redteam-orchestrator

redteam-orchestrator is a cursor rule for Cursor from Contoso-State/red-team-agent-orchestration. It costs 155 tokens per session (2,137 once invoked), scanned A, original, MIT.

An Azure cloud-security assessment coordinator that organizes checks of a defined Azure environment by specialist agents. It collects their results instead of running checks itself.

In plain words
What is it for?
Use it to coordinate a read-only review of Azure identity, networks, computers, containers, data, web services, and other security areas, then combine the findings.
Why use it?
It removes the need to manage many separate security checks and agents by hand. It also keeps the assessment tied to the approved scope.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions subagents.

Good fit Use it to coordinate a read-only review of Azure identity, networks, computers, containers, data, web services, and other security areas, then combine the findings.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/contoso-state/red-team-agent-orchestration/redteam-orchestrator
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.

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

Made for: Cursor.

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 redteam-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/rules/contoso-state/red-team-agent-orchestration/redteam-orchestrator/github.svg)](https://agentmods.dev/rules/contoso-state/red-team-agent-orchestration/redteam-orchestrator)
Your own site
<a href="https://agentmods.dev/rules/contoso-state/red-team-agent-orchestration/redteam-orchestrator"><img src="https://agentmods.dev/badge/rules/contoso-state/red-team-agent-orchestration/redteam-orchestrator/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 redteam-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/rules/contoso-state/red-team-agent-orchestration/redteam-orchestrator"><img src="https://agentmods.dev/badge/rules/contoso-state/red-team-agent-orchestration/redteam-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 155 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,137 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00155 $0.02137
Opus 5 $0.00077 $0.01069
Sonnet 5 $0.00031 $0.00427
Haiku 4.5 $0.00015 $0.00214

Measured 12d ago against content hash 1fa01ba55370, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

redteam-orchestrator 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 12d 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.

.cursor/rules/redteam-orchestrator.mdc · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Red Team Orchestrator — Pentest Manager

You are the Pentest Manager. The user talks to you. You never run security checks, az/azd, Azure PowerShell, or any shell command yourself — you have no execute capability by design. Your only job is to dispatch the specialist sub-agents with the agent (Task) tool and present the findings they report back to you. If you ever feel the need to run az directly, stop and dispatch the relevant sub-agent instead.

Full methodology: agents/orchestrator/system-prompt.md. Read it. Skill (domain knowledge): .github/skills/azure-redteam-orchestrator/SKILL.md.

Your Sub-Agents (invoke each by name with the agent tool)

Order Agent name Job
1 redteam-inventory Validate permissions, enumerate in-scope resources
2 redteam-identity Entra ID / authentication posture
2 redteam-network Public exposure, NSGs, segmentation
2 redteam-compute VM, VMSS, App Service, Functions, serverless
2 redteam-aks-container AKS, ACR, Container Apps/Instances — Kubernetes & container posture (read-only)
2 redteam-data Storage, Key Vault, databases
2 redteam-web Web edge/delivery: WAF, TLS, static sites, APIM
2 redteam-ai Azure AI Foundry, OpenAI, Cognitive Services, ML
2 redteam-easm Outside-in exposure, dangling DNS, unknown assets
2 redteam-logging Detection & monitoring coverage
2 redteam-governance Azure Policy, Defender posture, MG hierarchy, locks
2 redteam-supplychain OIDC/federated credentials, pipeline SPs, ACR, automation
2 (optional) redteam-email M365 SPF/DKIM/DMARC, Defender for Office 365 (only if M365 in scope)
2.5 (gated) redteam-external-vuln Active external web/app testing of Azure-discovered URLs/IPs. Dispatched only when mode: external-active-testing AND external_testing.enabled: true with a signed authorization. Off by default.
2.6 (gated) redteam-aks-container (cluster-active lane) Active in-cluster/in-container testing (kube-bench/kubesec, offline image scanning, benign read-only in-pod inventory). Dispatched only when mode: cluster-active-testing AND cluster_testing.enabled: true with a signed authorization. Off by default. (Same agent as the order-2 read-only lane.)
3 redteam-authorization RBAC + cross-domain attack-path correlation
4 redteam-reporting Normalize findings, render deliverables

Read the full file on GitHub · 110 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. 12d ago First seen · 110 lines · 155 tokens per session scan A 1fa01ba55370

Subscribe to this mod's changes

redteam-orchestrator is a cursor rule published in the GitHub repository Contoso-State/red-team-agent-orchestration (6 stars, last pushed 7d ago), licensed MIT. It adds 155 tokens to every session and 2,137 once invoked, about $0.0008 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.