review-pr

review-pr is a command for Claude Code from heznpc/PLOIDY. It costs 43 tokens per session (1,253 once invoked), scanned A, original, MIT.

A command that reviews a pull request from two viewpoints: one with access to the full repository and one that sees only the change and its description. A pull request is a proposed code change submitted for review before it is merged.

In plain words
What is it for?
For checking pull requests before merging, including their scope, design choices, tests, risks, and possible author bias.
Why use it?
It helps reveal whether the change meets its stated goal, includes unrelated work, or is more complicated than necessary.

Command for Claude Code

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/heznpc/ploidy/review-pr
Clone the repo
git clone --depth 1 https://github.com/heznpc/PLOIDY

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/heznpc/ploidy/review-pr.svg)](https://agentmods.dev/commands/heznpc/ploidy/review-pr)
Your own site
<a href="https://agentmods.dev/commands/heznpc/ploidy/review-pr"><img src="https://agentmods.dev/badge/commands/heznpc/ploidy/review-pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,253 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 $0.00043 $0.01253
Opus 5 $0.00022 $0.00626
Sonnet 5 $0.00009 $0.00251
Haiku 4.5 $0.00004 $0.00125

Measured 4d ago against content hash 44bbc18ede0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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/commands/review-pr.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The user wants a second-opinion review on a pull request before merging. If $ARGUMENTS is empty, target the current branch's PR; if it's a number or #N, target that PR on the configured remote.

1 · Gather the PR payload

Decide the target:

  • If $ARGUMENTS is blank → gh pr view --json title,body,author,headRefName,baseRefName,url for the current branch.
  • If $ARGUMENTS is a number → gh pr view $ARGUMENTS --json title,body,author,headRefName,baseRefName,url.

Then capture the diff:

  • gh pr diff <target> — limit to ~3000 lines for the fresh payload. If larger, keep the full diff for the Deep step and pass a <head> + <tail> + <... N lines elided ...> truncation to the Fresh sub-agent.

Store:

  • pr_title, pr_body, pr_url, base_ref, head_ref
  • diff_full (for Deep), diff_compact (for Fresh)

2 · Write the Deep-context review

You have the full repo. In ~250 words:

  1. Stated goal check — does the diff actually achieve what the PR body claims? Quote the specific claim and mark match / partial / mismatch.
  2. Scope discipline — is anything in the diff unrelated to the stated goal? Flag each file that looks scope-creeping.
  3. Over-engineering — are there abstractions, generalisations, or tests added "because we always do that" rather than needed for this change? Name them. If none, say so.
  4. Coverage gaps — given your knowledge of the repo, what didn't get touched that probably should have? (migrations, docs, CONVENTIONS.md, call sites elsewhere, …)
  5. Author-bias check — what in the PR author's decisions do you find yourself defending because you also would have written it that way? Name it explicitly. If nothing, say so.

Tag each finding HIGH / MEDIUM / LOW.

3 · Spawn a Fresh sub-agent

Use the Agent tool (subagent_type="general-purpose"). The fresh reviewer must see only the PR description + the (possibly truncated) diff — no repo context, no CLAUDE.md, no prior conversation.

Read the full file on GitHub · 131 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 · 131 lines · 0 tokens per session scan A 44bbc18ede0a

Subscribe to this mod's changes

review-pr is a command published in the GitHub repository heznpc/PLOIDY (0 stars, last pushed 8d ago), licensed MIT. It adds 43 tokens to every session and 1,253 once invoked, about $0.0002 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.