gitlab-mcp: Agent for Claude Code

.github/agents/csharp-reviewer.agent.md

csharp-reviewer is an agent for Claude Code from zereight/gitlab-mcp. It costs 51 tokens per session (1,904 once invoked), scanned A, original, MIT.

A read-only reviewer for C# code, the programming language commonly used with .NET. It checks C# type safety, asynchronous code, null handling, and common resource-management patterns.

In plain words
What is it for?
Use it to review C# methods and APIs, nullable annotations, async/await usage, LINQ, dependency injection, and disposal of resources.
Why use it?
It helps prevent null-reference errors, async deadlocks, leaked files or connections, and code that does not follow modern C# practices.

Agent for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: model in frontmatter.

This is zereight/gitlab-mcp's own configuration. It tells Claude Code how to work on gitlab-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gitlab-mcp configures →

About the project

gitlab-mcp is a service that lets AI agents interact with GitLab through the Model Context Protocol, an interface for exposing tools to agent clients. It supports work with projects, merge requests, issues, pipelines, wikis, releases, tags, and other GitLab resources through local or remote connections. The catalogue includes agents, skills, instructions, and an MCP entry for its workflows.

zereight/gitlab-mcp · 2,047 stars · on GitHub · zereight.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to zereight/gitlab-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zereight/gitlab-mcp/main/.github/agents/csharp-reviewer.agent.md
Clone the repo
git clone --depth 1 https://github.com/zereight/gitlab-mcp

Made for: Claude Code.

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/zereight/gitlab-mcp/csharp-reviewer/github.svg)](https://agentmods.dev/agents/zereight/gitlab-mcp/csharp-reviewer)
Your own site
<a href="https://agentmods.dev/agents/zereight/gitlab-mcp/csharp-reviewer"><img src="https://agentmods.dev/badge/agents/zereight/gitlab-mcp/csharp-reviewer/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 csharp-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/zereight/gitlab-mcp/csharp-reviewer"><img src="https://agentmods.dev/badge/agents/zereight/gitlab-mcp/csharp-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,904 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 $0.00051 $0.01904
Opus 5.5 $0.00020 $0.00762
Sonnet 5.5 $0.00010 $0.00381
Haiku 4.5 $0.00005 $0.00190

Measured 1mo ago against content hash ac2acf51b02e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

csharp-reviewer 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.github/agents/csharp-reviewer.agent.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

C# Reviewer

Role

You are C# Reviewer. Your mission is to enforce type safety, async correctness, nullable reference type hygiene, and idiomatic modern C# in .NET codebases.

Responsible for: nullable annotations, async/await correctness, LINQ patterns, IDisposable lifecycle, record/expression-body adoption, dependency injection patterns, and anti-pattern detection.

Not responsible for: implementing fixes, architecture design, writing tests, or runtime profiling.

Why This Matters

C# async/await mistakes (.Result, .Wait()) cause deadlocks in ASP.NET Core under load. Unannotated nullable reference types hide null-reference exceptions. Missing using statements leak file handles and database connections. Modern C# provides the tools to avoid all of these — they must be used.

Embedded Rules

Nullable Reference Types

  • CRITICAL: #nullable enable must be present in every file (or enabled project-wide in .csproj). Unannotated public APIs are incomplete.
  • CRITICAL: Do not use ! (null-forgiving operator) without a comment proving that null is impossible at that specific callsite.
  • HIGH: All public method parameters and return types must be annotated: string? for nullable, string for non-nullable.
  • HIGH: Do not assign null to a non-nullable reference type variable.
  • MEDIUM: Use ?? (null-coalescing) and ?. (null-conditional) to handle nullable values inline instead of explicit null checks where clarity is preserved.
  • LOW: Prefer is null / is not null over == null / != null for null checks (avoids operator overloading surprises).

Records and Immutable Data

  • HIGH: Use record for immutable data carriers instead of classes with manual Equals, GetHashCode, ToString, and with semantics.
    // BAD
    public class Point { public int X { get; init; } public int Y { get; init; } /*...*/ }
    // GOOD
    public record Point(int X, int Y);
    
  • MEDIUM: Use record struct for small value-type data carriers to avoid heap allocation.
  • MEDIUM: Use init-only setters for properties on classes that must be classes (not records) but should still be immutable after construction.

Read the full file on GitHub · 159 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. 1mo ago First seen · 159 lines · 51 tokens per session scan A ac2acf51b02e

Subscribe to this mod's changes

csharp-reviewer is an agent published in the GitHub repository zereight/gitlab-mcp (2,047 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 1,904 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 2026-08-30.

Related

Other agents, from other repositories

team-reviewer

Multi-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use when performing parallel code reviews across multiple quality dimensions.

wshobson/agents · 43 tokens

code-documentation-code-reviewer

Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanning, and configuration review with 2024/2025 best practices. Use PROACTIVELY for code quality assurance.

wshobson/agents · 60 tokens

code-reviewer-bug

name: code-reviewer-bug description: Specialized code reviewer for bug patterns — null safety, race conditions, resource leaks, logic and error-handling defects. Returns scored findings (severity × impact × confidence). skills: code-review model: inherit.

zxpmail/ReqForge · 0 tokens

sdd-tester

Runs the project's verification suite (type-check, lint, tests) and reports pass/fail with concrete failures. Use AFTER the implementer finishes a task and BEFORE the verifier. Read-only on source. Stack-agnostic — reads the commands from .memory/30-tech.md.

chohra-med/expo_boilerplate · 61 tokens

cr-correctness

Reviews a supplied diff for introduced behavioral and contract defects. Use only when dispatched by the code-review skill.

srtab/daiv · 26 tokens

code-reviewer

Expert code review specialist — quality/correctness/security/performance/testing with severity-ranked findings. Use when reviewer/qa-engineer delegates deep craft or PR explicitly warrants independent verification; opt-in via holistic caller.

ulises-jeremias/agent-toolkit · 45 tokens