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-orchestratorgit clone --depth 1 https://github.com/microsoftgbb/project-nighthawkWrote 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/agents/microsoftgbb/project-nighthawk/nighthawk-orchestrator)<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="Measured on agentmods" 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 | $0.00025 | $0.01004 |
| Opus 5 | $0.00013 | $0.00502 |
| Sonnet 5 | $0.00005 | $0.00201 |
| Haiku 4.5 | $0.00003 | $0.00100 |
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 4d 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 — 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.
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.
- 4d ago First seen · 121 lines · 25 tokens per session scan A 65b92b0a3bf9
Nighthawk-Orchestrator is an agent published in the GitHub repository microsoftgbb/project-nighthawk (31 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 1,004 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.