A guide for using CodeRabbit, an automated tool that reviews source-code changes and reports problems such as security issues, race conditions, and memory leaks.

It helps run plain-text reviews, review changes against a chosen Git branch, configure CodeRabbit, and use findings during implementation.

It gives developers a repeatable way to review local or uncommitted changes and connect reviews to GitHub or an AI coding workflow.

coderabbit — Skill for Claude Code by basher83/lunar-claude

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 basher83/lunar-claude --skill coderabbit

Clone the repo

git clone --depth 1 https://github.com/basher83/lunar-claude

Made for: Claude Code.

Or install claude-dev-sandbox, the plugin that ships this one along with the rest of its 2 skills, 1 command.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/basher83/lunar-claude/coderabbit/github.svg)](https://agentmods.dev/skills/basher83/lunar-claude/coderabbit)

Your own site

<a href="https://agentmods.dev/skills/basher83/lunar-claude/coderabbit"><img src="https://agentmods.dev/badge/skills/basher83/lunar-claude/coderabbit/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/basher83/lunar-claude/coderabbit"><img src="https://agentmods.dev/badge/skills/basher83/lunar-claude/coderabbit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,097 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 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.

Model	Per session	Once invoked
Fable 5.1	$0.00031	$0.01097
Opus 5.5	$0.00012	$0.00439
Sonnet 5.5	$0.00006	$0.00219
Haiku 4.5	$0.00003	$0.00110

Measured 2mo ago against content hash 75aa3149093c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

coderabbit 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 2mo 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/meta/claude-dev-sandbox/skills/coderabbit/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeRabbit

AI code review tool that catches race conditions, memory leaks, and security vulnerabilities. Integrates with Claude Code for autonomous review-and-fix workflows.

Quick Start: Claude Code Integration

Run CodeRabbit as part of your development workflow:

Implement the feature from the spec, then run coderabbit --prompt-only
in the background and fix any issues found.

Key flags for Claude Code:

--prompt-only - Minimal output optimized for AI agents
--plain - Plain text mode (no interactive UI)
--type uncommitted - Review only uncommitted changes

CLI Commands

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

# Authenticate (run once per Claude Code session)
coderabbit auth login

# Review code
coderabbit                          # Interactive mode
coderabbit --plain                  # Plain text output
coderabbit --prompt-only            # AI-optimized output
coderabbit --type uncommitted       # Only uncommitted changes
coderabbit --base develop           # Compare against develop branch

Claude Code Workflow

Recommended prompt pattern:

Please implement [feature] and then run coderabbit --prompt-only,
let it run as long as it needs (run it in the background) and fix any issues.

CodeRabbit reviews take 7-30+ minutes. Run in background and check periodically.

Fix prioritization: Fix critical issues first, ignore nits. Run CodeRabbit again after fixes to verify no new issues introduced. Limit to 2 iterations.

GitHub Commands

Use @coderabbitai in PR comments:

Command	Description
`@coderabbitai review`	Incremental review of new changes
`@coderabbitai full review`	Complete review from scratch
`@coderabbitai pause`	Stop automatic reviews
`@coderabbitai resume`	Restart reviews
`@coderabbitai summary`	Regenerate PR summary
`@coderabbitai generate docstrings`	Generate function docs (Pro)
`@coderabbitai generate unit tests`	Generate tests (Pro)
`@coderabbitai resolve`	Resolve all CR comments
`@coderabbitai configuration`	Show current settings

Read the full file on GitHub · 145 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.

2mo ago First seen · 145 lines · 31 tokens per session scan C 75aa3149093c

Subscribe to this mod's changes

coderabbit is a skill published in the GitHub repository basher83/lunar-claude (23 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 1,097 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.

Code review Security

coderabbit next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
coderabbitbasher83/lunar-claude	Skill	23	today	MIT	C	31	Claude Code
autoreviewopenclaw/clawhub	Skill	9.5k	today	MIT	A	17	Claude Code, Codex
agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills	Skill	2.2k	4d ago	MIT	A	115	Claude Code, Codex
omh-code-reviewrlaope/oh-my-hermes	Skill	5.3k	today	MIT	A	49	Claude Code, Codex
revdiff-planumputun/revdiff	Skill	949	today	MIT	A	84	Claude Code
explore-unknownsdzhng/skills	Skill	1.5k	yesterday	MIT	A	162	Claude Code, Codex
re0-mergeLilMGenius/paperthin	Skill	1.4k	today	MIT	A	51	Claude Code, Codex

coderabbit