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 vasilyu1983/AI-Agents-public --skill software-csharp-backendgit clone --depth 1 https://github.com/vasilyu1983/AI-Agents-publicWrote 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/vasilyu1983/ai-agents-public/software-csharp-backend)<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/software-csharp-backend"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/software-csharp-backend/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/vasilyu1983/ai-agents-public/software-csharp-backend"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/software-csharp-backend.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 | $0.00045 | $0.03006 |
| Opus 5.5 | $0.00018 | $0.01202 |
| Sonnet 5.5 | $0.00009 | $0.00601 |
| Haiku 4.5 | $0.00005 | $0.00301 |
Grade A, and why
software-csharp-backend 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 25d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
C# Backend Engineering
Quick Reference
| Decision | Default | Notes |
|---|---|---|
| Runtime | Current .NET LTS and its C# version | Look up the current LTS and its end date on the dotnet support policy page before naming a version. Treat any target within a year of end of support as a tracked migration, not a steady state. Choose the current LTS by default; choose a newer STS only if the team upgrades every year |
| API style | Minimal API for new endpoints | Controllers for large CQRS surface with many filters/action results |
| Persistence (SQL, write-heavy) | EF Core | Use Dapper when query shapes are complex and hand-tuned SQL wins |
| Persistence (SQL, query-heavy) | Dapper | Pair with EF Core for write path if aggregates exist |
| Persistence (document) | MongoDB driver | Use when schema variability is genuine, not habitual |
| Background worker | IHostedService / BackgroundService |
Add lease, graceful shutdown, and poison-message handling from day one |
| Resilience | Microsoft.Extensions.Resilience (Polly v8) |
AddStandardResilienceHandler() runs five strategies, outermost first: rate limiter → total timeout → retry → circuit breaker → attempt timeout. It retries all HTTP methods by default. Override the defaults for unsafe methods and for tight deadlines. Retry at one layer only: a handler added to a client that ConfigureHttpClientDefaults (for example, service defaults) already wraps, or an app-level retry around a retrying client or EF execution strategy, multiplies attempts. See references/resilience-policy-defaults.md |
| OpenAPI | Built-in ASP.NET Core OpenAPI (Microsoft.AspNetCore.OpenApi) |
Do not add Swashbuckle unless repo already uses it |
Route other tasks:
- NUnit fixture design, WireMock/Testcontainers setup, or flake reduction →
$qa-testing-nunit nuke/Build.cs, CI target sequencing, or artifact publication →$ops-nuke-cicd- Legacy
ILoggeror Serilog rewrite automation →$dev-structured-logs
What ships with it
29 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.
- agents/openai.yaml 295 B
- assets/api-host-template.cs 2.7 KB
- assets/dapper-query-handler-template.cs 1.9 KB
- assets/mongo-repository-template.cs 2.3 KB
- assets/options-configuration-template.cs 1.8 KB
- assets/pull-request-checklist-template.md 1.9 KB
- assets/resilient-http-client-template.cs 3.8 KB
- assets/service-class-template.cs 2.1 KB
- assets/test-data-builder-template.cs 758 B
- assets/test-fixture-template-nunit.cs 2.4 KB
- Data/sources.json 8.4 KB
- learnings.consolidated.md 599 B
- learnings.md 389 B
- references/aspnet-core-api-patterns.md 4.5 KB
- references/backend-architecture-principles.md 1.5 KB
- references/code-review-checklist.md 2.3 KB
- references/csharp-language-practices.md 2.9 KB
- references/data-access-patterns.md 3.0 KB
- references/dotnet-coding-standards.md 4.2 KB
- references/efcore-persistence-patterns.md 4.9 KB
- references/modular-architecture-principles.md 1.9 KB
- references/observability-standards.md 1.8 KB
- references/reliability-and-resilience.md 4.6 KB
- references/resilience-policy-defaults.md 3.3 KB
- references/runtime-ops-checklist.md 2.2 KB
- references/scenario-guides.md 2.0 KB
- references/security-baseline.md 1.6 KB
- references/testing-practices.md 2.3 KB
- references/version-compatibility-notes.md 7.4 KB
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.
- 25d ago Changed · -54 lines · +11 tokens per session c45439118f2b
- 1mo ago Changed 9a816dc2624b
- 1mo ago First seen · 215 lines · 34 tokens per session scan A fdefea813e3d
software-csharp-backend is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (101 stars, last pushed 14d ago), licensed MIT. It adds 45 tokens to every session and 3,006 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
fastapi-templates
Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.
csharp-patterns
C#/.NET: LINQ, async/await, DI, records, nullable refs, ASP.NET Core, EF Core, MediatR. Triggers: C#, .NET, dotnet, ASP.NET, EF Core, LINQ, record type, IServiceCollection.
dotnet-backend
Build and upgrade ASP.NET Core services with typed contracts, dependency lifetimes and verified persistence. Use when implementing .NET APIs, background services or runtime migrations; coordinate SDK, target framework and package support.
aspnet-core
Guidelines for ASP.NET Core web development covering API design, authentication, caching, and best practices.
dotnet
Guidelines for .NET backend development with C#, ASP.NET Core, and Entity Framework Core.
dotnet-aspnetcore-service
Use when building or extending a C# service on ASP.NET Core - Minimal APIs or controllers, DI and options, EF Core with Npgsql, ProblemDetails, HttpClientFactory resilience, async and cancellation.