coderabbit-cli

coderabbit-cli is a skill for Claude Code, Codex from sailingnaturali/claude-skills. It costs 115 tokens per session (1,431 once invoked), scanned A, original, MIT.

A command-line tool for sending your local code changes to CodeRabbit, an online code-review service, before you open a pull request. It prints CodeRabbit’s review findings in your terminal.

In plain words
What is it for?
Use it as a pre-pull-request review step, check whether the CLI is installed and ready, and run reviews on the intended code difference.
Why use it?
It lets you find issues before asking others to review the pull request. It also makes clear that your code changes and any extra files sent for context leave your computer.

Skill for Claude CodeCodex

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 skills/sailingnaturali/claude-skills/coderabbit-cli
Any agent
npx skills add sailingnaturali/claude-skills --skill coderabbit-cli
Clone the repo
git clone --depth 1 https://github.com/sailingnaturali/claude-skills

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 coderabbit-cli

README.md
[![agentmods](https://agentmods.dev/badge/skills/sailingnaturali/claude-skills/coderabbit-cli.svg)](https://agentmods.dev/skills/sailingnaturali/claude-skills/coderabbit-cli)
Your own site
<a href="https://agentmods.dev/skills/sailingnaturali/claude-skills/coderabbit-cli"><img src="https://agentmods.dev/badge/skills/sailingnaturali/claude-skills/coderabbit-cli.svg" alt="Measured on agentmods" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,431 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00115 $0.01431
Opus 5 $0.00057 $0.00715
Sonnet 5 $0.00023 $0.00286
Haiku 4.5 $0.00012 $0.00143

Measured 4d ago against content hash 1a971f64f35b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coderabbit-cli 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.

coderabbit-cli/skills/coderabbit-cli/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Driving the CodeRabbit CLI (cr) as a pre-PR review gate

The CodeRabbit CLI (cr) sends a repo's local diff to CodeRabbit's cloud review service and prints the findings in the terminal — an independent reviewer you can run before a PR exists. Reviews are rate-limited, so what matters is the three mechanics below: get one wrong and the run either judges the wrong diff or its output is gone. For the full command and flag reference, use CodeRabbit's CLI docs — this skill deliberately carries only what those docs don't.

Prerequisites — and what leaves the machine

  • Requires the cr CLI installed and authenticated against a CodeRabbit account — sign in with cr auth login (0.7.1's own --help additionally offers cr auth login --agent for an agent-driven OAuth flow). Rate limits and pricing are plan-dependent — check before wiring it into a workflow.
  • The diff is uploaded to CodeRabbit's cloud for analysis. Code leaves the machine. For a private or proprietary repo, make that call knowingly (policy, NDA, licensing) — and note that files passed as extra context via -c/--config are shared too.
  • cr doctor checks the installation and review readiness; cr --version tells you whether the claims below still apply.

Run your own audit first

A rate-limited cloud review is the second opinion, not the first. Before spending one, review the diff yourself with fresh eyes — ideally dispatch a subagent that didn't write the change to read git diff <base>...HEAD cold and try to prove it wrong — fix what survives verification, and re-run tests. Then cr reviews the corrected change instead of re-reporting what you could have caught locally.

The three mechanics that decide whether a run counts

1. Commit first — a dirty-tree review judges the wrong diff

cr review --committed reviews only committed changes. Running a review over a dirty tree is how you get a clean-looking "no findings" that never covered the work you just did. The reliable agent flow: commit, then review with --committed — what was reviewed is exactly what ships.

Read the full file on GitHub · 100 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 · 100 lines · 115 tokens per session scan A 1a971f64f35b

Subscribe to this mod's changes

coderabbit-cli is a skill published in the GitHub repository sailingnaturali/claude-skills (2 stars, last pushed 19d ago), licensed MIT. It adds 115 tokens to every session and 1,431 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens