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 mathisk2095/jko-claude-plugins --skill dotnet-backend-expertgit clone --depth 1 https://github.com/mathisk2095/jko-claude-pluginsWrote 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/mathisk2095/jko-claude-plugins/dotnet-backend-expert)<a href="https://agentmods.dev/skills/mathisk2095/jko-claude-plugins/dotnet-backend-expert"><img src="https://agentmods.dev/badge/skills/mathisk2095/jko-claude-plugins/dotnet-backend-expert.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 5.1 | $0.00181 | $0.03336 |
| Opus 5 | $0.00090 | $0.01668 |
| Sonnet 5 | $0.00036 | $0.00667 |
| Haiku 4.5 | $0.00018 | $0.00334 |
Grade A, and why
dotnet-backend-expert 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 7d 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 — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build real .NET backends. Not UI shells. Not Razor pages. Not MAUI. Build Kestrel-hosted services that stay clear under load, survive team growth, and remain easy to reason about in code review, LLD interviews, and production incidents.
Terminology Rule
Frame this skill as .NET 10 backend work.
- Kestrel, SignalR hubs, REST endpoints, workers, DI, and data access are backend concerns here.
- Do not describe this plugin's target using the web-stack brand name.
- Official Microsoft docs may still use that brand in article titles. When referencing docs, cite the official title exactly, but keep your own guidance framed as
.NET backend/Kestrel backend.
Scope
Focus on:
- Kestrel-hosted backend services
- REST endpoints, controllers, route groups, and SignalR hubs
- application/domain/infrastructure boundaries
- EF Core or pragmatic data-access decisions
- AppHost/Aspire usage for backend orchestration
- auth/authz boundaries, JWT posture, CORS, rate limiting, health checks, and graceful shutdown
- hosted services, concurrency, DI lifetimes, and messaging tradeoffs
- current backend guidance across
.NET 8,.NET 9, and.NET 10, with.NET 10as the default recommendation for new services
Do not drift into:
- MAUI, Blazor, Razor UI, WinUI, WPF, or desktop/mobile UI guidance
- front-end rendering or UX review
- CI/CD advice unless it directly changes backend architecture or operational behavior
Design Stance
Pick an architecture before adding layers:
- Default to a modular monolith. Split into distributed services only when bounded contexts, team topology, deployment independence, or failure isolation actually require it.
- Keep the host thin.
Program.cs, route groups, controllers, hubs, and AppHost setup are composition surfaces, not homes for business logic. - Let application services orchestrate. Use cases, workflows, transactions, and coordination live here.
- Let the domain protect invariants. Entities and value objects should own rules that must remain true.
- Let infrastructure adapt. EF Core, Dapper, external APIs, message buses, and caches are details, not the center of the design.
- Prefer simplicity over ceremony. A boundary is only worth keeping if it prevents coupling, protects invariants, or improves testability and change safety.
- Treat vague coordination names as suspicious.
Coordinator,Orchestrator,Manager, andEngineoften hide kitchen-sink classes; make them prove they are focused.
What ships with it
17 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.
- references/ai-slop.md 2.0 KB
- references/anti-patterns.md 3.2 KB
- references/apphost-aspire.md 1.6 KB
- references/architecture.md 4.3 KB
- references/concurrency.md 1.9 KB
- references/data-access.md 2.1 KB
- references/dependency-injection.md 2.9 KB
- references/distributed-architecture.md 1.9 KB
- references/endpoints-rest.md 2.5 KB
- references/error-handling.md 1.8 KB
- references/kestrel-hosting.md 2.6 KB
- references/modern-dotnet.md 3.5 KB
- references/project-structure.md 2.6 KB
- references/security-and-operations.md 2.7 KB
- references/signalr.md 6.1 KB
- references/solid-principles.md 3.2 KB
- references/testing.md 1.6 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.
- 7d ago First seen · 332 lines · 181 tokens per session scan A e2cd86619076
dotnet-backend-expert is a skill published in the GitHub repository mathisk2095/jko-claude-plugins (3 stars, last pushed yesterday), licensed MIT. It adds 181 tokens to every session and 3,336 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
validate-api
Run the project's Hurl scenarios with an OIDC access token passed as a secret variable.
backend-architecture
This skill should be used for consequential backend architecture decisions: module or service boundaries; modular monoliths versus independent services; service extraction and data migration; data ownership and consistency; synchronous, event-driven, actor/stateful, or pipeline designs; failure isolation…
validate-ws
Run a bounded, protocol-aware WebSocket probe with an OIDC bearer token.
peekaboo
Provides runtime observation and interaction for native macOS interfaces through accessibility state and screenshots. Use when the task depends on visible or interactive state in a running SwiftUI/AppKit app: what is rendered, focused, selected, enabled, reachable through menus/windows/dialogs, or experienced across a…
mobile-flows-maestro
This skill should be used when Maestro is explicitly requested or already present and the task is to author, run, or debug iOS/Android Maestro flows; use Maestro MCP; or handle Maestro selectors, system UI, permissions, Keychain, JavaScript, waits, device state, flakiness, or CI. Evidence includes a .maestro directory…
validate-mobile
Run a Maestro flow on an explicitly selected iOS or Android device and report behavioral evidence.