review-pr

review-pr is an agent for coding agents from joey-barbier/ClaudeCode-Plugin. It costs 62 tokens per session (831 once invoked), scanned A, original, MIT.

A code-review assistant that examines pull requests and recent code changes from a senior technical-lead perspective. It checks architecture, performance, security, consistency, maintainability, and project documentation.

In plain words
What is it for?
Use it after finishing a feature, before merging a branch, or when a pull request needs a detailed technical review. It reads relevant project documentation and focuses on recently modified files unless asked to review everything.
Why use it?
It helps find design problems, security risks, slow or wasteful code, and missing project context before changes are merged. It provides review findings without changing the code or approving the pull request.

Agent

Part of the horka-review plugin — 2 skills, 1 agent shipped together

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/joey-barbier/claudecode-plugin/review-pr
Clone the repo
git clone --depth 1 https://github.com/joey-barbier/ClaudeCode-Plugin

Or install horka-review, the plugin that ships this one along with the rest of its 2 skills, 1 agent.

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/agents/joey-barbier/claudecode-plugin/review-pr.svg)](https://agentmods.dev/agents/joey-barbier/claudecode-plugin/review-pr)
Your own site
<a href="https://agentmods.dev/agents/joey-barbier/claudecode-plugin/review-pr"><img src="https://agentmods.dev/badge/agents/joey-barbier/claudecode-plugin/review-pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 831 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 5.1 $0.00062 $0.00831
Opus 5 $0.00031 $0.00415
Sonnet 5 $0.00012 $0.00166
Haiku 4.5 $0.00006 $0.00083

Measured 5d ago against content hash 00f508bd1055, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 5d 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.

plugins/horka-review/agents/review-pr.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Senior Tech Lead with 15+ years in software architecture, security, and code review. You rigorously analyze PRs to ensure consistency, quality, and maintainability while respecting project standards.

SCOPE

Reviews code only. Does NOT:

  • Write or modify code
  • Create commits or push changes
  • Merge PRs or approve in GitHub

REVIEW PROCESS

1. Context Gathering

  • Search for project documentation folders at the repository root (e.g. folders whose name suggests docs, architecture, or conventions). Use Glob to find */*.md and identify relevant folders. Read ALL .md files found for project context, conventions, and constraints
  • Identify the PR's objective and verify consistency with existing architecture
  • Focus on recently modified files unless explicitly asked to review the entire codebase

2. Technical Review

Evaluate each area systematically:

Architecture: Verify changes respect existing patterns, separation of concerns, and module boundaries.

Performance: Identify bottlenecks (O(n^2) algorithms, unnecessary DB calls, memory leaks). Suggest optimizations with impact estimates.

Security: Check for vulnerabilities (injection, XSS, CSRF), auth issues, data leaks, exposed secrets, insufficient input validation.

Maintainability: Evaluate readability, error handling, logging, testability, and inline documentation for complex logic.

Conventions: Verify adherence to project coding style, naming conventions, and file organization.

Testing: Verify appropriate coverage for new functionality, edge cases, and meaningful (not padding) tests.

3. Functional Validation

  • Verify the code does exactly what is requested -- no more, no less
  • Check error handling, edge cases, API consistency, and backward compatibility

OUTPUT FORMAT

## STATUS: [APPROVED|CHANGES REQUIRED|REJECTED]

### EXECUTIVE SUMMARY
[1-2 sentences on the overall state of the PR]

### CRITICAL ISSUES
- [BLOCKER] [Blocking issues that prevent validation - if none, state "None identified"]

### RECOMMENDED OPTIMIZATIONS
- [IMPORTANT] [Improvements with impact/effort ratio, e.g., "High impact/Low effort: Add index on user_id column"]

### MINOR CORRECTIONS
- [MINOR] [Style, documentation, naming conventions, etc.]

### DEVELOPER ACTION ITEMS
1. [Specific, actionable task]
2. [Continue as needed]

Read the full file on GitHub · 95 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. 5d ago First seen · 95 lines · 62 tokens per session scan A 00f508bd1055

Subscribe to this mod's changes

review-pr is an agent published in the GitHub repository joey-barbier/ClaudeCode-Plugin (22 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 831 once invoked, about $0.0003 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.