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 instructions/microsoftgbb/project-nighthawk/copilot-instructionsgit 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 | $0.00513 | $0.00513 |
| Opus 5 | $0.00257 | $0.00257 |
| Sonnet 5 | $0.00103 | $0.00103 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
project-nighthawk copilot-instructions.md 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nighthawk Workspace Instructions
When working in this repository, you are helping to create deep technical notes about Azure Services and related technologies.
Using Nighthawk
For solution engineers: To generate a comprehensive, fact-checked technical report, use:
/Nighthawk <your question about AKS or ARO>
The orchestrator will automatically:
- Classify your question (AKS vs ARO)
- Research official GitHub repositories and Microsoft Learn
- Synthesize findings into a comprehensive report
- Fact-check all claims against sources
- Deliver a validated report with source citations
Individual agents (for advanced usage):
@Nighthawk-Classifier- Classify a question@Nighthawk-AKS-Researcher- Deep research on AKS@Nighthawk-ARO-Researcher- Deep research on ARO@Nighthawk-Synthesizer- Create report from research@Nighthawk-FactChecker- Validate a report
Note Format
Your findings should be written in markdown format with relevant headings and subheadings. Leverage Mermaid diagrams where appropriate to illustrate complex concepts.
Write the notes in a way that is easy to understand for someone new to the topic, while still providing deep technical insights for experienced users.
File Naming and Location
Save your notes in a file named Nighthawk-$todaysDate-$subject.md in the notes/ directory, where $todaysDate is the current date and $subject is the topic/theme of the note. Update the notes as you discover new information, or when asked to add additional results to the topic.
Ensure to include references and links to the source materials you used to compile the notes.
Skills
The following skills are available to Nighthawk researcher agents:
- nighthawk-local-repos — Required tool checklist, local repo paths, clone commands, and mandatory
git pullprocedure. Researcher agents must read this skill before every research run.- File:
.github/skills/Nighthawk-LocalRepos/SKILL.md
- File:
- nighthawk-report-templates — Writing principles, three report templates (architecture / bug / guidance), Mermaid diagram guidelines, and file naming conventions. Synthesizer must read this skill before writing any report.
- File:
.github/skills/Nighthawk-ReportTemplates/SKILL.md
- File:
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 · 47 lines · 513 tokens per session scan A 29868b1aeb8d
project-nighthawk copilot-instructions.md is an instructions file published in the GitHub repository microsoftgbb/project-nighthawk (31 stars, last pushed 3mo ago), licensed MIT. It adds 513 tokens to every session, about $0.0026 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 instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.