nina: Instructions file for Codex

AGENTS.md

nina AGENTS.md is an instructions file for Codex, OpenCode from isbeorn/nina. It costs 1,355 tokens per session, scanned A, original, MPL-2.0.

Repository guidance for contributors and coding agents working in the NINA solution. It explains project boundaries, where documentation belongs, and which files are the source of truth.

In plain words
What is it for?
Finding the right project guidance, understanding the NINA solution structure, and separating code changes from documentation changes in the NINA.Docs submodule.
Why use it?
It reduces confusion about which instructions apply to which projects and where related documentation changes should be made.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is isbeorn/nina's own configuration. It tells Codex and OpenCode how to work on nina 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 nina configures →

Reuse

Borrowing it

Nothing to install: this file belongs to isbeorn/nina. 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/isbeorn/nina/develop/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/isbeorn/nina

Made for: Codex, OpenCode.

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 nina AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/isbeorn/nina/agents-md/github.svg)](https://agentmods.dev/instructions/isbeorn/nina/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/isbeorn/nina/agents-md"><img src="https://agentmods.dev/badge/instructions/isbeorn/nina/agents-md/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 nina AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/isbeorn/nina/agents-md"><img src="https://agentmods.dev/badge/instructions/isbeorn/nina/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,355 This file is loaded in full into every session.
When invoked 1,355 The same file — it is already loaded in full.
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 $0.01355 $0.01355
Opus 5.5 $0.00542 $0.00542
Sonnet 5.5 $0.00271 $0.00271
Haiku 4.5 $0.00136 $0.00136

Measured 21d ago against content hash 4ebf9187cfc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 21d 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.

AGENTS.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for work in NINA.sln. Keep this entry point compact and put subsystem details in the owning architecture document.

Read For The Task

Use the relevant route when more context is needed. Guidance already loaded for the task does not need to be reread.

Task Reference
Find ownership, trace lifecycle or change a cross-project boundary Solution architecture and project index, then the owning project's linked document
Select tests, build on Windows or diagnose verification failures NINA repository skill and its task-specific references
Prepare an upstream contribution, release note or documentation update Contribution guide
Fix prose or links The affected document and its incoming links; application builds are unnecessary

NINA.Docs is a separate documentation repository included as a submodule. It is outside NINA.sln; coordinate user-facing documentation there when applicable.

Working Boundaries

  • Carry authorized local work through implementation and appropriate verification without repeated confirmation. Upstream discussion requirements apply to contribution proposals and major changes; they are not a separate approval gate for an agreed local task.
  • Preserve existing architecture, public interfaces and serialized compatibility unless the task requires changing them. Plugin consumers and saved profiles/sequences can outlive the current build.
  • Keep reusable logic in its owning library, app-shell composition in NINA and plugin loading rules in NINA.Plugin. Use shared mediator interfaces for communication from libraries to UI handlers.
  • Treat versioned repository files as the durable source of project knowledge. Record newly discovered contracts in the nearest doc, test or analyzer when they will help future work.

Style

  • Follow .editorconfig for C#. Preserve touched files' line endings; use CRLF for new files unless the location dictates otherwise.
  • Keep C# declarations readable: separate constructors, properties, methods and type declarations with one blank line. Keep related fields together and separate field groups from other members. Match the surrounding same-line brace style.
  • Within methods, separate guard clauses and distinct logical steps with blank lines. Expand control-flow bodies and long expressions instead of compressing them onto one line; wrap long parameter and argument lists consistently. Review new and touched code for this spacing before handoff, even when an automatic formatter preserves compact code.
  • Follow surrounding XAML style; there is no repository-wide XAML formatter configuration.
  • Prefer modern C# supported by the project.
  • Use CommunityToolkit.Mvvm source generators for new or refactored MVVM code whenever they can express the required behavior. Use [ObservableProperty], [RelayCommand] and notification attributes instead of handwritten boilerplate; prefer annotated partial properties when supported to preserve accessor visibility. Use generated On<Property>Changing and On<Property>Changed partial hooks for necessary setter side effects. Preserve public contracts, notification behavior and threading requirements; retain handwritten members when the generators cannot preserve them.
  • Avoid new warnings. Report any intentional deferral with its reason.

Read the full file on GitHub · 64 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. 21d ago Changed · +1 lines · +82 tokens per session 4ebf9187cfc5
  2. 28d ago Changed · +2 lines · +101 tokens per session 4a0a6ae970e1
  3. 1mo ago Changed · -169 lines · -1,529 tokens per session 3e0189df0c14
  4. 2mo ago First seen · 230 lines · 2,701 tokens per session scan A 891ae7b3dda4

Subscribe to this mod's changes

nina AGENTS.md is an instructions file published in the GitHub repository isbeorn/nina (258 stars, last pushed yesterday), licensed MPL-2.0. It adds 1,355 tokens to every session, about $0.0054 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

nina AGENTS.md compared with instructions from other repositories

nina AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
nina AGENTS.mdisbeorn/ninaInstructions file258yesterdayMPL-2.0A1,355Codex, OpenCode
plan-forge api-patterns.instructions.mdsrnichols/plan-forgeInstructions file62d agoMITA2,049GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot