review-pr

review-pr is a command for Claude Code from kumaran-is/claude-code-onboarding. It costs 73 tokens per session (965 once invoked), scanned A, original, MIT.

A pull request review that examines code changes from six angles, including comments, tests, errors, types, code quality, and unnecessary complexity.

In plain words
What is it for?
It is for checking a pull request or someone else's changes before merging, with optional focus on comments, tests, errors, or types.
Why use it?
It helps find behavioral gaps and maintainability problems before changes are merged or shared for review. The review depth is adjusted to the size of the change.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

Good fit It is for checking a pull request or someone else's changes before merging, with optional focus on comments, tests, errors, or types.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/kumaran-is/claude-code-onboarding/review-pr
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.

Clone the repo
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboarding

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/kumaran-is/claude-code-onboarding/review-pr.svg)](https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/review-pr)
Your own site
<a href="https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/review-pr"><img src="https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/review-pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 965 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 $0.00073 $0.00965
Opus 5 $0.00036 $0.00483
Sonnet 5 $0.00015 $0.00193
Haiku 4.5 $0.00007 $0.00097

Measured 4d ago against content hash 4d0c3f2f7889, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Review — 6 Roles

Run a concern-specific review of code changes. Each role examines a different dimension regardless of tech stack.

Roles

Role Agent Focus
Comment accuracy comment-analyzer Comments vs actual code
Test coverage pr-test-analyzer Behavioral gaps, not line coverage
Error handling silent-failure-hunter Silent failures, swallowed exceptions
Type design type-design-analyzer Invariants, encapsulation, invalid states
Code quality code-reviewer Bugs, style, CLAUDE.md compliance
Simplification code-simplifier Unnecessary complexity

Process

Step 0 — Risk-Gated Scope Assessment

Before dispatching reviewers, calculate the PR risk score to calibrate review depth.

git diff --shortstat HEAD~1
git diff --name-status HEAD~1

Apply the Size Risk factor from /pr-risk:

Files / Lines Risk Tier Review Depth
≤ 5 files, ≤ 100 lines 🟢 Low Run roles: errors, code only (skip comment-analyzer, type-design-analyzer for speed)
6-20 files, ≤ 600 lines 🟡 Medium Run all 6 roles
> 20 files OR > 600 lines 🟠 High Run all 6 roles + recommend running /pr-risk for full scoring

Check for security-sensitive patterns:

git diff --name-only HEAD~1 | grep -iE "auth|login|token|jwt|crypto|secret|password|permission|role|guard"

If security-sensitive files changed: always include security-reviewer via code-reviewer agent (flag it explicitly).

Print the risk tier before dispatching agents so the user sees it.

  1. Determine scope — From $ARGUMENTS; if not specified use git diff HEAD~1
  2. Determine roles — Parse topic filter from $ARGUMENTS (see Topic Filters below); default: all 6 (adjusted by risk tier from Step 0)
  3. Dispatch agents — Run each selected agent against the scope; collect findings
  4. Aggregate — Group all findings by severity across all roles

Read the full file on GitHub · 106 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 · 106 lines · 0 tokens per session scan A 4d0c3f2f7889

Subscribe to this mod's changes

review-pr is a command published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 965 once invoked, about $0.0004 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 2026-09-03.