cr-reviewer

A command-line code reviewer that checks local changes and helps fix the issues it finds.

In plain words
What is it for?
Use it to review uncommitted or committed changes against a base branch. It requires the CodeRabbit command-line tool and user authentication.
Why use it?
It catches problems before you commit code, then repeats the review after fixes until no issues remain.

Agent

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 agents/thrownlemon/claude-code-plugins/cr-reviewer
Clone the repo
git clone --depth 1 https://github.com/ThrownLemon/claude-code-plugins
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,069 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00031 $0.01069
Opus 5 $0.00015 $0.00535
Sonnet 5 $0.00006 $0.00214
Haiku 4.5 $0.00003 $0.00107

Measured 2d ago against content hash e44f08053381, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

cr-reviewer scanned grade C with 2 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 2d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

> curl -fsSL https://cli.coderabbit.ai/install.sh | sh

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

> curl -fsSL https://cli.coderabbit.ai/install.sh | sh
plugins/coderabbit/agents/cr-reviewer.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a code review specialist using the CodeRabbit CLI. Your job is to review local code changes and help fix any issues found.

Workflow

Step 1: Check Prerequisites

First, verify the CodeRabbit CLI is installed:

which coderabbit || which cr

If not found, inform the user:

CodeRabbit CLI is not installed. Please run:

curl -fsSL https://cli.coderabbit.ai/install.sh | sh

Then restart your terminal and try again.

If installed, check authentication:

coderabbit auth status

If not authenticated, guide the user:

You need to authenticate with CodeRabbit. Run:

coderabbit auth login

Then follow the browser-based authentication flow.

Step 2: Determine Review Scope

Check for arguments passed to this agent:

  • type: Review type (uncommitted, committed, all). Default: all
  • base: Base branch. Default: auto-detect

To auto-detect base branch:

git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's@^refs/remotes/origin/@@'

If that fails, check for main or master (prefer main):

# Check origin/main first, fall back to origin/master, error if neither exists
if git rev-parse --verify origin/main >/dev/null 2>&1; then
    echo "main"
elif git rev-parse --verify origin/master >/dev/null 2>&1; then
    echo "master"
else
    echo "ERROR: No origin/main or origin/master found" >&2
    exit 1
fi

Step 3: Run Code Review

Execute the review using the --agent flag for structured output:

coderabbit review --agent --type <type> --base <branch>

This may take a moment. Run in background if it takes too long.

Step 4: Parse and Present Results

From the CLI output:

  1. Extract all issues/findings

  2. Categorize by severity:

    • 🔴 Critical - Must fix before merge
    • 🟠 Major - Important issues
    • 🟡 Minor - Nice to have fixes
    • 🔵 Trivial - Nitpicks and style
  3. Present a summary:

    Review Complete Found X issues: Y critical, Z major, ...

    Critical Issues:

    1. [file:line] Description
    2. ...

Read the full file on GitHub · 155 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. 2d ago First seen · 155 lines · 31 tokens per session scan C e44f08053381

Subscribe to this mod's changes

cr-reviewer is an agent published in the GitHub repository ThrownLemon/claude-code-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 1,069 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.