00-redteam-readonly

00-redteam-readonly is a cursor rule for Cursor from Contoso-State/red-team-agent-orchestration. It costs 451 tokens per session, scanned A, original, MIT.

A set of rules for running Azure red-team reviews in read-only mode. It allows querying cloud settings while blocking changes, public attack testing, and access inside live containers or clusters unless the engagement explicitly enables and approves those activities.

In plain words
What is it for?
Use it as a safety boundary for Azure assessments: to allow read and query commands, require approval for controlled changes, restrict public probing to an authorised target list, and gate live cluster or container access.
Why use it?
It keeps assessment work from changing production systems or performing intrusive tests without clear authorisation. It also defines which specialist agent may perform each exceptional type of testing.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it as a safety boundary for Azure assessments: to allow read and query commands, require approval for controlled changes, restrict public probing to an authorised target list, and gate live cluster or container access.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/contoso-state/red-team-agent-orchestration/00-redteam-readonly
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 00-redteam-readonly

README.md
[![agentmods](https://agentmods.dev/badge/rules/contoso-state/red-team-agent-orchestration/00-redteam-readonly/github.svg)](https://agentmods.dev/rules/contoso-state/red-team-agent-orchestration/00-redteam-readonly)
Your own site
<a href="https://agentmods.dev/rules/contoso-state/red-team-agent-orchestration/00-redteam-readonly"><img src="https://agentmods.dev/badge/rules/contoso-state/red-team-agent-orchestration/00-redteam-readonly/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 00-redteam-readonly

Your own site · 80×15
<a href="https://agentmods.dev/rules/contoso-state/red-team-agent-orchestration/00-redteam-readonly"><img src="https://agentmods.dev/badge/rules/contoso-state/red-team-agent-orchestration/00-redteam-readonly.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 451 This file is loaded in full into every session.
When invoked 451 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.00451 $0.00451
Opus 5 $0.00226 $0.00226
Sonnet 5 $0.00090 $0.00090
Haiku 4.5 $0.00045 $0.00045

Measured 10d ago against content hash a0e4d1c5efb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

00-redteam-readonly scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

redteam-guardrails active: this is an Azure red team engagement with a READ-ONLY posture. Only read/query Azure commands are permitted (az list/show/get/query, Get-Az*, az rest --method GET). Mutating az/azd/Az PowerShel
.cursor/rules/00-redteam-readonly.mdc · 13 lines

What it actually says

Azure Red Team — Read-Only Posture

redteam-guardrails active: this is an Azure red team engagement with a READ-ONLY posture. Only read/query Azure commands are permitted (az list/show/get/query, Get-Az*, az rest --method GET). Mutating az/azd/Az PowerShell commands are blocked unless engagement.yaml sets mode: controlled-validation, in which case they require explicit human approval. The orchestrator must dispatch specialist agents — it does not run az itself. Active external probing (curl/nuclei/zap/sqlmap/nikto/httpx/testssl/nmap and similar) against public hosts is BLOCKED by default and only permitted for the External Vulnerability Agent (EVA) when the engagement is in mode: external-active-testing with external_testing enabled + authorized, and only against hosts on the Azure-derived allowlist (engagements//scope/external-targets.json). Reaching INTO a live cluster or container (kubectl exec/debug/cp/attach/port-forward/run, kube-bench, kubesec, trivy, grype, crictl, docker/nerdctl/podman run|exec) is BLOCKED by default and only permitted for the Azure Container & Kubernetes Agent when the engagement is in mode: cluster-active-testing with cluster_testing enabled + authorized, and only against clusters/registries on the Azure-derived cluster allowlist (engagements//scope/cluster-targets.json). Mutating kubectl/helm/runtime commands are blocked in EVERY mode; read-only kubectl (get/describe/logs/auth can-i) is always allowed.

The .cursor/hooks guard enforces this allowlist on every shell command and surfaces MCP tool calls for approval; never attempt to bypass it. Validate engagement scope and operate on one subscription at a time.

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. 10d ago First seen · 13 lines · 451 tokens per session scan A a0e4d1c5efb1

Subscribe to this mod's changes

00-redteam-readonly is a cursor rule published in the GitHub repository Contoso-State/red-team-agent-orchestration (6 stars, last pushed 5d ago), licensed MIT. It adds 451 tokens to every session, about $0.0023 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.