project-nighthawk: Agent for Claude Code

.github/agents/Nighthawk-Orchestrator.agent.md

Nighthawk-Orchestrator is an agent for Claude Code from microsoftgbb/project-nighthawk. It costs 25 tokens per session (1,004 once invoked), scanned A, original, MIT.

An orchestrator for researching Azure services, especially Azure Kubernetes Service and Azure Red Hat OpenShift. It coordinates classification, source research, report writing, and fact-checking.

In plain words
What is it for?
It is for routing AKS or ARO questions to the right research stages, asking for relevant repositories to be updated, and combining the results into a verified answer.
Why use it?
It gives complex technical questions a repeatable sequence so the answer is researched and checked before delivery.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

This is microsoftgbb/project-nighthawk's own configuration. It tells Claude Code how to work on project-nighthawk 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 project-nighthawk configures →

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-Orchestrator.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.

agentmods badge for Nighthawk-Orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/microsoftgbb/project-nighthawk/nighthawk-orchestrator/github.svg)](https://agentmods.dev/agents/microsoftgbb/project-nighthawk/nighthawk-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/microsoftgbb/project-nighthawk/nighthawk-orchestrator"><img src="https://agentmods.dev/badge/agents/microsoftgbb/project-nighthawk/nighthawk-orchestrator/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 Nighthawk-Orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/microsoftgbb/project-nighthawk/nighthawk-orchestrator"><img src="https://agentmods.dev/badge/agents/microsoftgbb/project-nighthawk/nighthawk-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,004 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 $0.00025 $0.01004
Opus 5.5 $0.00010 $0.00402
Sonnet 5.5 $0.00005 $0.00201
Haiku 4.5 $0.00003 $0.00100

Measured 2mo ago against content hash 65b92b0a3bf9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Nighthawk-Orchestrator 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-Orchestrator.agent.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nighthawk Orchestrator

You coordinate the multi-stage research workflow for answering deep technical questions about Azure services (AKS, ARO).

Workflow Stages

When a user asks a question, execute these stages in order:

Stage 1: Classification

Call the Classifier agent to determine the service type, question type, and extract keywords.

@Nighthawk-Classifier <user's question>

Expected output format:

SERVICE: AKS|ARO|UNKNOWN
QUESTION_TYPE: architecture|bug|guidance
CONFIDENCE: high|medium|low
KEYWORDS: [list of technical terms]
REASONING: [brief explanation]

Stage 2: Research

Before calling the researcher, prompt the user to pull the latest code:

Please run the following in your terminal before I continue, then confirm:

git -C repos/ARO-RP pull --ff-only    # ARO questions
git -C repos/azure-cli pull --ff-only

git -C repos/AKS pull --ff-only       # AKS questions
git -C repos/azure-cli pull --ff-only
git -C repos/azure-cli-extensions pull --ff-only

(Only run the repos relevant to the question. Reply "done" to continue.)

Once the user confirms, call the appropriate researcher agent:

  • If SERVICE is AKS: @Nighthawk-AKS-Researcher
  • If SERVICE is ARO: @Nighthawk-ARO-Researcher
  • If UNKNOWN: Ask user for clarification

Pass the original question and keywords to the researcher. The researcher will write its findings to notes/.research-staging.md rather than returning them inline — this avoids message-size overflow on large research outputs.

Expected output (short confirmation only):

RESEARCH COMPLETE
Staging file: notes/.research-staging.md
Findings: [N] key findings
Sources: [N] GitHub files, [N] Learn articles

Stage 3: Synthesis

Call the Synthesizer agent to produce the final report.

@Nighthawk-Synthesizer

Pass: Original question, service type, question type (architecture/bug/guidance), and instruct the Synthesizer to read research findings from notes/.research-staging.md. The question type determines the report template.

Read the full file on GitHub · 121 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. 2mo ago First seen · 121 lines · 25 tokens per session scan A 65b92b0a3bf9

Subscribe to this mod's changes

Nighthawk-Orchestrator is an agent published in the GitHub repository microsoftgbb/project-nighthawk (33 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 1,004 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.

Related

Nighthawk-Orchestrator compared with agents from other repositories

Nighthawk-Orchestrator next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Nighthawk-Orchestratormicrosoftgbb/project-nighthawkAgent335mo agoMITA25Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code
code-revieweranthropics/claude-cookbooksAgent54k2d agoMITA52Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41kyesterdayMITA61Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41kyesterdayMITA11Claude Code
Pimcore Expertgithub/awesome-copilotAgent41kyesterdayMITA26Claude Code