Plan Mode prevents unintentional file modifications, letting you think through solutions and build confidence before committing to action. The core principle is understand before you change, giving you a research-first approach that prevents costly mistakes and creates better architectural decisions.

Chat Mode

Learn and discuss without changing code.Mental Model: Talking to a knowledgeable colleague Best For: Explaining concepts, comparing approaches, code review discussions.

Plan Mode

Safely explore and plan with read-only tools.Mental Model: Architect surveying before renovation Best For: Understanding a codebase, bug investigation, planning implementations.

Agent Mode

Make actual changes with full tool access.Mental Model: Contractor executing approved blueprints Best For: Implementing features, fixing bugs, running tests and commands.

What Are the Use Cases for Plan Mode

Plan Mode excels in four key scenarios where understanding before acting prevents expensive mistakes:

Codebase Exploration

Navigate unfamiliar systems and trace data flows without modification risk.See exploration prompts →

Implementation Planning

Map dependencies and sequence complex changes before execution.
See planning prompts →

Issue Investigation

Debug systematically by tracing execution paths and analyzing root causes.See debugging prompts →

Architecture Analysis

Assess system health, identify bottlenecks, and plan improvements.See analysis prompts →

What Are the Best Practices for Plan Mode?

How to Plan Faster

  1. Scope your requests: Focus analysis on the user authentication module only, ignore the admin features
  2. Use targeted context: Analyze @Files and its direct imports for security issues

How to Create Higher Quality Plans

  1. Provide business context: This feature needs to handle Black Friday traffic (10x normal load). Plan accordingly.
  2. Share technical constraints: We're on AWS with strict security requirements. Plan a file upload system that meets SOC2 compliance.
  3. Ask for risk analysis: What could go wrong with this database migration? Plan rollback procedures.
  4. Request multiple perspectives: Show me 3 different approaches to implementing caching in this API, with pros and cons for each.

How to Enable Plan Mode

You can switch to Plan in the mode selector below the chat input box. How to select plan mode

What Tools Are Available in Plan Mode?

ToolAvailableDescription
File/directory readingBrowse and read any file or folder in your workspace
Grep/glob searchSearch for patterns across files and directories
Repository structure analysisUnderstand codebase organization and dependencies
Git history/diffsReview commits, branches, and changes
Web content fetchingAccess external documentation and resources
External API accessRead-only calls to external services
MCP toolsModel Context Protocol integrations
Database schema examinationAnalyze database structure (read-only)
File creation/editingCreating or modifying files
Terminal command executionRunning shell commands
System modificationsChanging system settings or configurations
Package installationInstalling dependencies or packages
Git commits/pushesMaking changes to version control
Database modificationsAltering database data or structure

How Context Integration Works in Plan Mode

Context is the foundation of effective planning. Without proper context, AI models fall back on generic patterns, leading to plans that don’t fit your specific system. Continue’s context system transforms broad suggestions into actionable strategies:
Context TypeUsageBest For
Highlighted Codecmd/ctrl + L (VS Code) or cmd/ctrl + J (JetBrains)Component-specific analysis
Active Fileopt/alt + enter when sending requestCurrent file context
@Files@Files package.json tsconfig.jsonSpecific file analysis
@Terminal@TerminalDebugging with output
@Git Diff@Git DiffChange impact analysis
After highlighting a React component: Analyze this component for performance bottlenecks and plan optimization strategies.
@Files docker-compose.yml Dockerfile - Review our containerization setup and suggest improvements for production deployment.
@Folder src/api - Evaluate our REST API design patterns and identify opportunities for better consistency.
@Codebase - Plan a strategy to migrate this web app to also support mobile using React Native.

Prompt Library

Codebase Exploration

Data Flow Analysis: Help me understand how state management works in this Redux app. Map out the data flow from actions to components.Microservices Communication: Analyze how our microservices communicate and identify potential bottlenecks in service-to-service calls.Database Schema Review: Examine the database schema and relationships to understand how user data is structured and accessed.
System Mapping: Map out this legacy codebase architecture. What are the main components and how do they communicate?Technical Debt Assessment: Analyze this codebase for technical debt hotspots and maintenance pain points.Modernization Planning: Assess this legacy system and recommend modernization opportunities that provide the highest impact with lowest risk.

Implementation Planning

Cloud Migration: Plan a migration from on-premise servers to AWS, considering our current Node.js application architecture.Package Manager Migration: Create a plan to migrate from npm to pnpm, analyzing dependencies and potential breaking changes.Monorepo Conversion: Plan how to convert our multiple repositories into a single monorepo using Nx or Lerna.
Service Extraction: Plan a refactor to extract shared authentication logic into a reusable service across these microservices.Payment Integration: We need to add Stripe payments to this e-commerce app. Plan the integration considering our current architecture.API Migration: @Codebase - Plan a migration from REST to GraphQL across our entire API.

Issue Investigation

Dashboard Performance: Users report slow page loads on the dashboard. Investigate performance bottlenecks in the @Files and related components.API Optimization: Plan a performance optimization strategy for this Node.js API, focusing on database queries and caching.Bundle Analysis: Analyze this React app for performance bottlenecks. What are the most expensive operations?
Race Condition Analysis: Users occasionally see stale data in the UI. Investigate potential race conditions in our async data fetching.Production Incidents: @Git Diff We're seeing 500 errors in production. Analyze recent changes and identify what might be causing the issue.Deployment Issues: Our staging environment works fine, but production deployments fail. Analyze environment differences.

Architecture Analysis

Traffic Planning: Analyze this @codebase architecture and identify potential bottlenecks for handling 10x more traffic.CDN Implementation: Plan a CDN strategy for our global user base, considering asset optimization and edge caching.Caching Strategy: Show me 3 different approaches to implementing caching in this API, with pros and cons for each.
Security Audit: Audit this API for security vulnerabilities, focusing on authentication, authorization, and data validation.Threat Modeling: Model potential security threats for this user registration flow and plan mitigation strategies.Compliance Planning: Plan GDPR compliance implementation for this user data handling system.

How to Transition From Plan to Execution

When to Transition to Agent Mode

Move to Agent Mode when you have: Clear understanding of the current system
Detailed implementation plan with specific steps
Risk assessment and mitigation strategies
Team approval (if required)
Success criteria defined

Key Takeaways

The three-mode system—Chat for learning, Plan for strategy, and Agent for execution—provides a complete development workflow that scales from simple bug fixes to complex system architecture. Remember:
  • Choose the right mode for each task
  • Start broad, then focus your planning sessions for better results
  • Transition to Agent mode with clear execution steps
The best code is planned code.