network-device-mcp: Instructions file for Claude Code

CLAUDE.md

network-device-mcp CLAUDE.md is an instructions file for Claude Code from mgarabito/network-device-mcp. It costs 958 tokens per session, scanned A, original, MIT.

Instructions for an AI assistant that works with network devices through serial consoles and SSH, which is a secure remote login method.

In plain words
What is it for?
They help with checking ports, opening device sessions, running safe network commands, reading output, saving logs, and updating network-device notes. Destructive operations require explicit confirmation.
Why use it?
They provide a defined way to connect to devices, inspect results, search project files, and record context while requiring confirmation before risky commands.

Instructions file for Claude Code

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

This is mgarabito/network-device-mcp's own configuration. It tells Claude Code how to work on network-device-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 network-device-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mgarabito/network-device-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/mgarabito/network-device-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mgarabito/network-device-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 network-device-mcp CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mgarabito/network-device-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mgarabito/network-device-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 958 This file is loaded in full into every session.
When invoked 958 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 $0.00958 $0.00958
Opus 5.5 $0.00383 $0.00383
Sonnet 5.5 $0.00192 $0.00192
Haiku 4.5 $0.00096 $0.00096

Measured 2mo ago against content hash 5f99b55c682a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

network-device-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 · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Network Device Assistant — Claude Code Context

This folder contains a local MCP server that gives Claude direct access to network devices via serial console and SSH.

MCP Server

The server starts automatically when Claude Code loads (registered via mcp_config.json). It exposes these tools:

Tool What it does
list_serial_ports List available COM ports
connect_serial Open a serial console session
connect_ssh Open an SSH session
send_command Run a CLI command (with safety check)
read_output Read pending output from a session
list_sessions Show active sessions
disconnect Close a session
save_session_log Save session history to file
search_project_files Search manuals, scripts, configs, context files
read_context_file Read a context/memory markdown file
update_context_file Append findings to a context file

Safety Rules

  • Read-only commands (show, ping, display, traceroute...) run immediately
  • Destructive commands (configure, delete, reload, write...) require confirmed=true
  • Catastrophic commands (format flash, erase startup-config, factory-default) are always blocked

Context / Memory Files

Operational knowledge lives in SSH Plugin/context/ — check these before troubleshooting:

  • known_issues.md — documented symptoms and resolutions
  • device_profiles.md — per-device connection details and notes
  • command_library.md — command reference by device family
  • troubleshooting_history.md — log of past sessions
  • script_index.md — index of scripts in the files directory
  • manual_index.md — index of technical manuals

Always check known_issues.md and device_profiles.md early in a troubleshooting session. After resolving an issue, update known_issues.md and troubleshooting_history.md.

File Search Paths

search_project_files searches:

  • context — SSH Plugin/context/ (memory files above)
  • manuals — AI Serial folder / manuals
  • scripts — AI Serial folder / scripts
  • configs — AI Serial folder / configs
  • logs — SSH Plugin/sessions/session_logs/

Read the full file on GitHub · 106 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 · 106 lines · 958 tokens per session scan A 5f99b55c682a

Subscribe to this mod's changes

network-device-mcp CLAUDE.md is an instructions file published in the GitHub repository mgarabito/network-device-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 958 tokens to every session, about $0.0038 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 2026-08-31.

Related

network-device-mcp CLAUDE.md compared with instructions from other repositories

network-device-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
network-device-mcp CLAUDE.mdmgarabito/network-device-mcpInstructions file05mo agoMITA958Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot