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

.claude/agents/redteam-email.md

redteam-email is an agent for Claude Code from Contoso-State/red-team-agent-orchestration. It costs 89 tokens per session (532 once invoked), scanned A, original, MIT.

An optional security reviewer for Microsoft 365 email systems, including Exchange Online and Defender for Office 365. It checks how domains authenticate email and how Microsoft protects against phishing, spoofing, unsafe links, and harmful attachments.

In plain words
What is it for?
Use it during a red-team security assessment when Microsoft 365 email is in scope, with permission to read DNS and Microsoft security settings.
Why use it?
It helps reveal email settings and mail-flow rules that could let attackers impersonate senders or deliver dangerous messages.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions subagents; names the TodoWrite tool.

This is Contoso-State/red-team-agent-orchestration's own configuration. It tells Claude Code how to work on red-team-agent-orchestration itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything red-team-agent-orchestration configures →

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/agents/redteam-email.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.

agentmods badge for redteam-email

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/contoso-state/red-team-agent-orchestration/redteam-email"><img src="https://agentmods.dev/badge/agents/contoso-state/red-team-agent-orchestration/redteam-email.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 532 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 $0.00089 $0.00532
Opus 5 $0.00044 $0.00266
Sonnet 5 $0.00018 $0.00106
Haiku 4.5 $0.00009 $0.00053

Measured 10d ago against content hash 035c1cd8727e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

redteam-email 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/agents/redteam-email.md · 39 lines

What it actually says

Red Team — Email Security (Optional, Microsoft 365)

Assess the organization's email security posture: domain authentication and the Exchange Online / Defender for Office 365 protections that stop phishing and spoofing.

Optional / adjacent scope. This domain is Microsoft 365 / Exchange Online, not core Azure. Dispatch it only when engagement.yaml scope includes M365 / Exchange and the caller has the required Microsoft Graph / Exchange Online read permissions. It is not a dependency for a baseline Azure assessment.

Methodology: agents/email-security/system-prompt.md. Checks: checks/email/checks.yaml. Skill (domain knowledge): .claude/skills/azure-redteam-email/SKILL.md. Az CLI runner: tools/az-cli/email.md.

Boundary

You own email authentication and mail protection: SPF/DKIM/DMARC, EOP/Defender for Office 365 policies, and mail-flow rules. Entra identity controls (MFA, Conditional Access, app registrations) remain with the identity agent — do not duplicate them.

Output

Run each check in checks/email/checks.yaml. Tooling is DNS resolution (SPF/DKIM/DMARC TXT) and Microsoft Graph via az rest GET (and/or Exchange Online PowerShell Get-* cmdlets where available). Emit findings to engagements/<session>/findings/raw/email-security.jsonl, ID prefix AZ-MAIL-.

Safety

Read-only. DNS lookups and Graph/Exchange Get-* reads only. Never send test phishing mail, never modify transport rules or policies, never read message contents. Report a summary 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. 10d ago First seen · 39 lines · 89 tokens per session scan A 035c1cd8727e

Subscribe to this mod's changes

redteam-email is an agent published in the GitHub repository Contoso-State/red-team-agent-orchestration (6 stars, last pushed 6d ago), licensed MIT. It adds 89 tokens to every session and 532 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.