csharp-quality

csharp-quality is an agent for Claude Code from bdfinst/agentic-dev-team. It costs 27 tokens per session (456 once invoked), scanned A, original, MIT.

A C# code-review agent that checks changed C# files for null-safety problems, unsafe asynchronous code, and older patterns that can be replaced with modern C# features. It reports issues as structured JSON with locations and suggested fixes.

In plain words
What is it for?
Use it to review changes in projects using C# project or solution files, including checks for nullable reference types, async/await usage, and record types.
Why use it?
It helps catch crashes, deadlocks, and type-safety problems during review instead of after the code is deployed.

Agent for Claude Code

Written for Claude Code: effort in frontmatter.

Part of the dev-team plugin — 96 skills, 54 agents, 4 hooks shipped together

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.

agentmods
npx agentmods add agents/bdfinst/agentic-dev-team/csharp-quality
Clone the repo
git clone --depth 1 https://github.com/bdfinst/agentic-dev-team

Made for: Claude Code.

Or install dev-team, the plugin that ships this one along with the rest of its 96 skills, 54 agents, 4 hooks.

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 csharp-quality

README.md
[![agentmods](https://agentmods.dev/badge/agents/bdfinst/agentic-dev-team/csharp-quality.svg)](https://agentmods.dev/agents/bdfinst/agentic-dev-team/csharp-quality)
Your own site
<a href="https://agentmods.dev/agents/bdfinst/agentic-dev-team/csharp-quality"><img src="https://agentmods.dev/badge/agents/bdfinst/agentic-dev-team/csharp-quality.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 456 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00027 $0.00456
Opus 5 $0.00014 $0.00228
Sonnet 5 $0.00005 $0.00091
Haiku 4.5 $0.00003 $0.00046

Measured today against content hash 25e2678db708, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

csharp-quality 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 today.

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/dev-team/templates/agents/csharp-quality.md · 64 lines

What it actually says

C# Quality

Output JSON:

{"status": "pass|warn|fail|skip", "issues": [{"severity": "error|warning|suggestion", "confidence": "high|medium|none", "file": "", "line": 0, "message": "", "suggestedFix": ""}], "summary": ""}

Status: pass=modern C#, warn=improvements needed, fail=unsafe patterns Severity: error=null safety issue or async misuse, warning=non-modern pattern, suggestion=style Confidence: high=mechanical (enable nullable, use record); medium=design choice; none=domain context

Context needs: diff-only File scope: *.cs

Activates when

.csproj or .sln exists.

Skip

Return skip when no .cs files in the changeset.

Detect

Nullable reference types:

  • <Nullable>enable</Nullable> missing in .csproj
  • Null-forgiving operator (!) used without safety check
  • Missing null checks at public API boundaries
  • dynamic type usage (loses type safety)

Async/await:

  • async void methods (except event handlers)
  • .Result or .Wait() on tasks (deadlock risk)
  • Missing ConfigureAwait(false) in library code
  • Fire-and-forget tasks without error handling

Modern C#:

  • Classes used for DTOs where record types would be immutable and concise
  • Manual Equals/GetHashCode where record handles it
  • string.Format instead of string interpolation
  • switch statements that could use pattern matching

Dependency injection:

  • new-ing services instead of injecting via constructor
  • Service locator anti-pattern (IServiceProvider.GetService in business logic)
  • Missing interface for testability
  • Transient services holding state

Ignore

Test projects, generated code, migration files, Razor views.

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. today First seen · 64 lines · 27 tokens per session scan A 25e2678db708

Subscribe to this mod's changes

csharp-quality is an agent published in the GitHub repository bdfinst/agentic-dev-team (280 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 456 once invoked, about $0.0001 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 2026-09-05.