pr-review

pr-review is a skill for Claude Code, Codex from magic3007/dotfiles. It costs 28 tokens per session (1,651 once invoked), scanned A, original, MIT.

A pull-request review workflow that examines the changes, assigns focused review tasks based on their type, and combines the findings.

In plain words
What is it for?
Reviewing the current branch's pull request or a specified pull request, with full or quick review modes.
Why use it?
It helps a review cover different kinds of changes systematically instead of relying on one general pass.

Skill for Claude CodeCodex

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 skills/magic3007/dotfiles/pr-review
Any agent
npx skills add magic3007/dotfiles --skill pr-review
Clone the repo
git clone --depth 1 https://github.com/magic3007/dotfiles

Made for: Claude Code, Codex.

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 pr-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/magic3007/dotfiles/pr-review.svg)](https://agentmods.dev/skills/magic3007/dotfiles/pr-review)
Your own site
<a href="https://agentmods.dev/skills/magic3007/dotfiles/pr-review"><img src="https://agentmods.dev/badge/skills/magic3007/dotfiles/pr-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,651 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 $0.00028 $0.01651
Opus 5 $0.00014 $0.00826
Sonnet 5 $0.00006 $0.00330
Haiku 4.5 $0.00003 $0.00165

Measured 4d ago against content hash d0b9782dd7a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pr-review 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 4d 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/skills/pr-review/SKILL.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Code Review (Dynamic Agent Allocation)

Intelligent code review for the current branch's Pull Request. Dynamically generates targeted review tasks based on PR changes.

Usage

Invoke with /pr-review or when the task matches.

Arguments:

  • No arguments: Review PR for current branch
  • PR number: Review specific PR (e.g., pr-review 123)
  • --quick: Quick mode, only run Phase 1 analysis

Quick Start

  1. Get current branch PR: gh pr view --json number,title,state,isDraft
  2. If PR doesn't exist or is closed, stop and explain
  3. Execute Phases 1-4 in order

Workflow Overview

Phase 1: Deep PR Analysis
    ├─ 1.0 PR Status Check
    ├─ 1.1 Get PR Summary
    └─ 1.2-1.4 Change Type Detection
    ↓
Phase 2: Dynamic Agent Planning
    ↓
Phase 3: Execute Review Tasks [Parallel]
    ↓
Phase 4: Confidence Scoring & Summary

Model Configuration

Mode CRITICAL/HIGH MEDIUM LOW
Default Opus Sonnet Haiku
Quick (--quick) Sonnet Sonnet Sonnet
Economy (--economy) Sonnet Haiku Haiku

Phase 1: Deep PR Analysis

1.0 PR Status Check

Check if PR should be reviewed:

  • Is it closed? → Stop
  • Is it a draft? → Note but continue
  • Is it bot-generated? → Skip

1.1 Get PR Summary

Get basic PR info: title, description, modified files, change summary.

1.2 Change Type Detection

Analyze each file change, detecting change types by risk level.

CRITICAL level types: FrameworkA, FrameworkB, FrameworkC, FrameworkD HIGH level types: distributed comm, DTensor, MoE, TP/EP/CP MEDIUM level types: tensor ops, workflow, API, compile LOW level types: tests, docs, config

1.3 Framework-Specific Risk Identification

Based on detected types, identify corresponding risks.

1.4 Output Change Analysis Report

CHANGE_ANALYSIS_REPORT:
- detected_types: [FRAMEWORK_PARALLEL, COMPONENT_A, FRAMEWORK_CORE, ...]
- risk_level: CRITICAL | HIGH | MEDIUM | LOW
- affected_files: [file1.py, file2.py, ...]
- identified_risks: [risk1, risk2, ...]
- related_frameworks: [frameworkA, frameworkB, frameworkC, ...]

Read the full file on GitHub · 233 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. 4d ago First seen · 233 lines · 28 tokens per session scan A d0b9782dd7a5

Subscribe to this mod's changes

pr-review is a skill published in the GitHub repository magic3007/dotfiles (11 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 1,651 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 2026-08-31.

Related

Other skills, from other repositories

git-commit

Create a new git commit for staged changes. Use when the user asks to commit staged changes with an auto-generated Conventional Commits message, or when Claude Code itself wants to run git commit.

aiya000/dotfiles · 43 tokens

inspect-malicious-code

Inspect a project for potentially malicious code (malware, spyware, etc.) using static analysis only. Use when the user asks to audit a project or dependency for malicious or suspicious code.

aiya000/dotfiles · 42 tokens

verify-git-command-location

Verify that the correct git binary is in use, especially when running under WSL with a Windows filesystem. Use the first time a git command is executed in a session.

aiya000/dotfiles · 40 tokens

define-markdown-format

Load and apply Markdown formatting rules for this project. Use when writing or editing Markdown files.

aiya000/dotfiles · 23 tokens

git-verify-identity

Verify that git user.name and user.email are configured. Use automatically before any git operation that requires identity (commits, rebases, cherry-picks, etc.), and when the user asks to check or verify their git identity.

aiya000/dotfiles · 52 tokens

create-oss-skill

Create well-formed Agent Skills following the agentskills.io specification. Scaffold directories, write SKILL.md files, bundle scripts, and structure instructions for progressive disclosure. Use when creating a new skill, reviewing skill structure, optimizing a skill description, or setting up evals for skill quality.

urmzd/dotfiles · 63 tokens