A command that examines open GitHub pull requests, which are proposed code changes awaiting review. It checks the changes against the project's code, standards, and goals.

Use it to review selected pull requests or all open ones, inspect their diffs and surrounding files, and assess code quality, risks, and test coverage.

It helps find bugs, missing tests, edge cases, and project-alignment problems before code is merged.

How jayminwest/seeds configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jayminwest/seeds. 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/jayminwest/seeds/main/.claude/commands/pr-reviews.md

Clone the repo

git clone --depth 1 https://github.com/jayminwest/seeds

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/jayminwest/seeds/pr-reviews.svg)](https://agentmods.dev/commands/jayminwest/seeds/pr-reviews)

Your own site

<a href="https://agentmods.dev/commands/jayminwest/seeds/pr-reviews"><img src="https://agentmods.dev/badge/commands/jayminwest/seeds/pr-reviews.svg" alt="Measured on agentmods" height="20"></a>

Per session 3 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 642 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 92% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00003	$0.00642
Opus 5	$0.00002	$0.00321
Sonnet 5	$0.00001	$0.00128
Haiku 4.5	$0.00000	$0.00064

Measured 8d ago against content hash 8f666ae262fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pr-reviews 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.

Origin

This is a copy

92% identical to pr-reviews — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/pr-reviews.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

intro

Review open pull requests for code quality, project alignment, and risks.

Argument: $ARGUMENTS — optional PR number(s) to review (e.g., 9 or 9 12 15). If empty, review all open PRs.

Steps

1. Discover PRs to review

If $ARGUMENTS contains PR number(s), use those
Otherwise, run gh pr list --state open --json number,title,author,headRefName,additions,deletions to get all open PRs
If there are no open PRs, say so and stop

2. Spawn a review team

Use the Task tool to spawn parallel agents (one per PR). Each agent should:

a. Gather context

gh pr view <number> --json title,body,author,additions,deletions,files,commits,comments,reviews,headRefName,baseRefName
gh pr diff <number> to get the full diff
Read any files touched by the PR to understand the surrounding code

b. Code quality review

Check for correctness — does the code do what the PR claims?
Check for bugs, edge cases, and error handling gaps
Check adherence to project conventions (see CLAUDE.md): strict TypeScript, zero runtime deps, Biome formatting, tab indentation, 100-char line width
Check test coverage — are new code paths tested? Do tests follow the "never mock what you can use for real" philosophy?
Flag any security concerns (injection, unsafe input handling, etc.)

c. Project alignment review

Does this change fit the project's architecture and direction?
Does it follow existing patterns or introduce unnecessary new ones?
Is the scope appropriate — does it do too much or too little?
Are there breaking changes or backward-compatibility concerns?

d. Risk assessment

What could go wrong if this is merged?
Are there performance implications?
Does it touch critical paths (config loading, JSONL store, issue lifecycle)?
Are there dependency or compatibility risks?
Could it conflict with other open PRs?

e. Produce a review summary

Each agent should return a structured review:

PR: #<number> — <title> by <author>
Verdict: Approve / Request Changes / Needs Discussion
Summary: 2-3 sentence overview
Strengths: What's good about this PR
Issues: Bugs, risks, or concerns (with file:line references)
Suggestions: Non-blocking improvements
Project alignment: How well it fits seeds' direction

Read the full file on GitHub · 65 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.

8d ago First seen · 65 lines · 3 tokens per session scan A 8f666ae262fd

Subscribe to this mod's changes

pr-reviews is a command published in the GitHub repository jayminwest/seeds (132 stars, last pushed 5d ago), licensed MIT. It adds 3 tokens to every session and 642 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to pr-reviews, differing in 4 lines, and is treated as a copy.

Code review Git and workflow

seeds: Command for Claude Code