Development

/coderabbit

Use when reviewing uncommitted changes, preparing PRs, checking for security issues, or verifying code quality. Runs AI code reviews via CLI. Covers code review, PR review, security scan, secrets scan. NOT for: runtime debugging (use debugger), test execution (run tests directly).

$ golems-cli skills install coderabbit

Good

100% best pass rate

8 assertions

3 evals

6 workflows

Updated 2 weeks ago

Fast AI code reviews via CodeRabbit CLI. Free for open source.

Repositories

Works in any git repo. Free tier covers open source repos. For private repos, ensure CodeRabbit is configured in the repo settings.

Quick Commands

cr review --plain           # Human-readable review
cr review --prompt-only     # For AI agents (minimal tokens)
cr review --type uncommitted # Only unstaged changes
cr review --base main       # Compare against main branch

Workflows

Workflow	Use Case
review	Standard code review
verify	Quick verification for Ralph V-* stories
security	Security-focused review
accessibility	A11y audit for UI changes
secrets	Scan for hardcoded secrets/keys
pr-ready	Pre-PR comprehensive check

Full SKILL.md source — includes LLM directives, anti-patterns, and technical instructions stripped from the Overview tab.

Fast AI code reviews via CodeRabbit CLI. Free for open source.

Repositories

Works in any git repo. Free tier covers open source repos. For private repos, ensure CodeRabbit is configured in the repo settings.

Quick Commands

cr review --plain           # Human-readable review
cr review --prompt-only     # For AI agents (minimal tokens)
cr review --type uncommitted # Only unstaged changes
cr review --base main       # Compare against main branch

Workflows

Workflow	Use Case
review	Standard code review
verify	Quick verification for Ralph V-* stories
security	Security-focused review
accessibility	A11y audit for UI changes
secrets	Scan for hardcoded secrets/keys
pr-ready	Pre-PR comprehensive check

Output Modes

Flag	Best For	Token Usage
`--plain`	Humans reading in terminal	High
`--prompt-only`	AI agents (Ralph, Claude)	Low
(default)	Interactive TUI	N/A

Integration with Ralph

For V-* verification stories, CodeRabbit runs FIRST as a fast pre-check:

cr review --prompt-only --type committed - Quick scan
If issues found → Fix before Claude verification
If clean → Proceed to full Claude verification

This reduces Claude API costs and catches obvious issues fast.

Configuration

Optional .coderabbit.yaml in repo root for custom rules:

reviews:
  language: en
  path_filters:
    - "!**/*.test.ts"
    - "!**/node_modules/**"

Requirements

CodeRabbit CLI installed: curl -fsSL https://cli.coderabbit.ai/install.sh | sh
Authenticated: cr auth login
Must run from git repository root

Good

Best Pass Rate

100%

Opus 4.6

Assertions

5 models tested

Avg Cost / Run

$0.1363

across models

Fastest (p50)

2.3s

Haiku 4.5

Behavior Evals

Phase 2 baseline — skill quality on Claude

Behavior Baseline

Opus 4.6

100%8/8

●

Sonnet 4.6

100%8/8

●

Haiku 4.5

38%3/8

○

Adapter Evals

Phase 2C — cross-AI portability

Adapter Portability

Codex

88%7/8

◒

Gemini 2.5

88%7/8

◒

Assertion	Opus 4.6	Sonnet 4.6	Haiku 4.5	Codex	Gemini 2.5	Consensus
runs-cr-review-command						5/5
surfaces-findings-with-severity						4/5
does-not-auto-approve						3/5
does-not-skip-review						4/5
explains-why-review-matters						4/5
runs-review-despite-pushback						4/5
uses-secrets-scan-mode						4/5
recommends-rotation-if-found						5/5

Token Usage

Opus 4.6

12,425

Sonnet 4.6

5,269

Haiku 4.5

4,236

Codex

5,888

Gemini 2.5

6,480

Input tokensOutput tokens

Cost per Run

Opus 4.6

$0.5220

Sonnet 4.6

$0.0421

Haiku 4.5

$0.0030

Codex

$0.0764

Gemini 2.5

$0.0378

Model	Input Tokens	Output Tokens	Cost / Run	Cost / 1K Runs
Opus 4.6	6,832	5,593	$0.5220	$522.00
Sonnet 4.6	3,074	2,195	$0.0421	$42.10
Haiku 4.5	2,258	1,978	$0.0030	$3.00
Codex	2,758	3,130	$0.0764	$76.40
Gemini 2.5	3,604	2,876	$0.0378	$37.80

Response Time (p50)

Haiku 4.5

2.3s

Codex

2.5s

Sonnet 4.6

3.2s

Gemini 2.5

4.6s

Opus 4.6

10.2s

Response Time (p95)

Codex

3.9s

Haiku 4.5

4.3s

Sonnet 4.6

5.4s

Gemini 2.5

8.5s

Opus 4.6

14.3s

Model	p50	p95	Overhead
Opus 4.6	10.2s	14.3s	+41%
Sonnet 4.6	3.2s	5.4s	+70%
Haiku 4.5	2.3s	4.3s	+87%
Codex	2.5s	3.9s	+57%
Gemini 2.5	4.6s	8.5s	+84%

Last evaluated: 2026-03-12 · Data is generated from skill assertions (real cross-model benchmarks coming soon)

Workflows

/coderabbit:secrets/coderabbit:pr-ready/coderabbit:accessibility/coderabbit:verify/coderabbit:review/coderabbit:security