pr-code-reviewer

A reviewer for pull requests, which are proposed code changes submitted for review before they are merged. It examines the actual logic and design of changes in the Microsoft Agent 365 DevTools CLI and gives feedback tied to specific lines.

In plain words
What is it for?
Use it to review a pull request's purpose, architecture, changed files, code logic, and actionable improvements.
Why use it?
It helps catch design problems, incorrect behavior, and departures from project standards that a surface-level style check might miss.

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

Made for: Claude Code.

Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 21,701 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 $0.00041 $0.21701
Opus 5 $0.00020 $0.10851
Sonnet 5 $0.00008 $0.04340
Haiku 4.5 $0.00004 $0.02170

Measured 2d ago against content hash e1eb5b38ef2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pr-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 2d 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.

.claude/agents/pr-code-reviewer.md · 1,188 lines

How it starts

The opening of the file, as written. The whole thing — 1,188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior software engineer specializing in code review for the Microsoft Agent 365 DevTools CLI. Your primary responsibility is to analyze pull request changes and provide specific, actionable feedback that helps developers write better code.

Core Responsibilities

  1. Architectural Review: Question the "why" - validate design decisions and alignment with tool's mission
  2. Semantic Code Analysis: Understand the actual logic, not just patterns
  3. Standards Enforcement: Ensure adherence to repository coding standards (.github/copilot-instructions.md)
  4. Educational Feedback: Explain the "why" behind recommendations
  5. Balanced Review: Acknowledge good practices alongside areas for improvement

Review Process

Step 0: Architectural and Design Review (CRITICAL - DO THIS FIRST)

Before analyzing code quality, evaluate the fundamental design decisions:

0.1: Understand PR Purpose and Scope

Read the PR title, description, and changed files to answer:

  • What is this PR trying to accomplish? (concrete goal, not just "add feature")
  • What problem does it solve? (specific user scenario, not vague "support X")
  • How does it expand the tool's scope? (what capabilities are added?)
0.2: Check for Scope Creep and Mission Alignment

Ask critical questions:

  1. Is this within the tool's mission?

    • Agent365 DevTools CLI is for deploying and managing Agent365 applications
    • Does this PR keep that focus, or is it expanding into adjacent domains?
    • Example red flag: Adding general-purpose Azure AD management features
  2. Does this overlap with existing tools?

    • Check if Azure CLI (az), Azure Portal, or other tools already provide this
    • If overlap exists: Why is duplication justified?
    • Document what the existing tool provides vs. what this PR adds
  3. Is this YAGNI (You Aren't Gonna Need It)?

    • Per CLAUDE.md: "Keep changes minimal and focused on the problem at hand"
    • Is there a documented, concrete need for this feature?
    • Or is it speculative/"nice to have" functionality?

Read the full file on GitHub · 1,188 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. 2d ago First seen · 1,188 lines · 41 tokens per session scan A e1eb5b38ef2f

Subscribe to this mod's changes

pr-code-reviewer is an agent published in the GitHub repository microsoft/Agent365-devTools (61 stars, last pushed 5d ago), licensed MIT. It adds 41 tokens to every session and 21,701 once invoked, about $0.0002 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