claude-code-action: Command for Claude Code

.claude/commands/review-pr.md

review-pr is a command for Claude Code from anthropics/claude-code-action. It costs 4 tokens per session (129 once invoked), scanned A, original, MIT.

A command that coordinates several specialist agents to perform a comprehensive code review and combines only the findings worth reporting.

In plain words
What is it for?
Use it to review a change, have specialists inspect key risk areas, and receive concise feedback as inline comments or general review notes.
Why use it?
It reduces the need to run separate reviews for code quality, performance, tests, documentation, and security.

Command for Claude Code ✓ vendor

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

This is anthropics/claude-code-action's own configuration. It tells Claude Code how to work on claude-code-action 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 claude-code-action configures →

▶ Claude Code GitHub Action: Automated PR Reviews Setup The Gray Cat · about review-pr · on YouTube →
About the project

Claude Code Action is a GitHub Action that lets Claude answer questions, review code, and implement changes in pull requests and issues. Development teams use it through comments, assignments, or automated prompts, with execution on their own GitHub runners. The catalogue entries define agents, commands, integrations, and instructions for operating the action.

anthropics/claude-code-action · 8,805 stars · on GitHub

Reuse

Borrowing it

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

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/anthropics/claude-code-action/review-pr.svg)](https://agentmods.dev/commands/anthropics/claude-code-action/review-pr)
Your own site
<a href="https://agentmods.dev/commands/anthropics/claude-code-action/review-pr"><img src="https://agentmods.dev/badge/commands/anthropics/claude-code-action/review-pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 4 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 129 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 $0.00004 $0.00129
Opus 5 $0.00002 $0.00064
Sonnet 5 $0.00001 $0.00026
Haiku 4.5 $0.00000 $0.00013

Measured 8d ago against content hash 7b03c6330355, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 · 21 lines

What it actually says

Perform a comprehensive code review using subagents for key areas:

  • code-quality-reviewer
  • performance-reviewer
  • test-coverage-reviewer
  • documentation-accuracy-reviewer
  • security-code-reviewer

Instruct each to only provide noteworthy feedback. Once they finish, review the feedback and post only the feedback that you also deem noteworthy.

Provide feedback using inline comments for specific issues. Use top-level comments for general observations or praise. Keep feedback concise.


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 · 21 lines · 4 tokens per session scan A 7b03c6330355

Subscribe to this mod's changes

review-pr is a command published in the GitHub repository anthropics/claude-code-action (8,805 stars, last pushed yesterday), licensed MIT. It adds 4 tokens to every session and 129 once invoked, about $0.0000 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.