review-pr

A command for performing a broad review of a GitHub pull request, a proposed set of code changes, using several specialised reviewers.

In plain words
What is it for?
It reviews architecture, code quality, and test coverage, then saves the findings for possible posting or resolution.
Why use it?
It collects the pull request context and checks the changes from multiple angles instead of relying on one review pass.

Command 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 commands/microsoft/agent365-python/review-pr
Clone the repo
git clone --depth 1 https://github.com/microsoft/Agent365-python

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,073 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 $0.00000 $0.02073
Opus 5 $0.00000 $0.01037
Sonnet 5 $0.00000 $0.00415
Haiku 4.5 $0.00000 $0.00207

Measured yesterday against content hash 42ebf9babc07, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-pr 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/commands/review-pr.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Pull Request

Review code changes in a specific pull request using a comprehensive multi-agent code review process with specialized reviewers for architecture, code quality, and test coverage.

Usage

/review-pr <PR_NUMBER>

Examples:

  • /review-pr 123 - Review pull request #123
  • /review-pr 45 - Review pull request #45

Instructions

You are coordinating a comprehensive code review for pull request #$ARGUMENTS.

Step 1: Gather PR Information

First, collect information about the pull request:

  1. Get PR details, changed files, and the HEAD commit SHA:

    if [ -z "$ARGUMENTS" ]; then
      echo "Error: Missing PR number. Usage: /review-pr <PR_NUMBER>" >&2
      exit 1
    fi
    
    if ! printf '%s\n' "$ARGUMENTS" | grep -Eq '^[0-9]+$'; then
      echo "Error: Invalid PR number '$ARGUMENTS'. PR number must be a positive integer. Usage: /review-pr <PR_NUMBER>" >&2
      exit 1
    fi
    
    gh pr view "$ARGUMENTS" --json number,title,body,baseRefName,headRefName,headRefOid,url,files
    gh pr diff "$ARGUMENTS"
    
  2. Extract key information:

    • List of changed files
    • PR URL for linking in review comments
    • HEAD commit SHA (headRefOid) - required for posting inline comments
  3. IMPORTANT: Save the diff output - you will need it to:

    • Include relevant diff context snippets in each finding
    • Determine the exact target file line numbers for inline comments (absolute line numbers in the target file, computed from the diff hunk headers, as required by /post-review-comments)
    • Determine the side (RIGHT for additions +, LEFT for deletions -)
  4. Create the .codereviews/ directory if it doesn't exist.

Step 2: Launch Parallel Code Reviews

Launch THREE sub-agents in parallel using the Task tool. Each agent MUST receive:

  • The PR number: $ARGUMENTS
  • The list of changed files (so they stay scoped to PR files only)
  • The PR URL for generating clickable links

CRITICAL: You MUST launch all three agents in a SINGLE message with THREE parallel Task tool calls:

Read the full file on GitHub · 227 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 · 227 lines · 0 tokens per session scan A 42ebf9babc07

Subscribe to this mod's changes

review-pr is a command published in the GitHub repository microsoft/Agent365-python (41 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,073 tokens. 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.