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.
curl -O https://raw.githubusercontent.com/Contoso-State/red-team-agent-orchestration/main/AGENTS.mdgit clone --depth 1 https://github.com/Contoso-State/red-team-agent-orchestrationWrote 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.
[](https://agentmods.dev/instructions/contoso-state/red-team-agent-orchestration/agents-md)<a href="https://agentmods.dev/instructions/contoso-state/red-team-agent-orchestration/agents-md"><img src="https://agentmods.dev/badge/instructions/contoso-state/red-team-agent-orchestration/agents-md/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.
<a href="https://agentmods.dev/instructions/contoso-state/red-team-agent-orchestration/agents-md"><img src="https://agentmods.dev/badge/instructions/contoso-state/red-team-agent-orchestration/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.03140 | $0.03140 |
| Opus 5.5 | $0.01256 | $0.01256 |
| Sonnet 5.5 | $0.00628 | $0.00628 |
| Haiku 4.5 | $0.00314 | $0.00314 |
Grade A, and why
red-team-agent-orchestration AGENTS.md 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 1mo 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| `tools/az/run-az.mjs` | Canonical shell-free, guard-gated `az` runner. **Never `spawnSync('az', …)` from Node** — on Windows `az` is a `.cmd` wrapper that fails ENOENT/EINVAL, which silently turns unrun checks into "0 How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Azure Red Team Agent Orchestration
Repository Purpose
This repository contains an agentic red team platform for Azure cloud infrastructure security assessment. AI agents coordinate to perform comprehensive penetration testing against Azure environments, identifying vulnerabilities across identity, RBAC, networking, compute/Kubernetes, data/SQL, web & static sites, AI/Foundry, external attack surface (EASM), governance & posture, DevOps & supply chain, email (M365), and monitoring domains.
Architecture
The system's primary orchestration standard is an explicit declarative graph, wired into the native Copilot CLI layers:
- Canonical graph (
graph/redteam.graph.json) — the single source of truth for scope validation, methodology memory, preflight inventory, parallel specialist fan-out, deterministic reduce, bounded evaluator-optimizer reflection, false-positive judging, human-in-the-loop active-lane interrupts, correlation, reporting, and Reflexion debrief. - Custom agents (
.github/agents/*.agent.md) — the dispatchable team. The user-invocableredteam-orchestrator(Pentest Manager) hands tasks to domain sub-agents through theagent(Task) tool. Sub-agents setdisable-model-invocation: trueso they only run when the Orchestrator dispatches them. - Skills (
.github/skills/azure-redteam-*) — auto-loaded domain knowledge each agent draws on. - Extension/hooks (
.github/extensions/redteam-guardrails) — a session-widepreToolUsehook that enforces read-only as an allowlist (deny-by-default) acrossaz/azdand Azure PowerShell, for every agent.
Graph engineering & self-improvement
The dependency-free Node runner (tools/graph/run-graph.mjs) provides deterministic graph execution with simulated dispatch by default; it does not launch a live Azure assessment. The separate live entry point (tools/graph/run-live.mjs) uses the Claude native adapter for bounded live assessment, with an explicit scoped engagement and fresh preflight. Standalone live CLI adapters for Copilot, Codex, and Cursor are not implemented; those runtimes support native agent orchestration separately. The first-class LangGraph deployment target in integrations/langgraph/ compiles the same JSON spec into a StateGraph and reuses the same read-only guard through a subprocess bridge.
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.
- 1mo ago Changed · +16 lines · +253 tokens per session 739f2b39ccc8
- 1mo ago Changed · +3 lines · +190 tokens per session 3bee53b22564
- 1mo ago Changed · +10 tokens per session 53c08ab53bd8
- 1mo ago First seen · 136 lines · 2,687 tokens per session scan A 38eb1ab2348b
red-team-agent-orchestration AGENTS.md is an instructions file published in the GitHub repository Contoso-State/red-team-agent-orchestration (6 stars, last pushed 1mo ago), licensed MIT. It adds 3,140 tokens to every session, about $0.0126 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.