Files
cline/docs/core-workflows/plan-and-act.mdx
T
0b0ca9b1fa docs: add SDK documentation (#10350)
* docs: add comprehensive SDK documentation as top-level tab

Adds 27 new documentation pages for the Cline SDK (@clinebot/core,
@clinebot/agents, @clinebot/llms, @clinebot/shared) organized into
a dedicated "SDK" tab in the Mintlify docs navigation.

Structure:
- Getting Started: overview, quickstart, examples
- Core Concepts: agents, sessions, tools, streaming/events, extensions,
  hooks, providers/models
- Guides: building an agent, custom tools, writing extensions, permission
  handling, scheduled agents, multi-agent teams, connectors, production
- Architecture: layered stack overview, hub-spoke RPC, package reference
- API Reference: ClineCore, Agent, Gateway, Tools API, Events, Types
- CLI: commands, configuration, connector setup

Removes the old single-page SDK overview (cline-sdk/overview.md) that
documented the previous ACP-based ClineAgent API, and removes its
reference from the Cline CLI navigation group.

* docs: fix SDK docs review feedback

- Change "desktop app" to "JetBrains plugin" in overview (not released yet)
- Rename "Providers & Models" to "Model Providers"
- Rename "Streaming & Events" to "Streaming Events"
- Remove duplicate cli/connectors.mdx (guides/connectors.mdx covers everything)

* docs: add wizard commands, Discord connector, and platform credential details

* feat(docs): create CLI tab with new feature pages and updated reference

- Add CLI as its own top-level tab in docs navigation
- Remove CLI group from Docs tab and SDK tab
- Delete SDK CLI pages (content moved to CLI tab)
- Add new feature pages: connectors, scheduling, MCP servers, agent teams
- Rewrite cli-reference.mdx with all new commands (connect, mcp, schedule,
  rpc, checkpoint, doctor) and new flags (reasoning-effort, thinking,
  sandbox, teams, spawn, tool-enable/disable, autoapprove)
- Update configuration.mdx with new directory structure, env vars
  (CLINE_DATA_DIR, CLINE_RPC_ADDRESS, CLINE_SESSION_BACKEND_MODE,
  CLINE_SANDBOX), and MCP wizard reference

* docs: rename Docs tab to Extension and reorder tabs

Tab order: Extension, CLI, SDK, Kanban, Enterprise, API, Learn

* docs: simplify SDK install to single @clinebot/core package

@clinebot/core re-exports from agents, llms, and shared, so users
only need one install and one import source. Updated all getting-started,
quickstart, examples, and guide pages to import from @clinebot/core.
Concept and reference pages keep individual package imports since they
document those specific packages.

* docs: use @clinebot/sdk as the primary install and import path

@clinebot/sdk is an alias for @clinebot/core that re-exports from all
packages. All user-facing pages (overview, quickstart, examples, guides)
now show npm install @clinebot/sdk and import from @clinebot/sdk.
Architecture and reference pages keep individual package names since
they document the internal package structure.

* docs: rename Extension tab to Cline

* docs: fix packages page and merge duplicate imports

* fix: use getting-started page in CLI tab nav and remove conflicting redirect

* docs: rename CLI Getting Started page title to Overview

* docs: rename cline-cli/ to cli/ and cline-sdk/ to sdk/

Shorter, cleaner URL paths. Updated all internal links across every
doc page and added 44 redirects for old paths so existing URLs
don't break.

* docs: update hub-spoke architecture from gRPC/RPC to WebSockets

- Rewrite hub-spoke.mdx: WebSocket protocol, capability brokerage,
  spoke workers, session participants, hub daemon discovery
- Replace all RPC/gRPC/sidecar references with hub/WebSocket across
  all SDK and CLI docs
- Backend modes: local/hub/remote/auto (was local/rpc/auto)
- Hub command replaces rpc command (cline hub start/stop/status/ensure)
- Default port 25463 (was 4317), log file hub-daemon.log
- Remove @clinebot/rpc and @clinebot/scheduler from architecture docs
  (functionality absorbed into @clinebot/core)
- Update ClineCore reference to remove rpc options
- Add capability brokerage and session participant concepts

* docs: add Ecosystem page to SDK tab

* docs: move Ecosystem page after Guides and fix opening sentence

* docs: rename extensions to plugins across all SDK and CLI docs

- Rename AgentExtension to AgentPlugin in all code examples
- Rename ExtensionAPI to PluginAPI
- Rename extensions.mdx to plugins.mdx, writing-extensions.mdx to writing-plugins.mdx
- Rename all variable names (databaseExtension -> databasePlugin, etc.)
- Rename config field from extensions to plugins
- Update all prose, section headers, and cross-links
- Add redirects for old paths

* clean up attempt 1

* remove deprecated features

* part 1 of large provider changes

* a large pass on workflows

* cli ref updates

* config rewrite

* more concise instsallation and model selection

* provider reorg cont

* update providers

* one step further cleaning up

* kanban finishing clean up

* wip...

* another big cleanup - remove the CLI tabgroup

* sdk tighten up pt1

* more sdk doc tightening

* making more progress

* doc update based on bee latest branch

* nit update on codepaths

* remove learn section

* docs: add plugin install command documentation

Document the new clite plugin install command across CLI reference,
customization plugins page, SDK plugins concept page, and the writing
plugins guide. Cover all three source types (npm, git, local), the
package.json manifest format with cline.plugins field, host-provided
dependency handling, auto-detection logic, and the install directory
structure.

Reference cline/typescript-lsp-plugin as a concrete install example.

* docs: deduplicate plugin install docs

Trim redundant plugin install content from CLI reference, SDK plugins
concept page, and writing-plugins guide. Each now links to the
customization/plugins page as the single source of truth for manifest
format, install commands, and directory layout.

* further simplify the doc

* further clean up

* mark warnings

* docs: rename @clinebot to @cline and clite to cline

SDK packages moved to the @cline npm org. Update all docs references
to use @cline/sdk, @cline/agents, @cline/core, @cline/shared, @cline/llms
and the cline CLI binary name.

* docs: streamline SDK docs with example references (#10617)

* docs: streamline SDK docs with example references and @cline/sdk imports

Replace large standalone code blobs in SDK docs with references to
working examples in the SDK repository. Users can now clone and run
real code instead of copy-pasting from docs.

- Update all imports from @cline/agents, @cline/core, @cline/shared
  to @cline/sdk (the public-facing package)
- Fix model IDs from claude-sonnet-4-6 to claude-sonnet-4-20250514
- Quickstart: trim duplicate code patterns, add cards linking to
  cli-agent, code-review-bot, multi-agent, desktop-app examples
- Overview: add examples table with difficulty progression, update
  install instructions to use @cline/sdk
- Building an Agent: rewrite as a walkthrough of the code-review-bot
  example rather than inline code blobs across 4 separate files
- Creating Custom Tools: rewrite to use createTool with zod, add
  completion tools section, reference working examples
- Tools: show createTool with zod as primary pattern
- Events: reference multi-agent example for streaming UI pattern
- Architecture: update install to @cline/sdk

* fix: use claude-sonnet-4-6 model ID across all SDK docs

* remove connector page from sdk

* small reordering

* clean up sdk app and plugin examples

---------

Co-authored-by: Renee Huang <renee@cline.bot>

* remove features/connectors

* doc revisions

* fix references after folder change

* docs: fix SDK review feedback after rebase

* docs: address Greptile SDK review feedback

* docs: move TUI page under CLI nav

* docs: restore TUI page placement

---------

Co-authored-by: Renee Huang <renee@cline.bot>
Co-authored-by: John Simone <john@cline.bot>
Co-authored-by: Arafatkatze <arafat.da.khan@gmail.com>
2026-05-12 16:55:33 -07:00

121 lines
5.9 KiB
Plaintext

---
title: "Plan & Act Mode"
sidebarTitle: "Plan & Act Mode"
description: "Think first, then build. Cline's dual-mode system for structured development."
---
Plan & Act modes separate thinking from doing. Plan mode lets you explore and strategize without changing files. Act mode executes against your plan.
<Tip>
**New to Plan & Act?** Watch [Plan & Act Deep Dive](https://youtu.be/b7o6URFPp64) to see it in action.
</Tip>
## Plan Mode
Plan mode is where you and Cline figure out what you're building and how. In this mode, Cline can read your codebase, run searches, and discuss strategy, but cannot modify any files or execute commands.
This constraint is intentional. It keeps the conversation focused on understanding and planning, without the distraction of implementation details. You can explore freely, ask questions, and iterate on the approach before committing to changes.
Use Plan mode to:
- Explore unfamiliar codebases before making changes
- Discuss architecture decisions and tradeoffs
- Identify edge cases and potential issues upfront
- Create a clear implementation strategy
- Review code and understand complex workflows
## Act Mode
Once you have a plan, switch to Act mode. Cline retains the full context from your planning session and can now modify files, run commands, and execute your strategy.
The conversation history carries over when you switch modes. Cline remembers everything you discussed in Plan mode, so you don't need to repeat yourself. This makes the transition seamless.
<Note>
While you can start directly in Act mode, planning first is highly recommended. The planning phase intentionally builds context that Cline needs to implement changes effectively. Without it, Cline may lack the understanding required to make the right decisions.
</Note>
## Typical Workflow
1. Start in Plan mode and describe what you want to build
2. Let Cline explore relevant files and understand the codebase
3. Discuss the approach, considering edge cases and potential issues
4. When confident in the plan, switch to Act mode
5. Cline implements the solution based on your planning session
For complex projects, you may cycle between modes multiple times. Return to Plan mode when you hit unexpected complexity or need to rethink the approach, then switch back to Act mode to continue implementation.
## When to Use Each Mode
| Scenario | Recommended Mode |
|----------|-----------------|
| Starting new features where the approach isn't obvious | Plan |
| Debugging tricky issues where you're unsure what's wrong | Plan |
| Making architectural decisions affecting multiple files | Plan |
| Understanding complex workflows before modifying them | Plan |
| Code review and security analysis | Plan |
| Learning a new codebase | Plan |
| Implementing a solution you've already planned | Act |
| Making routine changes with a clear approach | Act |
| Following established patterns in the codebase | Act |
| Running tests and making adjustments | Act |
| Quick fixes where the solution is obvious | Act |
## Using Different Models for Each Mode
You can configure separate models for Plan and Act modes. This is useful when you want to use a stronger reasoning model for planning and a faster model for implementation.
To enable this:
1. Open Cline Settings
2. Enable "Use different models for Plan and Act"
3. Select your preferred model for each mode
When enabled, switching between Plan and Act mode automatically switches to the configured model for that mode. Your model selection is preserved when you switch back.
**Example configurations:**
| Use Case | Plan Mode | Act Mode |
|----------|-----------|----------|
| Cost optimization | GLM 4.6 | Grok Code Fast |
| Maximum quality | Claude Opus | Claude Sonnet |
| Speed-focused | Gemini 3 Flash | Cerebras |
## Using `/deep-planning`
For complex tasks that need thorough analysis, use the `/deep-planning` slash command. This triggers an extended planning session where Cline:
1. Explores the codebase systematically
2. Identifies all affected files and dependencies
3. Creates a detailed implementation plan
4. Asks clarifying questions before proceeding
The deep planning prompt is optimized for each model family, so it adapts to the strengths of whatever model you're using. See [/deep-planning](/core-workflows/using-commands#deep-planning) for more details.
## Choosing the Right Approach by Task Size
### Small tasks: Act mode only
For quick fixes like typos, simple bug fixes, or following established patterns, start directly in Act mode. Planning adds overhead when the solution is obvious.
**Examples:** Fix a typo, add a missing import, update a config value, rename a variable.
### Medium tasks: Plan → Act
For most development work, start in Plan mode to understand the scope and approach, then switch to Act mode to implement. This is the sweet spot for features that touch a few files and have some complexity.
**Examples:** Add a new API endpoint, implement a UI component, fix a bug that requires investigation, refactor a single module.
### Large tasks: Use `/deep-planning`
For complex features that span multiple files, require architectural decisions, or will take multiple sessions to complete, use the `/deep-planning` slash command. This creates a detailed implementation plan that Cline can reference throughout the work.
**Examples:** Add a new feature across frontend and backend, major refactoring across the codebase, implementing a new system or integration, multi-step migrations.
## Tips
- Have Cline write a markdown file summarizing the plan for future reference
- Use [file mentions](/core-workflows/working-with-files) to point Cline at relevant files during planning
- Switch back to Plan mode when encountering unexpected complexity rather than pushing through
- Enable [Checkpoints](/core-workflows/checkpoints) before Act mode so you can roll back if needed
- For large tasks, ask Cline to create a todo list during planning that you can track in Act mode