/server.ts (eagerly inits session)
    • Recommended for MCP client configs (CI, containers, non-interactive environments)
  2. Interactive Mode (stdin is TTY, no --headless): User runs terminal-mcp in their terminal

    • Spawns a PTY shell process, pipes I/O to user's terminal
    • Exposes a Unix socket at /tmp/terminal-mcp.sock for AI tool access
    • src/index.ts → startInteractiveMode() → creates TerminalManager + createToolProxyServer()
  3. MCP Client Mode (stdin is not TTY, no --headless): Claude Code spawns terminal-mcp as MCP server

    • Connects to the Unix socket from interactive mode
    • Serves MCP protocol over stdio to Claude Code
    • src/client.ts → startMcpClientMode() → proxies tool calls to socket

Key Components

Terminal Layer (src/terminal/):

  • session.ts: Core integration of node-pty (PTY process) + @xterm/headless (terminal emulation). Handles shell-specific prompt customization via temp rc files.
  • manager.ts: Multi-session manager. Owns a map of TerminalSessions plus a single RecordingManager and (optional) SandboxController. The "default" session is auto-created on first use and is the implicit target of any tool call without a sessionId. Idle non-default sessions are GC'd on a 60s interval.

Read the full file on GitHub · 79 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. 2mo ago First seen · 79 lines · 1,109 tokens per session scan A 33cc16ce2d81

Subscribe to this mod's changes

terminal-mcp CLAUDE.md is an instructions file published in the GitHub repository elleryfamilia/terminal-mcp (147 stars, last pushed 2mo ago), licensed MIT. It adds 1,109 tokens to every session, about $0.0044 per session on Opus 5.5. 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 2026-08-30.

Related

terminal-mcp CLAUDE.md compared with instructions from other repositories

terminal-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
terminal-mcp CLAUDE.mdelleryfamilia/terminal-mcpInstructions file1472mo agoMITA1,109Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot