This feature is currently in open beta. We are actively improving it based on
your feedback. If you encounter any issues or have suggestions, please share
them on our Discord community or reach out to
our support team.
Overview
CodeRabbit Issue Planner analyzes your issues, specifications, and project codebase to generate Coding Plans you can handoff to any coding agent or IDE copilot. Because CodeRabbit deeply understands your codebase through continuous analysis, each plan is tailored to your architecture and conventions, covering codebase research, step-by-step tasks, and agent-ready prompts.Supported Issue Trackers
CodeRabbit Issue Planner supports four issue trackers. See the platform-specific guides for setup and configuration details.Planning
The recommended way to use Issue Planner is to enable auto-planning on your platform so that Coding Plans are generated automatically whenever it matches the conditions you configure. Refer to the platform-specific guides above to set up auto-planning. To generate a plan on demand, comment@coderabbitai plan on any issue.
Viewing and Refining Plans
How you view and refine Coding Plans depends on your platform:GitHub & GitLab
The full Coding Plan is posted as a comment directly on the issue. Reply to
the plan comment to refine details, challenge design choices, or request
changes.
Jira & Linear
The Coding Plan is available in the CodeRabbit web app. Use the chat
panel on the right to iterate on the plan before handing off the finalized prompts to
your coding agent.
Plan Structure
Each Coding Plan contains the following sections:| Section | Description |
|---|---|
| Summary | 2-3 sentence overview of the implementation approach |
| Research | Deep codebase analysis leveraging CodeRabbitās project knowledge, identifying relevant files, patterns, dependencies, and architectural decisions specific to the project |
| Design Choices | Decisions made during planning with rationale for each |
| Phases | Logical chunks of work that should be done together |
| Tasks | Individual tasks within each phase |
| Agent Prompt | Machine-readable instructions for coding agents (per phase and combined) |
Chatting about Your Plan
Chat with CodeRabbit to ask questions, request changes to specific tasks or phases, challenge design choices, or get clarification on implementation details. CodeRabbit responds and updates the plan accordingly. See the platform-specific guides for details on how chatting works on your platform.Re-planning
Provide feedback and regenerate your plan to incorporate changes. See the platform-specific guides for details on the re-planning workflow.Handing Off to a Coding Agent
Once youāre satisfied with a Coding Plan, copy the agentic prompts and paste them into your preferred coding agent (Claude Code, Cursor, GitHub Copilot, etc.). Depending on the platform, you can also handoff directly through the CodeRabbit IDE extension or let your coding agent fetch the plan via MCP. See the platform-specific guides for handoff options.Frequently Asked Questions
How long does plan generation take?
Plan generation typically takes between 5 and 10 minutes depending on the complexity of the issue and codebase.Can I regenerate a plan?
Yes. You can regenerate a plan on all supported platforms. See your platformās guide for specific instructions.Can multiple people work on the same plan?
Yes. Anyone in your organization can view plans, discuss them with CodeRabbit, and trigger re-plans.How is CodeRabbit different from using ChatGPT or coding agents for planning?
Any AI agent or LLM can write an implementation plan. The difference is in the quality and context behind that plan:- Deeper codebase understanding - When an AI agent generates a plan, it typically reviews only a handful of files. CodeRabbitās Coding Plans are grounded in deep codebase understanding through continuous code analysis and an extensive knowledge base. This means plans reference the right files, follow your established patterns, and integrate seamlessly with your existing code.
- Access to issues and better context - CodeRabbit works with issue trackers, surfacing relevant related issues, even when the assigned engineer isnāt aware of them. This broader context ensures plans account for ongoing work, previous decisions, and the full scope of your projectās direction.
- Collaborative review - CodeRabbit plans are available for review by other engineers and product owners. Team members can discuss, challenge design choices, and refine plans together before implementation begins.
- Accountability and history - Every plan version is preserved. You can track what was planned, when it was planned, and why decisions were made. This audit trail provides accountability and helps teams understand the evolution of features over time.