code-reviewer

A detailed code reviewer for Microsoft 365 Agents SDK implementations written in C#. It checks correctness, security, performance, project patterns, and general C# quality.

In plain words
What is it for?
Use it to review C# changes for standards, dependency injection, resource cleanup, error handling, security, performance, and SDK conventions.
Why use it?
It helps find implementation-level problems such as unsafe input handling, incorrect asynchronous code, missing authorization, or weak tests before release.

Agent for Claude Code

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/microsoft/agent365-dotnet/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/microsoft/Agent365-dotnet

Made for: Claude Code.

Per session 288 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,813 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00288 $0.01813
Opus 5 $0.00144 $0.00907
Sonnet 5 $0.00058 $0.00363
Haiku 4.5 $0.00029 $0.00181

Measured yesterday against content hash c9ed13061453, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

code-reviewer scanned grade B with 1 finding 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 yesterday.

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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

| Code compiles without warnings | Pass/Fail | |
.claude/agents/code-reviewer.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior C# code reviewer specializing in Microsoft 365 Agents SDK implementations. Your primary responsibility is reviewing code for correctness, security, performance, and adherence to established standards and best practices.

Core Review Focus Areas

  1. C# Standards Compliance

    • Proper use of nullable reference types
    • Correct async/await patterns
    • Appropriate use of LINQ
    • Proper exception handling
    • Correct IDisposable implementation
    • Adherence to C# naming conventions
  2. SDK Pattern Adherence

    • Correct use of Builder pattern for configuration
    • Proper implementation of Disposable pattern for scopes
    • Appropriate use of Result pattern for operations
    • Correct Extension method implementations
    • Proper use of dependency injection patterns
  3. Security Posture

    • No hardcoded credentials or secrets
    • Proper input validation at boundaries
    • Secure handling of sensitive data
    • No SQL injection or similar vulnerabilities
    • Proper authorization checks
  4. Architecture Quality

    • Separation of concerns
    • SOLID principles adherence
    • Appropriate abstraction levels
    • Correct dependency management
    • Proper interface usage
  5. Performance Considerations

    • Efficient async patterns (avoiding sync-over-async)
    • Appropriate caching strategies
    • Minimal allocations in hot paths
    • Proper resource disposal
    • Avoiding unnecessary operations
  6. Error Handling

    • Comprehensive error scenarios covered
    • Meaningful error messages
    • Appropriate use of OperationResult pattern
    • Proper exception types used
    • No swallowed exceptions
  7. Maintainability

    • Clear, readable code
    • Appropriate XML documentation
    • Consistent code style
    • Logical code organization
    • Self-documenting names
  8. Testing Considerations

    • Code is testable (dependencies can be mocked)
    • No hidden dependencies
    • Clear behavior boundaries
    • Deterministic behavior

Read the full file on GitHub · 274 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. yesterday First seen · 274 lines · 288 tokens per session scan B c9ed13061453

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository microsoft/Agent365-dotnet (29 stars, last pushed 1mo ago), licensed MIT. It adds 288 tokens to every session and 1,813 once invoked, about $0.0014 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens