dotnet-csharp-concurrency-specialist

dotnet-csharp-concurrency-specialist is an agent for Claude Code from novotnyllc/dotnet-artisan. It costs 58 tokens per session (1,849 once invoked), scanned A, original, MIT.

A read-only .NET specialist for finding problems caused by code that runs at the same time, such as race conditions, deadlocks, and unsafe shared access.

In plain words
What is it for?
Use it to inspect async code, locks, parallel work, thread safety, synchronization, and concurrent access problems in .NET applications.
Why use it?
It helps explain bugs that appear only under particular timing or load, which can be difficult to reproduce and diagnose by reading code normally.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the dotnet-artisan plugin — 9 skills, 14 agents, 2 MCP servers shipped together

Good fit Use it to inspect async code, locks, parallel work, thread safety, synchronization, and concurrent access problems in .NET applications.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/novotnyllc/dotnet-artisan/dotnet-csharp-concurrency-specialist
Install

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.

Clone the repo
git clone --depth 1 https://github.com/novotnyllc/dotnet-artisan

Made for: Claude Code.

Or install dotnet-artisan, the plugin that ships this one along with the rest of its 9 skills, 14 agents, 2 MCP servers.

Wrote 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.

agentmods badge for dotnet-csharp-concurrency-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/novotnyllc/dotnet-artisan/dotnet-csharp-concurrency-specialist/github.svg)](https://agentmods.dev/agents/novotnyllc/dotnet-artisan/dotnet-csharp-concurrency-specialist)
Your own site
<a href="https://agentmods.dev/agents/novotnyllc/dotnet-artisan/dotnet-csharp-concurrency-specialist"><img src="https://agentmods.dev/badge/agents/novotnyllc/dotnet-artisan/dotnet-csharp-concurrency-specialist/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.

agentmods 80×15 button for dotnet-csharp-concurrency-specialist

Your own site · 80×15
<a href="https://agentmods.dev/agents/novotnyllc/dotnet-artisan/dotnet-csharp-concurrency-specialist"><img src="https://agentmods.dev/badge/agents/novotnyllc/dotnet-artisan/dotnet-csharp-concurrency-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,849 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.01849
Opus 5 $0.00029 $0.00924
Sonnet 5 $0.00012 $0.00370
Haiku 4.5 $0.00006 $0.00185

Measured 10d ago against content hash b09642771ba2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dotnet-csharp-concurrency-specialist 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 10d 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.

plugins/dotnet-artisan/agents/dotnet-csharp-concurrency-specialist.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dotnet-csharp-concurrency-specialist

Concurrency analysis subagent for .NET projects. Performs read-only analysis of threading, synchronization, and concurrent access patterns to identify bugs, race conditions, and deadlocks. Grounded in guidance from Stephen Cleary's concurrency expertise and Joseph Albahari's threading reference.

Knowledge Sources

This agent's guidance is grounded in publicly available content from:

  • Stephen Cleary's "Concurrency in C#" (O'Reilly) -- Definitive guide to async/await synchronization, SynchronizationContext behavior, async-compatible synchronization primitives, and correct cancellation patterns. Key insight: prefer SemaphoreSlim over lock for async code; "There is no thread" for understanding async I/O. Source: https://blog.stephencleary.com/
  • Joseph Albahari's "Threading in C#" -- Comprehensive reference for .NET threading primitives, lock-free programming, memory barriers, and the threading model. Source: https://www.albahari.com/threading/
  • David Fowler's Async Guidance -- Practical async anti-patterns and diagnostic scenarios for ASP.NET Core applications. Source: https://github.com/davidfowl/AspNetCoreDiagnosticScenarios/blob/master/AsyncGuidance.md

Disclaimer: This agent applies publicly documented guidance. It does not represent or speak for the named knowledge sources.

Preloaded Skills

Always load these skills before analysis:

  • [skill:dotnet-csharp] (read references/async-patterns.md) -- async/await correctness, Task patterns, cancellation, ConfigureAwait
  • [skill:dotnet-csharp] (read references/concurrency-patterns.md) -- concurrency primitives: lock, SemaphoreSlim, Interlocked, ConcurrentDictionary, decision framework
  • [skill:dotnet-csharp] (read references/modern-patterns.md) -- language features used in concurrent code (pattern matching, records for immutable state)

Decision Tree

Is the bug a race condition?
  → Check shared mutable state
  → Look for missing locks, incorrect ConcurrentDictionary usage
  → Check for read-modify-write without atomicity

Is the bug a deadlock?
  → Check for blocking calls on async (.Result, .Wait(), .GetAwaiter().GetResult())
  → Check for nested lock acquisition in different orders
  → Check for SynchronizationContext capture in library code

Is it thread pool starvation?
  → Check for sync-over-async patterns
  → Check for long-running synchronous work on thread pool threads
  → Look for missing Task.Run for CPU-bound work in async pipelines

Is it a data corruption issue?
  → Check collection access from multiple threads without synchronization
  → Look for non-atomic compound operations on shared state
  → Verify ConcurrentDictionary GetOrAdd/AddOrUpdate delegate side effects

Read the full file on GitHub · 206 lines

Changes

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.

  1. 10d ago First seen · 206 lines · 58 tokens per session scan A b09642771ba2

Subscribe to this mod's changes

dotnet-csharp-concurrency-specialist is an agent published in the GitHub repository novotnyllc/dotnet-artisan (229 stars, last pushed 22d ago), licensed MIT. It adds 58 tokens to every session and 1,849 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

C#/.NET Janitor

Perform janitorial tasks on C#/.NET code including cleanup, modernization, and tech debt remediation.

github/awesome-copilot · 27 tokens

msbuild

Expert agent for MSBuild and .NET build troubleshooting, optimization, and project file quality. Routes to specialized agents for performance analysis and code review. Verifies MSBuild domain relevance before deep-diving. Specializes in build configuration, error diagnosis, binary log analysis, and resolving common…

dotnet/skills · 62 tokens

build-error-resolver

Autonomous .NET build fixer — parses dotnet build errors, categorizes them, applies known fix patterns, and rebuilds iteratively until green. Use when the build is broken, after a large refactor or dependency update, or whenever compiler errors need systematic resolution without hand-holding.

codewithmukesh/dotnet-claude-kit · 63 tokens

dotnet-concurrency-specialist

Expert in .NET concurrency, threading, and race condition analysis. Specializes in Task/async patterns, thread safety, synchronization primitives, and identifying timing-dependent bugs in multithreaded .NET applications. Use for analyzing racy unit tests, deadlocks, and concurrent code issues.

Aaronontheweb/dotnet-skills · 64 tokens

dnp-di-wiring-checker

🔌 Verifies DI container completeness — scans constructor injections and cross-references against service registrations.

zdanovichnick/dotnet-pilot · 27 tokens

dotnet-concurrency-specialist

Expert in .NET concurrency, threading, and race condition analysis. Specializes in Task/async patterns, thread safety, synchronization primitives, and identifying timing-dependent bugs in multithreaded .NET applications. Use for analyzing racy unit tests, deadlocks, and concurrent code issues.

F-U-S-E-E/FuseDevelopmentGroup · 64 tokens