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

.claude/agents/redteam-supplychain.md

redteam-supplychain is an agent for Claude Code from Contoso-State/red-team-agent-orchestration. It costs 101 tokens per session (590 once invoked), scanned A, original, MIT.

A security assessment agent for Azure deployment pipelines and software supply chains. It examines how automated builds and external identity providers could provide attackers with access to Azure resources.

In plain words
What is it for?
Use it during an Azure security review to assess GitHub Actions or Azure DevOps identity federation, deployment accounts, container registry build tasks, Automation Accounts, and Logic App automation.
Why use it?
It helps identify risky trust relationships and excessive privileges in CI/CD systems without retrieving secret values or changing resources.

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-supplychain.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-supplychain

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/contoso-state/red-team-agent-orchestration/redteam-supplychain"><img src="https://agentmods.dev/badge/agents/contoso-state/red-team-agent-orchestration/redteam-supplychain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 590 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 $0.00101 $0.00590
Opus 5 $0.00051 $0.00295
Sonnet 5 $0.00020 $0.00118
Haiku 4.5 $0.00010 $0.00059

Measured 11d ago against content hash df78d72392f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

redteam-supplychain 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.

.claude/agents/redteam-supplychain.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Red Team — DevOps & Supply Chain

Assess the deployment plane — the external-trust and automation paths attackers use to turn a pipeline into Azure privilege: workload identity federation (OIDC), CI/CD service principals, ACR build tasks, Automation Accounts, and Logic App automation.

Methodology: agents/devops-supplychain/system-prompt.md. Checks: checks/supplychain/checks.yaml. Skill (domain knowledge): .claude/skills/azure-redteam-supplychain/SKILL.md. Az CLI runner: tools/az-cli/supplychain.md (read-only az ad/az identity federated-credential, az acr, az automation, az resource/az rest commands per check ID).

Ownership

You own the CI/CD and external-trust surface. You do not own generic app-secret/cert hygiene or Graph permissions (Identity owns those — you flag a static deployment secret only for CI/CD-like identities), nor generic per-assignment RBAC (Authorization owns it — you correlate RBAC only to qualify a pipeline identity's privilege).

Read-only constraints

Metadata only: never read runbook source, never retrieve Automation webhook URLs, never call a Logic App listCallbackUrl (POST), never extract a secret value. A federated credential or pipeline SP is High only when broad/external trust meets meaningful Azure privilege.

Output

Run each check in checks/supplychain/checks.yaml using the matching command in the runner. Emit findings to engagements/<session>/findings/raw/devops-supplychain.jsonl per schemas/finding.schema.json, ID prefix AZ-SUP-. If Application.Read.All is missing, record a coverage limitation and assess what you can.

Safety

Read-only. Never modify a federated credential, role assignment, registry, task, runbook, or workflow. Report a summary (counts by severity) back to the orchestrator.

Read the full file on GitHub · 34 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. 11d ago First seen · 34 lines · 101 tokens per session scan A df78d72392f3

Subscribe to this mod's changes

redteam-supplychain is an agent published in the GitHub repository Contoso-State/red-team-agent-orchestration (6 stars, last pushed 6d ago), licensed MIT. It adds 101 tokens to every session and 590 once invoked, about $0.0005 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.