rally: Command for Claude Code

.claude/commands/review-pr.md

review-pr is a command for Claude Code from ddgonzal3/rally. It costs 0 tokens per session (2,488 once invoked), scanned A, original, MIT.

A command that coordinates a thorough, repeated review of the changes in a pull request, which is a proposed code change awaiting review. It can apply fixes and stage the resulting files.

In plain words
What is it for?
Finding issues in pull-request changes, applying review fixes, staging them, and reporting the results.
Why use it?
It organizes large code reviews through separate helper agents, keeping the main conversation focused on coordinating findings and fixes.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

This is ddgonzal3/rally's own configuration. It tells Claude Code how to work on rally 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 rally configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ddgonzal3/rally. 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/ddgonzal3/rally/main/.claude/commands/review-pr.md
Clone the repo
git clone --depth 1 https://github.com/ddgonzal3/rally

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 review-pr

README.md
[![agentmods](https://agentmods.dev/badge/commands/ddgonzal3/rally/review-pr.svg)](https://agentmods.dev/commands/ddgonzal3/rally/review-pr)
Your own site
<a href="https://agentmods.dev/commands/ddgonzal3/rally/review-pr"><img src="https://agentmods.dev/badge/commands/ddgonzal3/rally/review-pr.svg" alt="Measured on agentmods" height="20"></a>
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 2,488 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 $0.00000 $0.02488
Opus 5 $0.00000 $0.01244
Sonnet 5 $0.00000 $0.00498
Haiku 4.5 $0.00000 $0.00249

Measured 8d ago against content hash b75a7cb15d51, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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/commands/review-pr.md · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Review (Edit, Fix Loop & Stage)

You are a senior engineer orchestrating a thorough, iterative code review. Your goal is to leave the code meaningfully better than you found it.

CRITICAL: All review work MUST be delegated to Task agents. The main agent handles only orchestration (branch detection, merging findings, applying fixes, staging, and reporting). This keeps the main conversation context clean and unaffected by the volume of code read during review.

Step 1: Determine the Base Branch (Main Agent)

This is lightweight — do it directly.

  1. If PR number provided:

    gh pr view <number> --json baseRefName,headRefName,files
    
  2. If branch name provided:

    gh pr list --head <branch-name> --json number,baseRefName
    # If no PR exists, ask the user for the target branch
    
  3. If "current branch" or no input:

    gh pr view --json baseRefName,number 2>/dev/null
    # If no PR, detect default branch
    git symbolic-ref refs/remotes/origin/HEAD | sed 's@^refs/remotes/origin/@@'
    

Store: BASE_BRANCH="<determined-base>"

Step 2: Collect Changed File List (Main Agent)

Run these commands to get the file list and stats — but do NOT read the files yourself:

git diff --name-only $(git merge-base HEAD $BASE_BRANCH)...HEAD
git diff --stat $(git merge-base HEAD $BASE_BRANCH)...HEAD
git log --oneline $(git merge-base HEAD $BASE_BRANCH)...HEAD

Use the file count to decide the review strategy in Step 3.

Step 3: Delegate Review to Task Agents

All code reading and review happens in subagents. Never read changed files or diffs in the main context.

Small PRs (1-4 files, single layer)

Launch one Task agent (subagent_type: general-purpose) with this prompt structure:

You are a senior engineer doing a thorough code review. Review the PR diff and changed files against the checklist below.

BASE_BRANCH: <base>
Changed files: <file list>

## Instructions

1. Run: git diff $(git merge-base HEAD <base>)...HEAD
2. Read each changed file completely
3. Understand what the PR is trying to accomplish
4. Review against EVERY checklist category below
5. For each issue found, note: file, line, severity, description
6. Return your findings in the structured format at the bottom

<include the full Review Checklist from below>
<include the Severity Levels from below>
<include the Output Format from below>

Read the full file on GitHub · 276 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. 8d ago First seen · 276 lines · 0 tokens per session scan A b75a7cb15d51

Subscribe to this mod's changes

review-pr is a command published in the GitHub repository ddgonzal3/rally (6 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,488 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 2026-08-31.