pr-review

pr-review is a skill for Claude Code, Codex from nimble-giant/nimble-mold. It costs 53 tokens per session (873 once invoked), scanned A, original, Apache-2.0.

A code-review command for checking the changes in a pull request, which is a proposed code update for merging into a project. It can write a Markdown report or, after approval, post comments on the pull request.

In plain words
What is it for?
Use it to review a pull request by number or URL, review the current pull request, or produce focused feedback in a selected area.
Why use it?
It helps find problems in proposed changes without manually checking every changed line. You can also limit the review to security, performance, or testing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review a pull request by number or URL, review the current pull request, or produce focused feedback in a selected area.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nimble-giant/nimble-mold/pr-review
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.

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

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/nimble-giant/nimble-mold/pr-review/github.svg)](https://agentmods.dev/skills/nimble-giant/nimble-mold/pr-review)
Your own site
<a href="https://agentmods.dev/skills/nimble-giant/nimble-mold/pr-review"><img src="https://agentmods.dev/badge/skills/nimble-giant/nimble-mold/pr-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pr-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/nimble-giant/nimble-mold/pr-review"><img src="https://agentmods.dev/badge/skills/nimble-giant/nimble-mold/pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 873 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 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 $0.00053 $0.00873
Opus 5 $0.00026 $0.00436
Sonnet 5 $0.00011 $0.00175
Haiku 4.5 $0.00005 $0.00087

Measured 10d ago against content hash 74d574418ade, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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.

skills/pr-review/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Review

Purpose

This command helps reviewers conduct comprehensive code reviews efficiently. It analyzes PR changes, generates review feedback, and can either output a markdown review file (silent mode) or post comments directly to the PR (interactive mode with plan approval).

Command Name

pr-review

Invocation Syntax

/pr-review <pr-number> [--silent-mode|-s] [--focus=<area>]
/pr-review <pr-url> [--silent-mode|-s] [--focus=<area>]
/pr-review [--silent-mode|-s] [--focus=<area>]

Examples:

# Silent mode (default) - generates markdown review file
/pr-review 1234
/pr-review 1234 --silent-mode
/pr-review 1234 -s

# Interactive mode - posts comments to PR after plan approval
/pr-review 1234 --silent-mode=false

# Focus on specific areas
/pr-review 1234 --focus=security
/pr-review 1234 --focus=performance
/pr-review 1234 --focus=testing

# Auto-detect current PR
/pr-review --silent-mode=false

Flags:

  • --silent-mode / -s: Generate markdown review file only (default: true)
  • --silent-mode=false: Interactive mode with plan approval and PR commenting
  • --focus=<area>: Focus review on specific areas (security, performance, testing, architecture, etc.)

Workflow Overview

Execute this workflow when the command is invoked:

  1. Parse Flags: Determine silent mode and focus areas
  2. Fetch PR Information: Get PR details, diff, and context
  3. Analyze Code Changes: Comprehensive code review analysis
  4. Generate Review: Create structured review feedback
  5. Output Mode: Either save markdown file (silent) or enter plan mode (interactive)

Phase 1: Flag Parsing and Setup

Step 1.1: Parse Command Flags

Default behavior: --silent-mode=true

// Parse user input for flags
const flags = {
  silentMode: true,  // Default to silent mode
  focus: null,       // No specific focus by default
  prNumber: null,
  prUrl: null
};

// Check for explicit flags in user input
if (input.includes('--silent-mode=false')) flags.silentMode = false;
if (input.includes('--focus=')) flags.focus = extractFocusArea(input);

Read the full file on GitHub · 147 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 147 lines · 53 tokens per session scan A 74d574418ade

Subscribe to this mod's changes

pr-review is a skill published in the GitHub repository nimble-giant/nimble-mold (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 53 tokens to every session and 873 once invoked, about $0.0003 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.