proxmox-mcp: Instructions file for Claude Code

CLAUDE.md

proxmox-mcp CLAUDE.md is an instructions file for Claude Code from NANDI-Services/proxmox-mcp. It costs 2,602 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for the NANDI-Services/proxmox-mcp repository. The repository is a TypeScript MCP server that lets administrators operate Proxmox VE infrastructure.

In plain words
What is it for?
Working on the Proxmox MCP server, running linting, type checks, builds, tests, end-to-end tests, documentation generation, and release validation.
Why use it?
It gives contributors the project’s purpose, architecture guidance, commands, and release-related checks in one place.

Instructions file for Claude Code

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

This is NANDI-Services/proxmox-mcp's own configuration. It tells Claude Code how to work on proxmox-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 proxmox-mcp configures →

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nandi-services/proxmox-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nandi-services/proxmox-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,602 This file is loaded in full into every session.
When invoked 2,602 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 $0.02602 $0.02602
Opus 5 $0.01301 $0.01301
Sonnet 5 $0.00520 $0.00520
Haiku 4.5 $0.00260 $0.00260

Measured 8d ago against content hash 6691c76f4001, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

proxmox-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 8d 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 · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 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.

AGENTS.md holds the release runbook and the documentation sync gate. Follow it for anything release- or commit-adjacent; it is not repeated here.

What this is

An MCP server that operates real Proxmox VE infrastructure. It is published to npm as nandi-proxmox-mcp for other admins to install against their own clusters — this repo is the tool, not one person's installation. Changes are judged by whether a stranger can install and run them.

TypeScript, ESM ("type": "module"), Node >= 20.

Commands

npm ci                    # deps (lockfile-exact)
npm run lint              # eslint, type-aware
npm run typecheck         # tsc --noEmit
npm run build             # tsc -p tsconfig.build.json -> dist/
npm test                  # unit + integration. No Docker needed.
npm run test:e2e          # e2e against the Docker emulator (see Testing)
npm run validate:release  # manifest + package metadata + descriptor sync
npm run docs:tools        # regenerate docs/TOOLS.md (CI fails on drift)

Run a single test file or case:

npx vitest run tests/unit/retry-policy.test.ts
npx vitest run -t "does not retry a non-idempotent create"
npx vitest run -c vitest.e2e.config.ts tests/e2e/cluster-routing.e2e.test.ts

npm run clean uses cmd.exe syntax and only works on Windows.

The CLI has an interactive path that is easy to disable by accident

setup chooses between the wizard and the scripted path via hasCliOverrides, which looks only at --proxmox-host, --proxmox-user, --token-name and --token-secret. It cannot go back to asking "was any option defined?": commander supplies defaults for --proxmox-realm and --scope, so that test is always true and the bare nandi-proxmox-mcp setup dies with "missing required options" instead of prompting. tests/unit/setupWizard.test.ts pins this.

The wizard takes an injectable Prompt and probe (ask(options, deps)) so it can be driven by a test. Piping a file into the real readline does not work — readline flushes every line at once, lines arriving between two questions are dropped, and the process then exits cleanly having answered nothing, which reads as a hang.

Read the full file on GitHub · 115 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. 8d ago First seen · 115 lines · 2,602 tokens per session scan A 6691c76f4001

Subscribe to this mod's changes

proxmox-mcp CLAUDE.md is an instructions file published in the GitHub repository NANDI-Services/proxmox-mcp (0 stars, last pushed 26d ago), licensed MIT. It adds 2,602 tokens to every session, about $0.0130 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