interminal: Instructions file for Claude Code

CLAUDE.md

interminal CLAUDE.md is an instructions file for Claude Code from QiuwenZheng/interminal. It costs 1,000 tokens per session, scanned A, original, MIT.

Repository instructions for Interminal, a server that gives AI assistants access to local shells and SSH connections, including interactive commands.

In plain words
What is it for?
Use them when modifying the MCP tools, session manager, local or SSH channels, command handling, or installation setup.
Why use it?
They explain how the server is organised and how its session and channel abstractions work, reducing the risk of breaking command execution or remote sessions.

Instructions file for Claude Code

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

This is QiuwenZheng/interminal's own configuration. It tells Claude Code how to work on interminal 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 interminal configures →

Reuse

Borrowing it

Nothing to install: this file belongs to QiuwenZheng/interminal. 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/QiuwenZheng/interminal/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/QiuwenZheng/interminal

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 interminal CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/qiuwenzheng/interminal/claude-md"><img src="https://agentmods.dev/badge/instructions/qiuwenzheng/interminal/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,000 This file is loaded in full into every session.
When invoked 1,000 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 $0.01000 $0.01000
Opus 5 $0.00500 $0.00500
Sonnet 5 $0.00200 $0.00200
Haiku 4.5 $0.00100 $0.00100

Measured 9d ago against content hash 2d590d5786b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

interminal 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 9d 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 · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 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.

Project Overview

Interminal is an MCP server that gives AI assistants terminal access — SSH and local shells — with support for interactive commands. It is distributed via uvx and has no build step.

Running & Installation

# Run directly (no install)
python mcp_server.py

# Install from source
pip install .

# Run via uvx (published package)
uvx interminal

There are no test, lint, or build commands configured in this project.

Architecture

mcp_server.py          ← FastMCP tool definitions (6 tools)
    ↓
session_manager.py     ← SessionManager: SSH sessions + transient local execution
    ↓
channel.py             ← Channel abstraction (SSHChannel | LocalChannel | PtyChannel)
    ↓
command.py             ← RunningCommand: background read loop, UTF-8 decoding

Key design decisions

Channel duck-typingSSHChannel, LocalChannel, and PtyChannel share an interface without ABC/abstractmethod. All three implement read(), write(), close(), send_control(), and is_finished().

Two-phase timeout (_wait_for_result in session_manager.py) — Phase 1 waits up to pause_timeout + 1s for the first byte; if it times out we return immediately (already satisfies the "silent for pause_timeout" contract — going into Phase 2 would waste another full pause_timeout). Phase 2 only runs when bytes are actually arriving, collecting until a pause_timeout gap or total_timeout hits.

PtyChannel platform split — Windows uses pywinpty.PtyProcess; Unix uses stdlib pty with fcntl non-blocking I/O. pywinpty is an optional dependency.

SSHChannel stdin referencesession_manager.py explicitly retains a reference to stdin to prevent Python GC from calling __del__ and closing the paramiko channel prematurely.

Incremental UTF-8 decodingcommand.py uses codecs.getincrementaldecoder so multibyte characters split across reads are assembled correctly.

Read the full file on GitHub · 76 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. 9d ago First seen · 76 lines · 1,000 tokens per session scan A 2d590d5786b2

Subscribe to this mod's changes

interminal CLAUDE.md is an instructions file published in the GitHub repository QiuwenZheng/interminal (3 stars, last pushed 1mo ago), licensed MIT. It adds 1,000 tokens to every session, about $0.0050 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens