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.
curl -O https://raw.githubusercontent.com/isbeorn/nina/develop/.codex/skills/nina-repository/SKILL.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/skills/isbeorn/nina/nina-repository)<a href="https://agentmods.dev/skills/isbeorn/nina/nina-repository"><img src="https://agentmods.dev/badge/skills/isbeorn/nina/nina-repository/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.
<a href="https://agentmods.dev/skills/isbeorn/nina/nina-repository"><img src="https://agentmods.dev/badge/skills/isbeorn/nina/nina-repository.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00106 | $0.00796 |
| Opus 5 | $0.00053 | $0.00398 |
| Sonnet 5 | $0.00021 | $0.00159 |
| Haiku 4.5 | $0.00011 | $0.00080 |
Grade A, and why
nina-repository 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 11d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NINA Repository
Core Workflow
Use this skill as a routing layer, not a replacement for the repo docs.
- Find the repo root by locating
NINA.sln. - Read
AGENTS.mdbefore making repo changes. - Read
CONTRIBUTING.mdwhen the task touches contribution workflow, release notes, localization, docs, tests, installers, or PR expectations. - Read the owning project's
ARCHITECTURE.mdbefore non-trivial edits in that project. - Use
references/project-map.mdto choose the likely owner and neighboring files. - Use
references/testing-map.mdto choose concrete test filters and command templates. - If a task reveals missing reusable guidance, update the closest repository doc, route map, test, or tooling before finishing.
Edit Rules
- Keep changes in the owning layer and follow existing local patterns first.
- Use
references/project-map.mdfor recurring checks such as DI, localization, runtime files, plugin/sequencer metadata, persistence, and documentation/release-note implications. - Follow
.editorconfigand surrounding style; preferCommunityToolkit.Mvvmfor new or refactored MVVM code where it fits. - Add or update focused tests for testable behavior changes, and update
references/testing-map.mdonly when a new route, command, or constraint will help future agents. - Keep file-writing tests isolated from shared user state unless the shared location is the behavior under test.
- Prefer making durable rules enforceable with tests, analyzers, scripts, or CI when the boundary matters repeatedly.
Verification
Prefer targeted tests while iterating and broaden only when the changed surface justifies it. Use references/testing-map.md for concrete filters and command templates.
For .NET build and test commands in this sandbox, start with the stable invocation shape instead of rediscovering environment failures:
- Set
DOTNET_CLI_HOMEto the repo-local.dotnet-clidirectory and setDOTNET_SKIP_FIRST_TIME_EXPERIENCE=1,DOTNET_ADD_GLOBAL_TOOLS_TO_PATH=0, andDOTNET_CLI_TELEMETRY_OPTOUT=1in the same PowerShell command. - Use
--no-restoreunless restore is the explicit task or a missing-assets error proves it is needed. - Add
-m:1 -p:UseSharedCompilation=false -p:GeneratePackageOnBuild=falseto targeteddotnet buildanddotnet testcommands to avoid MSBuild/compiler-server sandbox failures. - For
NINA/NINA.csprojapp builds, also add-p:RunPostBuildEvent=Neverunless the post-build output is part of the task. - If a previous .NET command fails with no compiler errors, first rerun it with these flags before inspecting long diagnostic logs.
- If a build or test run fails only because the sandbox denied writes under
obj,bin,TestResults, or user-profile test paths, rerun the same command with appropriate filesystem access before treating it as a product regression.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 48 lines · 106 tokens per session scan A b830d184023f
nina-repository is a skill published in the GitHub repository isbeorn/nina (232 stars, last pushed yesterday), licensed MPL-2.0. It adds 106 tokens to every session and 796 once invoked, about $0.0005 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 skills, from other repositories
mapsui
Use when embedding interactive 2D maps in .NET desktop (WinForms/WPF) or mobile (MAUI) applications — tile layers, vector features, map controls. Mapsui: cross-platform .NET map component library.
make-wpf-custom-control
Generates WPF CustomControl C# class and XAML ControlTemplate style from a control name. Use when creating a new custom control, scaffolding a templated control, or generating CustomControl boilerplate code. Usage: /wpf-dev-pack:make-wpf-custom-control.
make-wpf-project
Scaffolds a complete WPF project structure with MVVM, DI, and best practices. Use when starting a new WPF application, creating a WPF solution from scratch, or setting up project structure with CommunityToolkit.Mvvm or Prism. Usage: /wpf-dev-pack:make-wpf-project [--minimal|--full|--prism].
make-wpf-converter
Generates WPF IValueConverter or IMultiValueConverter classes with MarkupExtension pattern. Use when creating a new value converter, scaffolding a MultiValueConverter, or adding a converter with direct XAML usage. Usage: /wpf-dev-pack:make-wpf-converter [multi].
wpf-rule-view-viewmodel-wiring-communitytoolkit
View-ViewModel wiring for CommunityToolkit.Mvvm: Mappings.xaml + implicit DataTemplate (ViewModel First).
wpf-rule-prohibitions
Banned wpf-dev-pack patterns (P-001..P-004): ViewModelLocator, code-behind DataContext, Stateless ViewModel, mixing composition paths.