Why CC GUI Is the Ideal Companion for Claude Code and Codex in IntelliJ IDEA

CC GUI Overview

CC GUI (formerly Claude Code GUI) is an MIT‑licensed, open‑source JetBrains plugin that embeds Claude Code and Codex CLI capabilities into a single IDEA panel. It provides a visual workbench rather than a simple sidebar chat.

Switch between Claude Code and Codex without changing plugins.

Use @file to reference files, send image descriptions, and roll back conversations, simplifying context provision compared to manual CLI.

Diff results appear directly in IDEA’s Diff panel with clickable line navigation.

History search, favorites, export, and token‑cost statistics show where usage costs are incurred.

Built‑in slash commands and optional MCP server extensions.

Comparison with Official ACP

Core Positioning: ACP runs the agent inside the IDE; CC GUI provides a full visual workbench.

Key Capabilities: ACP offers diff view and context sharing; CC GUI adds session management, image input, Skill system, and MCP support.

Target Users: ACP suits heavy CLI users; CC GUI targets users who want to complete tasks entirely within the IDE.

Trade‑off: ACP is lightweight and CLI‑centric; CC GUI is more complete and GUI‑centric.

Both can be installed simultaneously and switched according to the scenario.

Three‑Minute Installation

Install the plugin via Settings → Plugins, search for “CC GUI”, and install the version with the highest download count (≈385.6k downloads).

Configure a provider using one of four methods:

Create an API key in the Anthropic Console (separate from Claude.ai Pro/Max subscription).

Import an existing endpoint from the local ~/.claude/settings.json file.

Use cc-switch, a community provider manager.

Specify a custom third‑party endpoint (convenient for users in China).

Start a conversation from the right‑hand panel, e.g., “Analyze the current project structure.”

/plan Mode – Architecture First

In /plan mode the AI acts as an architect, generating a detailed plan without modifying code. Example prompt: /plan 设计下银联的接入方案 The AI scans the project, reads relevant classes (e.g., PaymentService), extracts key points from payment documentation, and returns a review‑ready plan covering:

Files to modify

New classes to add

Required SDK dependencies

Where to place signatures and encryption

Callback and async notification handling

After the plan is approved, switch to /agent to let the AI apply the changes.

Token Cost Statistics

Simple chat (5 rounds): ~15K tokens

Code review (~100 lines): ~25K tokens /plan for a medium project: ~40K tokens

AI Commit generates Conventional Commits from staged diffs, accelerating commit creation by about five times. AI Review runs a diff before a commit or PR, flagging boundary conditions, null pointers, potential infinite loops, and naming issues.

MCP Server Configuration

Enter the server address, headers, and authentication once; the same mcp.json works for Claude Desktop and Cursor. Installing the Chrome DevTools MCP extension enables the agent to invoke Chrome for front‑end testing that requires a logged‑in session.

Comparison with Qoder and CodeBuddy

Nature: CC GUI is a GUI shell for CLI agents; Qoder and CodeBuddy are standalone AI coding agents.

Open‑source: CC GUI is MIT‑licensed; Qoder and CodeBuddy are closed‑source.

Model: CC GUI uses Claude + Codex + custom models; the others use built‑in models.

Entry barrier: CC GUI requires a Claude/Codex subscription; Qoder offers a free tier; CodeBuddy provides a free personal tier.

Strength: CC GUI reuses existing subscriptions and is community‑driven; Qoder is deeply optimized for the Java ecosystem; CodeBuddy integrates well with the Tencent ecosystem.

All three can be installed together without conflict.

Limitations

The quality of context supplied to the AI matters; misuse of @file leads to poor results.

Clear definition of project boundaries is required because the AI lacks business‑logic awareness.

Effective use depends on the user’s ability to review AI‑generated code; generation is easy, review is hard.

Suggested Starter Tasks

Adding unit tests

Generating boilerplate code

Outlining module logic

Converting screenshots to initial code

Project Repository

https://github.com/zhukunpenglinyutong/jetbrains-cc-gui