pr-review

pr-review is a command for coding agents from notque/vexjoy-agent. It costs 13 tokens per session (2,615 once invoked), scanned A, original, MIT.

A command that reviews a pull request or a local Git branch diff using several specialized reviewers. It can also record recurring review patterns for later reference.

In plain words
What is it for?
Use it to review local or GitHub changes, focus on selected review aspects, run review agents in parallel, and learn from repeated issues.
Why use it?
It provides a broad review even when there is no open pull request, and it turns review findings into actionable feedback across different areas of the change.

Command

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 commands/notque/vexjoy-agent/pr-review
Clone the repo
git clone --depth 1 https://github.com/notque/vexjoy-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 pr-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/notque/vexjoy-agent/pr-review.svg)](https://agentmods.dev/commands/notque/vexjoy-agent/pr-review)
Your own site
<a href="https://agentmods.dev/commands/notque/vexjoy-agent/pr-review"><img src="https://agentmods.dev/badge/commands/notque/vexjoy-agent/pr-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,615 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 $0.00013 $0.02615
Opus 5 $0.00006 $0.01307
Sonnet 5 $0.00003 $0.00523
Haiku 4.5 $0.00001 $0.00262

Measured 2d ago against content hash 639c4b4b3c9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 2d 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.

commands/pr-review.md · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Comprehensive PR Review (with Retro Learning)

Comprehensive PR review using specialized agents, with automatic knowledge capture.

This is a local fork of pr-review-toolkit:review-pr with a retro learning phase that records review patterns to the knowledge store.

Scope

This command accepts either a PR reference or a local branch diff. You do not need an open PR to use it.

Invocation form What it reviews
/pr-review (no argument) Uncommitted and committed local changes against the base branch (HEAD vs base)
/pr-review 123 or /pr-review https://github.com/org/repo/pull/123 The diff of the specified open PR

When no argument is provided, the command reads git diff to determine changed files. When a PR number or URL is provided, it fetches the PR diff via gh pr view. All review phases and retro learning apply in both cases.

Usage

/pr-review              # Full review (all aspects)
/pr-review tests errors # Specific aspects only
/pr-review all parallel # All agents in parallel

Related: /pr-review-address-feedback — Process existing GitHub reviewer comments (validate-then-fix workflow)

Review Aspects

  • comments - Analyze code comment accuracy and maintainability
  • tests - Review test coverage quality and completeness
  • errors - Check error handling for silent failures
  • types - Analyze type design and invariants (if new types added)
  • code - General code review for project guidelines
  • simplify - Simplify code for clarity and maintainability
  • all - Run all applicable reviews (default)

Instructions for Claude

Review Aspects (optional): "$ARGUMENTS"

Phase 1: Determine Review Scope

  1. Check git status to identify changed files: git diff --name-only
  2. Parse arguments to see if user requested specific review aspects
  3. Default: Run all applicable reviews
  4. Check if PR already exists: gh pr view 2>/dev/null

Phase 2: Identify Applicable Reviews

Read the full file on GitHub · 273 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. 2d ago Changed 639c4b4b3c9f
  2. 6d ago First seen · 273 lines · 13 tokens per session scan A 85119791a870

Subscribe to this mod's changes

pr-review is a command published in the GitHub repository notque/vexjoy-agent (420 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 2,615 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.