redteam-governance

redteam-governance is a cursor rule for Cursor from Contoso-State/red-team-agent-orchestration. It costs 87 tokens per session (473 once invoked), scanned A, original, MIT.

A read-only Azure security review focused on cloud-wide guardrails, which are controls intended to prevent unsafe configuration. It examines Azure Policy, Defender for Cloud, management groups, resource locks, and security contacts.

In plain words
What is it for?
Use it to assess policy coverage and exceptions, cloud security posture, inherited management-group controls, resource locks, and security-contact settings.
Why use it?
It shows where protective controls are missing, weakened, or inconsistently applied across an Azure environment.

Cursor rule for Cursor

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

Good fit Use it to assess policy coverage and exceptions, cloud security posture, inherited management-group controls, resource locks, and security-contact settings.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/rules/contoso-state/red-team-agent-orchestration/redteam-governance"><img src="https://agentmods.dev/badge/rules/contoso-state/red-team-agent-orchestration/redteam-governance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 473 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 $0.00087 $0.00473
Opus 5 $0.00044 $0.00236
Sonnet 5 $0.00017 $0.00095
Haiku 4.5 $0.00009 $0.00047

Measured 11d ago against content hash 59845deea368, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

redteam-governance 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 11d 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-governance.mdc · 30 lines

What it actually says

Red Team — Governance & Posture

Assess the Azure control plane — the guardrails meant to prevent, detect, and contain misconfiguration: Azure Policy coverage, Defender for Cloud posture, management-group hierarchy, resource locks, and security contacts.

Methodology: agents/governance-posture/system-prompt.md. Checks: checks/governance/checks.yaml. Skill (domain knowledge): .github/skills/azure-redteam-governance/SKILL.md. Az CLI runner: tools/az-cli/governance.md (read-only az policy / az security / az account management-group / az lock commands per check ID).

Ownership

You own control-plane guardrails. You do not re-flag Defender plan on/off (Logging owns CHK-LOG-DEFENDER-DISABLED), per-assignment RBAC (Authorization owns it — you flag only MG/root inheritance/blast-radius), or diagnostic/SIEM coverage (Logging).

Output

Run each check in checks/governance/checks.yaml using the matching command in the runner. Emit findings to engagements/<session>/findings/raw/governance-posture.jsonl per schemas/finding.schema.json, ID prefix AZ-GOV-. If Security Reader or Management Group Reader is missing, record a coverage limitation and continue.

Safety

Read-only. Never modify a policy, exemption, lock, or contact. Report a summary (counts by severity) back to the orchestrator.

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. 11d ago First seen · 30 lines · 87 tokens per session scan A 59845deea368

Subscribe to this mod's changes

redteam-governance is a cursor rule published in the GitHub repository Contoso-State/red-team-agent-orchestration (6 stars, last pushed 6d ago), licensed MIT. It adds 87 tokens to every session and 473 once invoked, about $0.0004 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.