msp-script-library: Instructions file for Claude Code

CLAUDE.md

msp-script-library CLAUDE.md is an instructions file for Claude Code from DTC-Inc/msp-script-library. It costs 6,115 tokens per session, scanned A, original, MIT.

Repository instructions for an MSP script library. An MSP, or managed service provider, uses scripts to automate work for many customers and systems.

In plain words
What is it for?
Use them when creating, reviewing, or modifying automation and management scripts for platforms, vendors, deployments, or remote-management systems.
Why use it?
They keep PowerShell scripts consistent and prevent scripts from failing when run through remote-management tools that provide settings as environment variables.

Instructions file for Claude Code

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

This is DTC-Inc/msp-script-library's own configuration. It tells Claude Code how to work on msp-script-library 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 msp-script-library configures →

Reuse

Borrowing it

Nothing to install: this file belongs to DTC-Inc/msp-script-library. 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/DTC-Inc/msp-script-library/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/DTC-Inc/msp-script-library

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 msp-script-library CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dtc-inc/msp-script-library/claude-md"><img src="https://agentmods.dev/badge/instructions/dtc-inc/msp-script-library/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,115 This file is loaded in full into every session.
When invoked 6,115 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 $0.06115 $0.06115
Opus 5.5 $0.02446 $0.02446
Sonnet 5.5 $0.01223 $0.01223
Haiku 4.5 $0.00611 $0.00611

Measured 2mo ago against content hash 76f816b701d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

msp-script-library 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 · 546 lines

How it starts

The opening of the file, as written. The whole thing — 546 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.

Repository Overview

This is an MSP (Managed Service Provider) script library containing PowerShell scripts for automation, deployment, configuration, and management tasks across various platforms and vendors. Scripts are designed to be executed both interactively and via RMM (Remote Monitoring and Management) platforms.

Code Architecture

Script Structure Standard

All scripts follow a consistent three-part structure defined in script-template-powershell.ps1:

  1. RMM Variable Declaration Section (top of file)

    • Comment block listing all required RMM variables
    • Format: ## PLEASE COMMENT YOUR VARIABLES DIRECTLY BELOW HERE IF YOU'RE RUNNING FROM A RMM
    • Each variable should be documented as a comment (e.g., ## $variableName)
  2. Input Handling Section

    • All RMM-supplied variables come via environment variables ($env:VarName). NinjaRMM passes script preset variables to PowerShell as environment variables, so the script must read them via $env: at every use site. Bare $VarName references resolve to $null in true RMM mode and silently fall through to the interactive branch.
    • Detects execution context via $env:RMM — environment variables are strings, so compare against "1" not 1. Anything other than "1" is interactive mode.
    • Interactive mode: Prompts user with Read-Host for required inputs with validation loop. Write the result back to $env:Description so the rest of the script can keep referencing $env: consistently.
    • RMM mode: Uses pre-set environment variables passed by the RMM platform. Defaults for any optional variables (custom field names, state file paths, etc.) should be set at the top of the script by writing to $env: directly:
      if ([string]::IsNullOrEmpty($env:CustomFieldFooBoolean)) {
          $env:CustomFieldFooBoolean = "fooDetected"
      }
      
    • Sets $LogPath based on context:
      • SYSTEM-context script, interactive: $env:WINDIR\logs\
      • SYSTEM-context script, RMM: $env:RMMScriptPath\logs\ (fallback to $env:WINDIR\logs\ if $env:RMMScriptPath is null)
      • User-context script: $env:LOCALAPPDATA\dtc-logs\ — $env:WINDIR\logs\ requires admin and a user-context script will fail to write there
    • Always captures $env:Description for audit trail

Read the full file on GitHub · 546 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 · 546 lines · 6,115 tokens per session scan A 76f816b701d5

Subscribe to this mod's changes

msp-script-library CLAUDE.md is an instructions file published in the GitHub repository DTC-Inc/msp-script-library (2 stars, last pushed 2mo ago), licensed MIT. It adds 6,115 tokens to every session, about $0.0245 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

msp-script-library CLAUDE.md compared with instructions from other repositories

msp-script-library CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
msp-script-library CLAUDE.mdDTC-Inc/msp-script-libraryInstructions file22mo agoMITA6,115Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file281k2d agoMITA4,335Codex, OpenCode