A command for starting a read-only Azure red-team reconnaissance engagement, which checks the setup, validates the agreed scope, and builds an inventory of cloud resources.

Use it to check an Azure environment, confirm which subscription and resource types are in scope, record exclusions, and create a resource inventory.

It helps catch missing tools, sign-in problems, invalid scope, and unsafe multi-subscription targets before reconnaissance begins.

How Contoso-State/red-team-agent-orchestration configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Contoso-State/red-team-agent-orchestration. 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/Contoso-State/red-team-agent-orchestration/main/.claude/commands/recon.md

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/contoso-state/red-team-agent-orchestration/recon/github.svg)](https://agentmods.dev/commands/contoso-state/red-team-agent-orchestration/recon)

Your own site

<a href="https://agentmods.dev/commands/contoso-state/red-team-agent-orchestration/recon"><img src="https://agentmods.dev/badge/commands/contoso-state/red-team-agent-orchestration/recon/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/contoso-state/red-team-agent-orchestration/recon"><img src="https://agentmods.dev/badge/commands/contoso-state/red-team-agent-orchestration/recon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,359 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00021	$0.01359
Opus 5	$0.00010	$0.00679
Sonnet 5	$0.00004	$0.00272
Haiku 4.5	$0.00002	$0.00136

Measured 10d ago against content hash ba4656a382ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

recon 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 10d 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/recon.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/recon — Reconnaissance & Inventory

You are acting as the Orchestrator Agent (agents/orchestrator/system-prompt.md). Begin a new red team engagement reconnaissance phase.

Steps

Verify the environment. Run node tools/preflight/check-environment.mjs. If any required check fails (Node ≥ 22.5, Azure CLI installed + signed in, resource-graph extension), show the doctor's remediation and stop until it passes — the inventory pipeline needs all of them. This is read-only.
Load scope. Read engagement.yaml. If it does not exist, tell the user to copy engagement.example.yaml to engagement.yaml and fill it in, then stop.
Validate scope against schemas/engagement.schema.json. Echo a one-line summary: engagement ID, mode, target subscription, assessment focus (scope.domains / scope.resource_types), and any exclusions. Confirm with the user before proceeding if anything looks off.
- Hard stop: scope.subscriptions must contain exactly one subscription. If not, stop and require /setup to regenerate engagement.yaml for a single-subscription run.
- If no focus is set (scope.resource_types and scope.domains both empty), ask "What is your assessment focus for this subscription?" before enumerating — offer the focus menu (Full estate · Public/internet exposure · Virtual Machines & compute · Data stores · Identity & access · AI/Foundry · Logging & governance · DevOps & supply chain · or specific resource types like just VMs or just Public IPs). Pass the chosen scope.resource_types to the Inventory agent so Resource Graph filters server-side.

3.5. Confirm identity, target, and mode — do not proceed until the user says yes.

Run az account show and present a full pre-flight confirmation block:

Read the full file on GitHub · 73 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.

10d ago First seen · 73 lines · 21 tokens per session scan A ba4656a382ed

Subscribe to this mod's changes

recon is a command published in the GitHub repository Contoso-State/red-team-agent-orchestration (6 stars, last pushed 5d ago), licensed MIT. It adds 21 tokens to every session and 1,359 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.

Cloud DevOps and cloud Security

cost-optimize

You are a cloud cost optimization expert specializing in reducing infrastructure expenses while maintaining performance and reliability. Analyze cloud spending, identify savings opportunities, and implement cost-effective architectures across AWS, Azure, GCP, and OCI. Where provider-specific code appears below, adapt…

wshobson/agents · 0 tokens

deploy

Deploy a frontend (React, Next.js, or static HTML) to a live URL on Butterbase.

butterbase-ai/butterbase-skills · 20 tokens

integrate

Set up third-party service integrations.

nxtg-ai/forge-plugin · 6 tokens

env

Manage Vercel environment variables. Commands include list, pull, add, remove, and diff. Use to sync environment variables between Vercel and your local development environment.

vercel/vercel-plugin · 35 tokens

scan

Scan AWS account for cost optimization.

prajapatimehul/claude-aws-cost-saver · 6 tokens

finops-feedback

Step 5 (Feedback Loop & Celebration) — measure realized against projected savings, compute a labelled Cloud Entropy proxy, close the opportunity, and emit at least one new idea or policy update so the loop actually closes. Applies the double-loop gate. Mutates on the closure path.

glassity/agent-skills · 57 tokens

red-team-agent-orchestration: Command for Claude Code