pr

pr is a command for coding agents from juanmhidalgo/claude-plugins. It costs 34 tokens per session (1,424 once invoked), scanned A, original, MIT.

A thorough review workflow for a GitHub pull request, which is a proposed code change submitted for review.

In plain words
What is it for?
Use it to review eligible pull requests, inspect project instructions, summarize changes, and run parallel checks for code quality and compliance.
Why use it?
It checks whether the request should be reviewed and examines the changes from several perspectives, reducing the chance of missing defects or project-rule violations.

Command

Part of the code-review plugin — 5 skills, 14 commands, 13 agents 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 commands/juanmhidalgo/claude-plugins/pr
Clone the repo
git clone --depth 1 https://github.com/juanmhidalgo/claude-plugins

Or install code-review, the plugin that ships this one along with the rest of its 5 skills, 14 commands, 13 agents.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/pr.svg)](https://agentmods.dev/commands/juanmhidalgo/claude-plugins/pr)
Your own site
<a href="https://agentmods.dev/commands/juanmhidalgo/claude-plugins/pr"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,424 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 $0.00034 $0.01424
Opus 5 $0.00017 $0.00712
Sonnet 5 $0.00007 $0.00285
Haiku 4.5 $0.00003 $0.00142

Measured 3d ago against content hash 45f1c8bb400c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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.

code-review/commands/pr.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pull Request Code Review

Target PR: $ARGUMENTS Repository: !git remote get-url origin Current branch: !git branch --show-current

Execute this multi-step code review workflow precisely:


Step 1: Eligibility Check

Use Agent tool with subagent_type="code-review:pr-eligibility-checker" and model="haiku" to check if the PR is eligible for review.

Stop conditions (do not proceed if any are true):

  • PR is closed or merged
  • PR is a draft
  • PR author is a bot (dependabot, renovate, github-actions)
  • PR is trivial (only docs/config/lockfiles)
  • PR already has a Claude Code review comment

If not eligible, inform the user why and stop.


Step 2: CLAUDE.md Discovery

Use Glob to find CLAUDE.md files: **/CLAUDE.md

Read each one found. Focus on rules relevant to the changed files.


Step 3: PR Summary

Use Agent tool with subagent_type="code-review:pr-summarizer" and model="haiku" to get a summary of the PR changes.

Store this summary for context in the parallel reviews.


Step 4: Parallel Code Review (5 Agents)

Launch these 5 agents in parallel using multiple Agent tool calls in a single message:

  1. CLAUDE.md Compliance - subagent_type="code-review:claudemd-compliance-reviewer" (Sonnet)

    • Provide: PR number, CLAUDE.md files from Step 2, PR summary
  2. Bug Scanner - subagent_type="code-review:bug-scanner" (Sonnet)

    • Provide: PR number
  3. Git History - subagent_type="code-review:git-history-reviewer" (Sonnet)

    • Provide: PR number, files changed
  4. Previous PR Comments - subagent_type="code-review:pr-comments-reviewer" (Sonnet)

    • Provide: PR number, files changed
  5. Code Comments - subagent_type="code-review:code-comments-reviewer" (Sonnet)

    • Provide: PR number, files changed

Collect all issues from all agents.


Step 5: Confidence Scoring

For each issue found in Step 4, launch a parallel Haiku agent using Agent tool with subagent_type="code-review:confidence-scorer" and model="haiku".

Read the full file on GitHub · 196 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. 3d ago First seen · 196 lines · 34 tokens per session scan A 45f1c8bb400c

Subscribe to this mod's changes

pr is a command published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 8d ago), licensed MIT. It adds 34 tokens to every session and 1,424 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.