secure-cluster-mcp: Instructions file for Claude Code

CLAUDE.md

secure-cluster-mcp CLAUDE.md is an instructions file for Claude Code from FlorianSp2000/secure-cluster-mcp. It costs 312 tokens per session, scanned A, original, MIT.

A set of project instructions for safely using an MCP server with a shared university HPC cluster. An HPC cluster is a group of powerful computers used by many researchers for large jobs.

In plain words
What is it for?
Use it when working with the cluster over SSH or SCP, which are tools for remote commands and file transfers. It requires dry-run checks, path validation, rate limits, limited log output, and confirmation before transfers, job submissions, or remote changes.
Why use it?
It helps prevent wasted computing time, blocked research jobs, damaged data, and unsafe remote commands by requiring checks and confirmation.

Instructions file for Claude Code

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

This is FlorianSp2000/secure-cluster-mcp's own configuration. It tells Claude Code how to work on secure-cluster-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 secure-cluster-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to FlorianSp2000/secure-cluster-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/FlorianSp2000/secure-cluster-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/FlorianSp2000/secure-cluster-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 secure-cluster-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/floriansp2000/secure-cluster-mcp/claude-md.svg)](https://agentmods.dev/instructions/floriansp2000/secure-cluster-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/floriansp2000/secure-cluster-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/floriansp2000/secure-cluster-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 312 This file is loaded in full into every session.
When invoked 312 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 $0.00312 $0.00312
Opus 5 $0.00156 $0.00156
Sonnet 5 $0.00062 $0.00062
Haiku 4.5 $0.00031 $0.00031

Measured 6d ago against content hash 19e0ee097397, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

secure-cluster-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 6d 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 · 43 lines

What it actually says

CLAUDE.md - Project Instructions

CRITICAL: CLUSTER SAFETY

This MCP server interacts with a shared university HPC cluster. Mistakes can:

  • Waste compute resources (expensive)
  • Block other researchers' jobs
  • Corrupt research data
  • Get user banned from cluster

MANDATORY RULES

  1. DRY_RUN=true by default - Never execute real SSH/SCP without explicit user confirmation
  2. Never spam cluster - Rate limit all commands (max 30/5min)
  3. Validate ALL paths - Must be under REMOTE_BASE_PATH, reject others
  4. Log tail only - Default 200 lines, never full logs unless requested
  5. No destructive commands - Never rm, never overwrite without confirmation
  6. Fail fast - If validation fails, raise error immediately, don't proceed

Before ANY cluster interaction:

  • Check DRY_RUN flag
  • Validate paths
  • Check rate limits
  • Log what would happen

Cluster File Transfer

Use scp via the MCP tools, never raw commands.

Cluster details (from .env):

  • CLUSTER_HOST - cluster IP
  • CLUSTER_USER - username
  • REMOTE_BASE_PATH - remote working directory

ALWAYS confirm with user before:

  1. Any file transfer
  2. Any job submission
  3. Any command that modifies remote state

Development

Use uv for Python environment management.

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. 6d ago First seen · 43 lines · 312 tokens per session scan A 19e0ee097397

Subscribe to this mod's changes

secure-cluster-mcp CLAUDE.md is an instructions file published in the GitHub repository FlorianSp2000/secure-cluster-mcp (1 stars, last pushed 3mo ago), licensed MIT. It adds 312 tokens to every session, about $0.0016 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

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

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

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

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

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

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