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.
git clone --depth 1 https://github.com/Contoso-State/red-team-agent-orchestrationWrote 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.
[](https://agentmods.dev/rules/contoso-state/red-team-agent-orchestration/redteam-orchestrator)<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.
<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>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 | $0.00155 | $0.02137 |
| Opus 5 | $0.00077 | $0.01069 |
| Sonnet 5 | $0.00031 | $0.00427 |
| Haiku 4.5 | $0.00015 | $0.00214 |
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.
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 |
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.
- 12d ago First seen · 110 lines · 155 tokens per session scan A 1fa01ba55370
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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.