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/isbeorn/nina/agents-mdgit clone --depth 1 https://github.com/isbeorn/ninaWrote 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/instructions/isbeorn/nina/agents-md)<a href="https://agentmods.dev/instructions/isbeorn/nina/agents-md"><img src="https://agentmods.dev/badge/instructions/isbeorn/nina/agents-md.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 | $0.02701 | $0.02701 |
| Opus 5 | $0.01350 | $0.01350 |
| Sonnet 5 | $0.00540 | $0.00540 |
| Haiku 4.5 | $0.00270 | $0.00270 |
Grade A, and why
nina AGENTS.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 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file is a solution-wide navigation guide for humans and coding agents working in NINA.sln. It complements the per-project ARCHITECTURE.md files and stays focused on boundaries that are backed up by the code.
For repository-wide contribution workflow, branch expectations, release-note updates, and general coding rules, also read CONTRIBUTING.md.
Scope
This guide covers the projects listed in NINA.sln.
Documentation Boundary
NINA.Docsis a git submodule declared in.gitmodulesand points tohttps://github.com/isbeorn/nina.docs.git.- It is not part of the
NINA.slnproject architecture documented below. - If a code change also requires user-facing documentation updates, handle that separately in the
NINA.Docssubmodule /nina.docsrepository, following the documentation notes inCONTRIBUTING.md.
Repository Knowledge
- Treat repository-local, versioned files as the system of record for future contributors and coding agents.
- Keep this file as a map. Put detailed subsystem guidance in the owning
ARCHITECTURE.md,CONTRIBUTING.md, or a focused checked-in reference. - If a review, bug, or repeated agent mistake reveals a durable rule, update the nearest doc, test, analyzer, script, or route map instead of relying on off-repo memory.
Code Style And Formatting
- Maintain the existing line-ending style of every touched file; default to CRLF for new files unless the target location dictates LF.
- Treat the root
.editorconfigas the canonical C# style source. It covers indentation, line endings, namespace style,usingplacement,varpreferences, naming, and selected analyzer severities. - Do not introduce new warnings casually. If an existing warning blocks a focused cleanup, keep the fix scoped and document any intentional deferral in the PR.
- For XAML, follow surrounding file style; no repo-wide XAML formatter configuration is checked in.
- Prefer modern C# supported by the target project. For new or refactored MVVM code, prefer
CommunityToolkit.Mvvmwhere it fits instead of expanding legacy relay-command patterns.
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 · 230 lines · 2,701 tokens per session scan A 891ae7b3dda4
nina AGENTS.md is an instructions file published in the GitHub repository isbeorn/nina (227 stars, last pushed 6d ago), licensed MPL-2.0. It adds 2,701 tokens to every session, about $0.0135 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
Fluence.Wpf AGENTS.md
AGENTS.md instructions for sintaxasn/Fluence.Wpf, covering fluence.wpf - developer handbook, 1. project overview, solution layout, clr namespaces and 2. coding standards.
Fluence.Wpf copilot-instructions.md
Copilot instructions for sintaxasn/Fluence.Wpf, covering fluence.wpf -- copilot instructions, project at a glance, non-negotiable rules, theme architecture (3-slot layout -- do not break) and reference priority.
ModbusForge AGENTS.md
AGENTS.md instructions for nokkies/ModbusForge, covering ai agent instructions, git workflow, pushing changes to github, creating a release and versioning.
Fluence.Wpf CLAUDE.md
Claude Code instructions for sintaxasn/Fluence.Wpf, a project described as: Fluence.Wpf is a modern theming and control library based on WinUI 3, but for WPF on .NET 4.7.2 / .NET 10.
maui uitests.instructions.md
Instructions for dotnet/maui, covering ui testing guidelines for .net maui, ui test structure, two-project requirement, base class and infrastructure and naming conventions.
maui performance-hotpaths.instructions.md
Instructions for dotnet/maui, covering performance-critical path rules, hot paths in maui, allocation avoidance, caching and invalidation and collection iteration.