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

.claude/commands/redteam-graph.md

redteam-graph is a command for Claude Code from Contoso-State/red-team-agent-orchestration. It costs 12 tokens per session (534 once invoked), scanned A, original, MIT.

A workflow standard for running an Azure red-team assessment as one dependency-aware graph. A graph here is a defined map of tasks, their order, and how their results flow between them.

In plain words
What is it for?
Use it to validate scope, load prior data, run specialist reviews in parallel, merge results, check for false positives, authorize active testing, correlate findings, and produce a report.
Why use it?
It removes ad hoc coordination between checks and makes the assessment sequence, review steps, approvals, and report generation explicit and repeatable.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code; mentions Codex.

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/commands/redteam-graph.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-graph

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/contoso-state/red-team-agent-orchestration/redteam-graph"><img src="https://agentmods.dev/badge/commands/contoso-state/red-team-agent-orchestration/redteam-graph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 534 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 $0.00012 $0.00534
Opus 5 $0.00006 $0.00267
Sonnet 5 $0.00002 $0.00107
Haiku 4.5 $0.00001 $0.00053

Measured 10d ago against content hash 49291160599b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

redteam-graph 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/commands/redteam-graph.md · 29 lines

How it starts

The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Azure Red Team — Graph Orchestration Standard

Every engagement in this framework runs as ONE explicit, declarative graph. The single source of truth is graph/redteam.graph.json (redteam-azure v2.0.0): 14 nodes over a 12-specialist read-only roster, validated by tools/graph/validate-graph.mjs.

Two engines, one graph

  • Dependency-free Node runner — tools/graph/run-graph.mjs — executes the graph inside every CLI runtime (GitHub Copilot, Claude Code, OpenAI Codex, Cursor) with zero runtime dependencies.
  • First-class LangGraph target — integrations/langgraph/ — compiles the same JSON into a Python StateGraph for deployment.

Control flow

validate_scope (one subscription + read-only attestation) -> memory_load -> preflight_inventory -> Send fan-out across the roster (plan_specialists -> run_specialist) -> deterministic fan-in merge (collect_raw) -> bounded evaluator-optimizer reflection loop (evaluate, max_revisions=2, quality_threshold=0.85) -> Agent-as-a-Judge false-positive gate (judge) -> human-authorized active lanes (authorize_active interrupt) -> correlate -> report -> reflexion_debrief.

Self-improving loops (primary standard)

The evaluator-optimizer cycle, the Agent-as-a-Judge gate, and the reflexion debrief are auto-applied at runtime with NO pull request and NO human gate — tools/graph/self-improve.mjs. Cross-run learning is written ONLY to the memory/methodology/ namespace.

Immutable boundary

Read-only enforcement in guardrails/guard.mjs sits OUTSIDE the learning surface. Self-improvement can never modify guardrails/** or any guardrail namespace — that firewall is the one thing the graph cannot rewrite.

When you plan or run an engagement, follow this graph. Do not invent an ad-hoc order of operations; extend the team by editing graph/redteam.graph.json (and its roster) and re-validating, so every runtime and the LangGraph target stay in lock-step.

Read the full file on GitHub · 29 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. 10d ago First seen · 29 lines · 12 tokens per session scan A 49291160599b

Subscribe to this mod's changes

redteam-graph is a command published in the GitHub repository Contoso-State/red-team-agent-orchestration (6 stars, last pushed 5d ago), licensed MIT. It adds 12 tokens to every session and 534 once invoked, about $0.0001 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.