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 skills add tmj-90/gaffer --skill csharp-conventionsgit clone --depth 1 https://github.com/tmj-90/gafferWrote 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/tmj-90/gaffer/csharp-conventions)<a href="https://agentmods.dev/skills/tmj-90/gaffer/csharp-conventions"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/csharp-conventions/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/tmj-90/gaffer/csharp-conventions"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/csharp-conventions.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00126 | $0.02152 |
| Opus 5.5 | $0.00050 | $0.00861 |
| Sonnet 5.5 | $0.00025 | $0.00430 |
| Haiku 4.5 | $0.00013 | $0.00215 |
Grade A, and why
csharp-conventions 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 16d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write idiomatic modern C#
Modern C# puts nullability in the type system, values in records, and asynchrony in a first-class model with cancellation. Code that suppresses warnings, blocks on tasks, or news up its dependencies gives that back. For the builder and the reviewer of a .NET diff; the solution's config and existing code win over it.
Procedure
- Discover the solution's conventions first. Call
search_lorefor .NET conventions. Readglobal.json(SDK pin),Directory.Build.propsandDirectory.Packages.props(central package versions; a new or bumped package is a blocker, see thedependency-upgradeskill), the.csproj(TargetFramework,LangVersion,Nullable,TreatWarningsAsErrors,AnalysisLevel/AnalysisMode,ImplicitUsings),.editorconfig(naming and diagnostic severities),.config/dotnet-tools.json, and the CI workflow. Identify the test framework (xUnit v2/v3, NUnit, MSTest), assertion and mocking libraries, the error policy (exceptions vs aResulttype) and minimal APIs vs controllers. Copy a sibling class and its test. - Pin the exact commands from CI (the
run-testsandrun-lintskills). Use the defaults below only when the repo defines none. - Write the change with the idioms below, then walk the concurrency section for every
task, disposable, shared field,
DbContextand outbound call you touched. - Test each acceptance criterion's own behaviour. One test (or
[Theory]row) per AC that fails without your change, plus its error path;WebApplicationFactoryfor API behaviour. If the AC involves shared state or persistence, add a test that runs N concurrent calls (Task.WhenAlloverEnumerable.Range) and asserts the invariant. UseTimeProvider/FakeTimeProviderinstead of real delays. - Verify, then stop. Done when: the build has no new warnings at the configured
level,
dotnet format --verify-no-changes --no-restoreis clean, tests are green, and every AC has a test. Record the output with therecord-evidenceskill; the runner submits the work.
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.
- 16d ago Changed · +53 lines · +22 tokens per session 6794f1c4fa05
- 19d ago First seen · 76 lines · 104 tokens per session scan A 85b0c499e359
csharp-conventions is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 17d ago), licensed Apache-2.0. It adds 126 tokens to every session and 2,152 once invoked, about $0.0005 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 2026-09-28.
Other skills, from other repositories
sota-dotnet
State-of-the-art C# / .NET engineering rules (.NET LTS releases, modern C#) that Claude applies when writing or auditing .NET code. Covers modern idioms (records, nullable reference types, pattern matching, spans, file-scoped namespaces), API/null/immutability/IDisposable design, async/await & concurrency…
aspnet-core
Guidelines for ASP.NET Core web development covering API design, authentication, caching, and best practices.
blazor
Guidelines for Blazor development including component lifecycle, state management, and performance optimization.
dotnet
Guidelines for .NET backend development with C#, ASP.NET Core, and Entity Framework Core.
unity-project-architecture
Use when writing or restructuring Unity C# code - assembly definitions and dependency direction, small components with cached references, ScriptableObjects for data and events, DI instead of singletons, Input System, Addressables, serialization safety and Unity 6 API changes.
godot-csharp-and-gdextension
Use when a Godot project uses or considers C# (.NET) or native code - when C# is the right call and its export limits (no web export), C# node patterns with generated SignalName/StringName caching, plain C# rule libraries tested with dotnet test, and GDExtension (godot-cpp, godot-rust) pinning and build hygiene.