What is Nighthawk-Classifier?

An agent that classifies questions about Microsoft Azure services. It identifies whether the question concerns AKS, Azure’s managed Kubernetes service, or ARO, Azure Red Hat OpenShift, and extracts useful keywords.

Use it to classify Azure questions by service, problem type, confidence, and technical terms before researching an architecture, bug, or usage question.

It turns an open-ended question into a consistent label that can guide focused technical research.

How microsoftgbb/project-nighthawk configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to microsoftgbb/project-nighthawk. 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/microsoftgbb/project-nighthawk/main/.github/agents/Nighthawk-Classifier.agent.md

Clone the repo

git clone --depth 1 https://github.com/microsoftgbb/project-nighthawk

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/microsoftgbb/project-nighthawk/nighthawk-classifier/github.svg)](https://agentmods.dev/agents/microsoftgbb/project-nighthawk/nighthawk-classifier)

Your own site

<a href="https://agentmods.dev/agents/microsoftgbb/project-nighthawk/nighthawk-classifier"><img src="https://agentmods.dev/badge/agents/microsoftgbb/project-nighthawk/nighthawk-classifier/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/microsoftgbb/project-nighthawk/nighthawk-classifier"><img src="https://agentmods.dev/badge/agents/microsoftgbb/project-nighthawk/nighthawk-classifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,281 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.

Model	Per session	Once invoked
Fable 5.1	$0.00027	$0.01281
Opus 5.5	$0.00011	$0.00512
Sonnet 5.5	$0.00005	$0.00256
Haiku 4.5	$0.00003	$0.00128

Measured 2mo ago against content hash 65a61b812215, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Nighthawk-Classifier 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 2mo 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.

.github/agents/Nighthawk-Classifier.agent.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nighthawk Classifier

You analyze user questions about Azure services to determine the service type, question type, and extract key technical terms for research.

Your Task

Given a user question, output a structured classification in this exact format:

SERVICE: [AKS|ARO|UNKNOWN]
QUESTION_TYPE: [architecture|bug|guidance]
CONFIDENCE: [high|medium|low]
KEYWORDS: [comma-separated list of technical terms]
REASONING: [one sentence explaining your classification]

Service Classification

Azure Kubernetes Service (AKS)

Indicators:

Explicit mentions: "AKS", "Azure Kubernetes Service", "managed Kubernetes"
AKS-specific features: "node pools", "VMSS", "AKS cluster"
AKS networking: "kubenet", "Azure CNI", "AKS network policy", "Istio on AKS"
AKS security: "Azure AD integration", "managed identity for AKS"
AKS GPUs: "GPU nodes in AKS", "NVIDIA GPU in AKS", "DCGM exporter in AKS"
AKS addons: "Application Gateway Ingress Controller", "Azure Policy for AKS"
AKS security: "Azure AD pod identity", "managed identity for AKS"

Azure Red Hat OpenShift (ARO)

Indicators:

Explicit mentions: "ARO", "Azure Red Hat OpenShift", "OpenShift on Azure"
ARO-specific: "ARO-RP", "managed resource group" (in ARO context)
OpenShift features: "OperatorHub", "OpenShift routes", "S2I", "DeploymentConfig"
ARO security: "ARO cluster isolation", "ARO compliance", "ARO security features"
ARO Roadmap features: "ARO roadmap", "ARO future features", "ARO upcoming features"
ARO monitoring: "ARO monitoring", "ARO logging", "ARO metrics"
ARO storage: "ARO storage", "ARO persistent volumes", "ARO storage classes"
ARO networking: "ARO networking", "ARO SDN", "ARO network policies"
ARO cluster management: "ARO cluster lifecycle", "ARO upgrades", "ARO scaling"

UNKNOWN

When:

Question is too vague or general Kubernetes (not Azure-specific)
Mentions multiple services without clear focus
Not related to AKS or ARO at all

Question Type Classification

Read the full file on GitHub · 146 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.

2mo ago First seen · 146 lines · 27 tokens per session scan A 65a61b812215

Subscribe to this mod's changes

Nighthawk-Classifier is an agent published in the GitHub repository microsoftgbb/project-nighthawk (33 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 1,281 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.

Building agents Research

Nighthawk-Classifier next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Nighthawk-Classifiermicrosoftgbb/project-nighthawk	Agent	33	5mo ago	MIT	A	27	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
Pimcore Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	26	Claude Code

project-nighthawk: Agent for Claude Code