diff --git a/plugins/README.md b/plugins/README.md
index cf4a21ecc5..dc2d2122d8 100644
--- a/plugins/README.md
+++ b/plugins/README.md
@@ -22,6 +22,7 @@ Learn more in the [official plugins documentation](https://docs.claude.com/en/do
 | [hookify](./hookify/) | Easily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or explicit instructions | **Commands:** `/hookify`, `/hookify:list`, `/hookify:configure`, `/hookify:help`<br>**Agent:** `conversation-analyzer` - Analyzes conversations for problematic behaviors<br>**Skill:** `writing-rules` - Guidance on hookify rule syntax |
 | [learning-output-style](./learning-output-style/) | Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style) | **Hook:** SessionStart - Encourages users to write meaningful code (5-10 lines) at decision points while receiving educational insights |
 | [plugin-dev](./plugin-dev/) | Comprehensive toolkit for developing Claude Code plugins with 7 expert skills and AI-assisted creation | **Command:** `/plugin-dev:create-plugin` - 8-phase guided workflow for building plugins<br>**Agents:** `agent-creator`, `plugin-validator`, `skill-reviewer`<br>**Skills:** Hook development, MCP integration, plugin structure, settings, commands, agents, and skill development |
+| [planwith](./planwith/) | Combine /plan and your prompt into a single command | **Command:** `/planwith` - Enter plan mode with your prompt inline, combining `/plan` + prompt into one step |
 | [pr-review-toolkit](./pr-review-toolkit/) | Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification | **Command:** `/pr-review-toolkit:review-pr` - Run with optional review aspects (comments, tests, errors, types, code, simplify, all)<br>**Agents:** `comment-analyzer`, `pr-test-analyzer`, `silent-failure-hunter`, `type-design-analyzer`, `code-reviewer`, `code-simplifier` |
 | [ralph-wiggum](./ralph-wiggum/) | Interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly until completion | **Commands:** `/ralph-loop`, `/cancel-ralph` - Start/stop autonomous iteration loops<br>**Hook:** Stop - Intercepts exit attempts to continue iteration |
 | [security-guidance](./security-guidance/) | Security reminder hook that warns about potential security issues when editing files | **Hook:** PreToolUse - Monitors 9 security patterns including command injection, XSS, eval usage, dangerous HTML, pickle deserialization, and os.system calls |
diff --git a/plugins/planwith/.claude-plugin/plugin.json b/plugins/planwith/.claude-plugin/plugin.json
new file mode 100644
index 0000000000..9a0d9bc8e2
--- /dev/null
+++ b/plugins/planwith/.claude-plugin/plugin.json
@@ -0,0 +1,9 @@
+{
+  "name": "planwith",
+  "description": "Combine /plan and your prompt into a single command",
+  "version": "1.0.0",
+  "author": {
+    "name": "Anthropic",
+    "email": "support@anthropic.com"
+  }
+}
diff --git a/plugins/planwith/README.md b/plugins/planwith/README.md
new file mode 100644
index 0000000000..ac513ba56c
--- /dev/null
+++ b/plugins/planwith/README.md
@@ -0,0 +1,71 @@
+# Planwith Plugin
+
+Combine `/plan` and your prompt into a single command.
+
+## Overview
+
+The Planwith Plugin provides the `/planwith` command, which allows you to enter plan mode and specify your planning task in a single command. Instead of typing `/plan` and then entering your prompt separately, you can combine both into one step.
+
+## Command: `/planwith`
+
+Enters plan mode with your prompt inline.
+
+**Usage:**
+```bash
+/planwith Add user authentication with OAuth
+```
+
+This is equivalent to:
+```bash
+/plan
+# [wait for plan mode to activate]
+Add user authentication with OAuth
+```
+
+**Examples:**
+```bash
+/planwith implement user authentication with OAuth 2.0
+/planwith refactor the database layer to use connection pooling
+/planwith add a dark mode toggle to the settings page
+```
+
+## How it Works
+
+When you invoke `/planwith <prompt>`:
+1. The command calls `EnterPlanMode` to activate plan mode
+2. Your prompt is passed as the planning task
+3. Plan mode proceeds with the standard planning workflow
+
+This gives you the full plan mode experience (read-only restrictions, plan file creation, structured workflow) with the convenience of an inline prompt.
+
+## Best Practices
+
+- **Be specific**: Include context in your prompt
+  - Good: `/planwith add OAuth 2.0 login with Google and GitHub providers`
+  - Less good: `/planwith add login`
+
+- **Let planning complete**: Allow Claude to explore and ask questions
+
+- **Review the plan**: Check the proposed approach before approving implementation
+
+## When to Use
+
+**Use for:**
+- Quick entry into plan mode with a specific task
+- When you already know what you want to plan
+- Reducing the two-step `/plan` + prompt into one step
+
+**Don't use for:**
+- When you want to enter plan mode without a specific task (use `/plan` instead)
+
+## Installation
+
+This plugin is included in the Claude Code repository. The command is automatically available when using Claude Code.
+
+## Author
+
+Anthropic (support@anthropic.com)
+
+## Version
+
+1.0.0
diff --git a/plugins/planwith/commands/planwith.md b/plugins/planwith/commands/planwith.md
new file mode 100644
index 0000000000..5d3bde391c
--- /dev/null
+++ b/plugins/planwith/commands/planwith.md
@@ -0,0 +1,20 @@
+---
+description: Enter plan mode with an inline prompt
+argument-hint: <planning prompt>
+allowed-tools: EnterPlanMode
+---
+
+# Plan With Inline Prompt
+
+Your task: Enter plan mode and then work on the user's request.
+
+## User Request
+
+$ARGUMENTS
+
+## Instructions
+
+1. First, call the `EnterPlanMode` tool to enable plan mode
+2. Once plan mode is enabled, proceed with the user's request above
+
+Do this now - invoke EnterPlanMode first, then work on the planning task.