ssh-mcp CLAUDE.md

ssh-mcp CLAUDE.md is an instructions file for coding agents from LightspeedDMS/ssh-mcp. It costs 4,027 tokens per session, scanned C, original, MIT.

Project instructions and documentation for an SSH MCP server, including a fix for duplicated terminal output and notes about Villenele, its terminal-history testing framework.

In plain words
What is it for?
Use it when working on SSH connections, terminal output formatting, the xterm.js display, or Villenele terminal-history tests.
Why use it?
It explains the cause and remedy of a terminal display bug, helping maintainers avoid reintroducing duplicate or incorrectly formatted SSH output.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/lightspeeddms/ssh-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/LightspeedDMS/ssh-mcp

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 ssh-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lightspeeddms/ssh-mcp/claude-md.svg)](https://agentmods.dev/instructions/lightspeeddms/ssh-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lightspeeddms/ssh-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/lightspeeddms/ssh-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,027 This file is loaded in full into every session.
When invoked 4,027 The same file — it is already loaded in full.
Security scan C 2 findings. Scan, not verified.
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 $0.04027 $0.04027
Opus 5 $0.02014 $0.02014
Sonnet 5 $0.00805 $0.00805
Haiku 4.5 $0.00403 $0.00403

Measured 3d ago against content hash 1e63476d49ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

ssh-mcp CLAUDE.md scanned grade C with 2 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 3d 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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

'ssh_connect {"name": "test-session", "host": "localhost", "username": "jsbattig", "keyFilePath": "~/.ssh/id_ed25519"}',

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. **Verify HTML loads**: `curl -s [MCP_URL] | head -20`
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

CLAUDE.md · 392 lines

How it starts

The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LS-SSH-MCP Project Documentation

Terminal Echo Duplication Fix (v2.0.1)

Issue Resolution

Problem: Terminal commands showed duplicate output with different formatting - clean output followed by mangled output without ANSI colors.

Root Cause: Dual broadcast architecture in ssh-connection-manager.ts where SSH stream data was processed through two different paths:

  1. Raw SSH stream (preserved ANSI colors and formatting)
  2. Processed stream through prepareOutputForBrowser() (stripped ANSI codes, mangled spacing)

Solution: Modified broadcastToLiveListeners() method to conditionally process data based on source type:

  • SSH stream data (source === 'system') bypasses prepareOutputForBrowser()
  • Non-SSH data continues processing for necessary cleanup
  • Implementation at ssh-connection-manager.ts:205

Result: Single clean terminal output with preserved ANSI colors and formatting. xterm.js handles ANSI codes natively, eliminating need for server-side processing of SSH streams.

Validation: All Villenele testing framework tests passing with exact assertions. Terminal behavior now matches standard SSH client experience.


Villenele - Terminal History Testing Framework

Framework Name: Villenele

Villenele is the official name for our comprehensive Terminal History Testing Framework. When referenced by name, "Villenele" refers to the complete 9-story epic testing infrastructure designed specifically for SSH terminal emulation validation.

Purpose and Overview

The Terminal History Testing Framework is a comprehensive testing infrastructure designed to validate SSH terminal emulation and WebSocket-based browser terminal display. It addresses the critical challenge of testing terminal history formatting, command echo behavior, and real-time terminal interactions in a browser environment.

Core Problem Solved

The framework specifically solves issues with terminal prompt concatenation and display formatting that occurred when browsers connected to SSH sessions. Original problems included:

Read the full file on GitHub · 392 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. 3d ago First seen · 392 lines · 4,027 tokens per session scan C 1e63476d49ee

Subscribe to this mod's changes

ssh-mcp CLAUDE.md is an instructions file published in the GitHub repository LightspeedDMS/ssh-mcp (6 stars, last pushed 11mo ago), licensed MIT. It adds 4,027 tokens to every session, about $0.0201 per session on Opus 5. A static security scan graded it C with 2 findings (reaches for credential files, makes network calls). 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

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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 · 5,182 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 · 4,345 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

next.js 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