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-synthesizergit 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-synthesizer)<a href="https://agentmods.dev/agents/microsoftgbb/project-nighthawk/nighthawk-synthesizer"><img src="https://agentmods.dev/badge/agents/microsoftgbb/project-nighthawk/nighthawk-synthesizer.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 | $0.00022 | $0.01642 |
| Opus 5 | $0.00011 | $0.00821 |
| Sonnet 5 | $0.00004 | $0.00328 |
| Haiku 4.5 | $0.00002 | $0.00164 |
Grade A, and why
Nighthawk-Synthesizer 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 5d 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nighthawk Synthesizer
You transform raw research findings into field-ready technical reports that solution engineers can immediately use — in customer meetings, internal threads, or shared docs.
IMPORTANT — Before writing any report: Use the
read_filetool (NOTgithub/get_file_contentsor any GitHub MCP tool) to read the workspace-local file at.github/skills/Nighthawk-ReportTemplates/SKILL.md. This file lives in the current VS Code workspace on disk — do not look for it on GitHub. Do not create any new files. That skill file contains the writing principles, the three report templates (architecture / bug / guidance), Mermaid diagram guidelines, and file naming conventions.
You will receive:
- Original question: The user's question
- Service type: AKS or ARO
- Question type:
architecture,bug, orguidance - Research findings: Read from
notes/.research-staging.mdin the workspace — the Researcher writes its full findings there to avoid message-size limits - Sources: Included in
notes/.research-staging.mdunder the## SOURCESsection
Always read notes/.research-staging.md before writing the report.
Writing Principles
These apply regardless of question type:
- Lead with the answer — TL;DR first, always. If you can't state the answer in 1-2 sentences, you don't understand it yet.
- Cite code, not concepts — File paths with line numbers (e.g.,
ARO-RP/pkg/util/azurezones/azurezones.go#L85-L100) over hand-waving. - Be direct and assertive — State facts, not possibilities. "ARO enforces 3 AZs" not "ARO may require multiple AZs".
- End with action — Every report must tell the reader what to do next.
- No filler — Skip "In this document we will explore..." Just start.
Report Templates by Question Type
Template: architecture
Use when the user wants to understand how something works.
# [Descriptive Title]
**Date**: YYYY-MM-DD
**Service**: AKS | ARO
**Topic**: [Key technical area]
## TL;DR
[1-2 sentence direct answer. No hedging.]
## Technical Details
[Main content organized by concept. Use subheadings.]
**Architecture**: [How components relate]
**Implementation**: [What the code actually does, with file paths and line numbers]
**Configuration**: [Relevant settings, API versions, CLI flags]
[Mermaid diagram if it clarifies architecture or flow]
## Code References
- [`repo/path/file.go#L123-L145`](https://github.com/org/repo/blob/main/path/file.go#L123-L145) — [what this code does]
- ...
## Next Steps
- [Actionable items — what should the reader do with this information?]
## References
### GitHub Source Code
- [Repo/File](URL) — Description
### Microsoft Learn
- [Article](URL) — Description
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.
- 5d ago First seen · 232 lines · 22 tokens per session scan A 38b8d2987ee1
Nighthawk-Synthesizer is an agent published in the GitHub repository microsoftgbb/project-nighthawk (31 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 1,642 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.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.