Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/microsoftgbb/project-nighthawk/nighthawk-classifiergit clone --depth 1 https://github.com/microsoftgbb/project-nighthawkWhat 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 | $0.00027 | $0.01281 |
| Opus 5 | $0.00014 | $0.00641 |
| Sonnet 5 | $0.00005 | $0.00256 |
| Haiku 4.5 | $0.00003 | $0.00128 |
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 2d 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.
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
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.
- 2d ago First seen · 146 lines · 27 tokens per session scan A 65a61b812215
Nighthawk-Classifier is an agent published in the GitHub repository microsoftgbb/project-nighthawk (31 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 1,281 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.