review-pr-ci

review-pr-ci is a command for Claude Code from anthropics/claude-cookbooks. It costs 18 tokens per session (666 once invoked), scanned A, original, MIT.

A command for reviewing a GitHub pull request and posting the result automatically in a continuous-integration environment.

In plain words
What is it for?
Use it in automated checks to gather a pull request’s diff, analyse the changed code, and publish the review on GitHub.
Why use it?
It provides a repeatable review flow and applies a clear outcome: approve, comment, or request changes.

Command for Claude Code ✓ vendor

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it in automated checks to gather a pull request’s diff, analyse the changed code, and publish the review on GitHub.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/anthropics/claude-cookbooks/review-pr-ci
About the project

Claude Cookbooks is a collection of code examples and guides that show developers how to build applications with the Claude API. Users consult its notebooks and recipes to learn techniques such as classification and retrieval-augmented generation. The catalogue add-ons provide commands, skills, agents, hooks, settings, and instructions related to using these examples.

anthropics/claude-cookbooks · 52,628 stars · on GitHub

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.

Clone the repo
git clone --depth 1 https://github.com/anthropics/claude-cookbooks

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-ci

README.md
[![agentmods](https://agentmods.dev/badge/commands/anthropics/claude-cookbooks/review-pr-ci/github.svg)](https://agentmods.dev/commands/anthropics/claude-cookbooks/review-pr-ci)
Your own site
<a href="https://agentmods.dev/commands/anthropics/claude-cookbooks/review-pr-ci"><img src="https://agentmods.dev/badge/commands/anthropics/claude-cookbooks/review-pr-ci/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for review-pr-ci

Your own site · 80×15
<a href="https://agentmods.dev/commands/anthropics/claude-cookbooks/review-pr-ci"><img src="https://agentmods.dev/badge/commands/anthropics/claude-cookbooks/review-pr-ci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 666 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 $0.00018 $0.00666
Opus 5 $0.00009 $0.00333
Sonnet 5 $0.00004 $0.00133
Haiku 4.5 $0.00002 $0.00067

Measured 12d ago against content hash e03a3e08f5ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

review-pr-ci 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 12d 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.

Origin

Copies of this mod

3 near-identical copies found in the catalogue:

.claude/commands/review-pr-ci.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Arguments

  • $ARGUMENTS: The PR number to review

Your task

Review the specified pull request and post a review to GitHub. This command is designed for CI/automated environments.

Step 1: Gather PR context

Get the PR details and diff:

gh pr view $ARGUMENTS
gh pr diff $ARGUMENTS

Step 2: Review the code changes

Use the Task tool with subagent_type: "code-reviewer" to perform a thorough code review of the changes. Pass the diff and changed files to the agent for analysis.

The code-reviewer agent will analyze:

  • Code quality and best practices
  • Potential bugs or issues
  • Security concerns
  • Performance considerations
  • Documentation and comments

Step 3: Determine review outcome

Based on the code review findings, determine the appropriate review action:

  • APPROVE (--approve): Code looks good, no significant issues found
  • REQUEST_CHANGES (--request-changes): Critical issues that must be fixed before merging
  • COMMENT (--comment): Suggestions or minor issues that don't block merging

Step 4: Post the review

Post the review to GitHub using:

gh pr review $ARGUMENTS --body "YOUR_REVIEW_BODY" --approve|--request-changes|--comment

Format your review body using this template with collapsible sections:

## PR Review

**Recommendation**: APPROVE | REQUEST_CHANGES | COMMENT

### Summary
[1-2 sentence overview of what this PR does]

<details>
<summary>Actionable Feedback (N items)</summary>

List specific items that need attention. Use checkboxes for trackable items:

- [ ] `file.py:42` - Description of issue or required change
- [ ] `notebook.ipynb` (in cell with `some_code = ...`) - Description
- [ ] General: Description of non-file-specific feedback

</details>

<details>
<summary>Detailed Review</summary>

### Code Quality
[Analysis of code patterns, readability, maintainability]

### Security
[Any security considerations or concerns]

### Suggestions
[Optional improvements that aren't blocking]

### Positive Notes
[What was done well - be specific]

</details>

Read the full file on GitHub · 93 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. 12d ago First seen · 93 lines · 18 tokens per session scan A e03a3e08f5ba

Subscribe to this mod's changes

review-pr-ci is a command published in the GitHub repository anthropics/claude-cookbooks (52,628 stars, last pushed 8d ago), licensed MIT. It adds 18 tokens to every session and 666 once invoked, about $0.0001 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.