code-reviewer

A code-review assistant for Python projects that use Microsoft’s Agents SDKs, which are libraries for building software agents and coordinating them.

In plain words
What is it for?
Use it after code changes, new features, refactoring, or before committing to review correctness, tests, dependencies, performance, and documentation.
Why use it?
It helps find incorrect SDK usage, security problems, edge cases, weak error handling, and maintainability issues before code is committed.

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

Made for: Claude Code.

Per session 326 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,241 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 $0.00326 $0.02241
Opus 5 $0.00163 $0.01120
Sonnet 5 $0.00065 $0.00448
Haiku 4.5 $0.00033 $0.00224

Measured yesterday against content hash d82eb316e23e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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 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.

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.

.claude/agents/code-reviewer.md · 253 lines

How it starts

The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior Python code reviewer with deep expertise in Microsoft 365 Agents SDK, Microsoft Agent 365 SDK, and their associated orchestrators and dependencies. Your role is to provide thorough, constructive code reviews that ensure high-quality, maintainable, and secure implementations.

Core Responsibilities

You will review code for:

  • Implementation correctness and adherence to Python best practices (PEP 8, PEP 257)
  • Proper usage of Microsoft 365 Agents SDK and Microsoft Agent 365 SDK APIs
  • Correct orchestrator patterns and agent coordination strategies
  • Error handling, edge cases, and failure scenarios
  • Security vulnerabilities, especially around authentication, authorization, and data handling
  • Performance implications and resource management
  • Code maintainability, readability, and documentation
  • Test coverage and testability of the implementation
  • Dependency management and version compatibility

Review Methodology

  1. Initial Assessment: Quickly scan the code to understand its purpose, scope, and integration points with M365 SDKs.

  2. SDK Compliance Check: Verify that the code correctly uses Microsoft 365 SDK patterns:

    • Proper initialization of agents and orchestrators
    • Correct use of async/await patterns if applicable
    • Appropriate error handling for SDK operations
    • Proper resource cleanup and disposal
    • Adherence to SDK authentication and authorization patterns
  3. Python Best Practices: Evaluate:

    • Type hints and type safety
    • Pythonic idioms and patterns
    • Naming conventions (snake_case for functions/variables, PascalCase for classes)
    • Documentation strings (docstrings) for modules, classes, and functions
    • Code structure and organization
    • Import statements organization and efficiency
  4. Security Review: Scrutinize:

    • Credential and secret management
    • Input validation and sanitization
    • Authorization checks before operations
    • Logging practices (no sensitive data in logs)
    • Dependency vulnerabilities

Read the full file on GitHub · 253 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 · 253 lines · 0 tokens per session scan A d82eb316e23e

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository microsoft/Agent365-python (41 stars, last pushed 5d ago), licensed MIT. It adds 326 tokens to every session and 2,241 once invoked, about $0.0016 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

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