coderabbit
CodeRabbit CLI and Configuration
Local-first AI code review: catch issues before they reach the PR. The CodeRabbit CLI (coderabbit, alias cr) reviews working-tree or branch changes locally, so the PR-side review becomes confirmation instead of iteration -- this saves billable PR review rounds (both CodeRabbit's own quota and any Copilot credits). Covers the CLI surface -- local reviews, plus the beta cloud Coding Agent commands -- and .coderabbit.yaml tuning. PR-side mechanics (threads, re-requests, the bot loop) live in the git-pr skill.
Verified against CodeRabbit CLI v0.9.2 (2026-11-01): every subcommand's --help on the official build, hidden subcommands included, compared with the CLI command reference -- still generated from v0.9.1 --help -- and this skill's v0.9.1 notes, since the v0.9.1 binary was not run alongside; the hidden and removed review flags run on a clean tree, usage --agent read, and the v0.9.1 base_branches default exercised in a scratch repository. Also checked: the CLI changelog, which now has a v0.9.1 entry and none for v0.9.2; the agent-mode, cloud-task and review-command pages; and the plans, rate-limit and usage-based add-on pages. Flags are tagged with the version that introduced them. The billed and pushing coderabbit code commands were not exercised; their handling comes from those docs and --help. The cloud-task guide still covers neither the v0.9.1 additions (code archive, code goal, new --goal/--private/--access, resume --interactive) nor v0.9.2's code autofix recover. If coderabbit --version reports something newer, diff --help of each subcommand against this list and read the changelog entries since v0.9.2 before relying on flag details here.
When to Use
- Reviewing local changes -- "review my changes", "run coderabbit", pre-commit/pre-push/pre-PR checks
- Driving a review-fix loop -- run review, fix valid findings, re-run to verify
- Configuring CodeRabbit -- create or tune
.coderabbit.yaml, reduce review noise, disable redundant linters - Checking limits -- rate limits per plan, review budgeting
- Setting up the CLI -- install, auth, updates, headless/CI usage
- Running cloud Coding Agent tasks --
coderabbit code new/resume/push, handing a local session off to the cloud (beta, v0.9.0)