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 Benknightdark/neo-skills --skill neo-csharpgit clone --depth 1 https://github.com/Benknightdark/neo-skillsWrote 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/benknightdark/neo-skills/neo-csharp)<a href="https://agentmods.dev/skills/benknightdark/neo-skills/neo-csharp"><img src="https://agentmods.dev/badge/skills/benknightdark/neo-skills/neo-csharp/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/benknightdark/neo-skills/neo-csharp"><img src="https://agentmods.dev/badge/skills/benknightdark/neo-skills/neo-csharp.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 | $0.00065 | $0.01329 |
| Opus 5.5 | $0.00026 | $0.00532 |
| Sonnet 5.5 | $0.00013 | $0.00266 |
| Haiku 4.5 | $0.00006 | $0.00133 |
Grade A, and why
neo-csharp 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 1mo 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Modern C# (10+) Expert Skill
Trigger On
- The user asks to write, debug, refactor, or review C# code.
- The project directory contains
*.cs,*.csproj, or single-file C# scripts. - The target framework is .NET 6.0 (LTS) and above.
- Code modernization is needed (e.g., converting legacy nested namespaces to File-scoped namespaces).
Workflow
- Perceive (Version Awareness):
- Check
.csprojto identifyTargetFrameworkand determine the syntax upper limit:net6.0: C# 10 (File-scoped namespaces, Global usings).net7.0: C# 11 (Raw string literals, Required members).net8.0: C# 12 (Primary Constructors, Collection Expressions).net9.0: C# 13 (paramscollections,Lockobject).net10.0: C# 14 (Extension members,fieldkeyword).
- Check
- Reason (Planning Phase):
- Evaluate the modernization level of the current code to determine the refactoring strategy.
- In lower version environments (like .NET 6), avoid using higher version syntax (like Primary Constructors), but prioritize using File-scoped namespaces.
- In higher version environments, actively adopt new features to reduce boilerplate code.
- Act (Execution Phase):
- Write high-quality code, prioritizing "syntactic sugar" to improve readability.
- Implement strong typing and immutable data structures (
record,record struct). - Utilize Interpolated string handlers and Span to optimize performance-sensitive paths.
- Validate (Standard Validation):
- Validate the safety of NRT (Nullable Reference Types).
- Check if asynchronous operations correctly handle cancellation tokens (
CancellationToken). - Ensure naming conventions comply with official .NET recommendations.
Feature Roadmap (C# 10 - 14)
C# 10 & 11 (Foundation)
- File-scoped Namespaces: Reduce indentation levels.
- Global Using Directives: Centralize common namespaces management.
- Raw String Literals:
"""..."""easily handle multi-line and special characters. - Required Members: Ensure required properties during object initialization.
- List Patterns:
if (list is [1, 2, ..])powerful collection matching.
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.
- 1mo ago First seen · 93 lines · 65 tokens per session scan A f093c0fed7e5
neo-csharp is a skill published in the GitHub repository Benknightdark/neo-skills (7 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 1,329 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
csharp-dotnet
Use when building on .NET 8+ with C# 12. Covers nullable reference types, records, async/await correctness, minimal APIs, dependency injection, and EF Core query performance. Trigger on "async deadlock in my asp.net app", "turn on nullable reference types", "ef core is doing n+1 queries", "set up a minimal api in .net…
create-pubsub-dotnet
Creates a Dapr pub/sub app in .NET (publisher, subscriber or both) with declarative, programmatic or streaming subscriptions, run with dapr run or Aspire. Use for "create a pub/sub app in .NET" or "build a Dapr publisher and subscriber in C#". For an existing project use add-pubsub-dotnet.
create-agent-dotnet
Creates a durable AI agent app in .NET with Microsoft Agent Framework on Dapr Workflow, run locally with dapr run. Use for "create an agent in .NET" or "scaffold a .NET agent". For Diagrid Catalyst use the catalyst-ai plugin.
create-workflow-dotnet
Creates a Dapr workflow app in .NET, run locally with dapr run. Use for "create a workflow in .NET" or "build a workflow app in C#". For Diagrid Catalyst use the catalyst-ai plugin.
add-workflow-dotnet
Adds Dapr Workflow to an existing .NET (ASP.NET Core, plain or Aspire) project. Shows a plan for approval, then adds the workflow, activities and management endpoints with targeted edits, building after each. Use for "add a workflow to my .NET project" or "make this process a durable workflow". For a new project use…
check-prereq-agent-dotnet
Checks prerequisites for building durable AI agents in .NET with Microsoft Agent Framework on Dapr Workflow. Use for "check prerequisites for .NET agents" or "verify .NET agent environment".