setup

setup is a command for Claude Code from Contoso-State/red-team-agent-orchestration. It costs 16 tokens per session (2,302 once invoked), scanned A, original, MIT.

A first-time setup command for choosing an Azure subscription and creating the local scope file for an assessment. An Azure subscription is the account container that holds cloud resources and billing.

In plain words
What is it for?
Use it to check Azure sign-in, review an existing scope, and create or replace the engagement configuration before assessment work begins.
Why use it?
It helps ensure the assessment starts with the correct signed-in account and clearly records which subscription is allowed.

Command for Claude Code

Written for Claude Code: installed under .claude/.

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 commands/contoso-state/red-team-agent-orchestration/setup
Clone the repo
git clone --depth 1 https://github.com/Contoso-State/red-team-agent-orchestration

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 setup

README.md
[![agentmods](https://agentmods.dev/badge/commands/contoso-state/red-team-agent-orchestration/setup.svg)](https://agentmods.dev/commands/contoso-state/red-team-agent-orchestration/setup)
Your own site
<a href="https://agentmods.dev/commands/contoso-state/red-team-agent-orchestration/setup"><img src="https://agentmods.dev/badge/commands/contoso-state/red-team-agent-orchestration/setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,302 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 5.1 $0.00016 $0.02302
Opus 5 $0.00008 $0.01151
Sonnet 5 $0.00003 $0.00460
Haiku 4.5 $0.00002 $0.00230

Measured 6d ago against content hash 7bf8737e77fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

setup 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/commands/setup.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/setup — Engagement Setup

You are acting as the Orchestrator Agent (Pentest Manager). Walk the user through creating engagement.yaml for a new Azure red team assessment. This is read-only — you only read Azure account context and write the local engagement.yaml scope file. Never assess resources here.

Steps

  1. Check for an existing scope. If engagement.yaml already exists, show its current engagement name, mode, and target subscription, and ask the user whether to keep, edit, or replace it. Only continue if they want to create or replace.

  2. Confirm Azure sign-in and identity. Run az account show. If it fails or returns nothing, tell the user to run az login first, then stop. (Tip: node tools/preflight/check-environment.mjs verifies sign-in plus the rest of the toolchain — Node, the Azure CLI, and the resource-graph extension — in one read-only step.)

    Once signed in, display the authenticated identity in a clear summary block:

    ┌─────────────────────────────────────────────────────────────┐
    │  Authenticated identity                                      │
    │  Name/UPN:  <displayName or userPrincipalName>               │
    │  Type:      <user | service-principal | managed-identity>   │
    │  Object ID: <id>                                             │
    │  Tenant:    <tenantId>                                       │
    └─────────────────────────────────────────────────────────────┘
    

    Then ask explicitly:

    ⚠️ This assessment runs in READ-ONLY mode. All Azure operations are restricted to read/query commands. No resources will be modified.

    Is this the correct identity to run the assessment as?

    • Type yes to continue.
    • Type no (or run az login / az login --service-principal) to change identity first.

Read the full file on GitHub · 141 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. 6d ago First seen · 141 lines · 16 tokens per session scan A 7bf8737e77fa

Subscribe to this mod's changes

setup is a command published in the GitHub repository Contoso-State/red-team-agent-orchestration (6 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 2,302 once invoked, about $0.0001 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.