Claude Composer
A CLI tool that adds automatic prompt acceptance, toolset configuration, and notifications to Claude Code.
What is Claude Composer?
Claude Composer is a CLI tool that wraps Claude Code to add small enhancements like automatic prompt acceptance, configurable toolsets, and system notifications. It solves the problem of frequent interruptions during AI-assisted coding by streamlining the confirmation process and providing better workflow control.
Developers who regularly use Claude Code for AI-assisted programming and want to reduce manual confirmations and customize their tool usage.
Developers choose Claude Composer because it reduces friction in the Claude Code workflow, offers configurable safety features, and provides greater visibility through notifications—all while maintaining compatibility with existing Claude Code options.
Overview
Claude Composer is a command-line interface wrapper for Claude Code that provides quality-of-life enhancements for developers using AI-assisted coding. It reduces interruptions and offers greater control over the Claude Code experience.
Key Features
- Reduced Interruptions — Automatically accepts confirmation prompts to streamline workflow.
- Tool Management — Configurable toolsets define which tools Claude can use during a session.
- Enhanced Visibility — System notifications keep users informed about Claude Code's status and actions.
- YOLO Mode — A flag to accept all prompts automatically for uninterrupted operation.
- Trusted Roots — Defines trusted parent directories to auto-accept initial trust prompts.
Philosophy
Claude Composer is designed to minimize friction and maximize productivity when using Claude Code, providing sensible defaults and configurable safety nets.
Use Cases
Best For
- Reducing confirmation prompts when using Claude Code
- Configuring which tools Claude can access during coding sessions
- Getting system notifications for Claude Code status updates
- Running Claude Code in uninterrupted 'YOLO' mode
- Defining trusted directories for auto-accepting trust prompts
- Wrapping Claude Code with custom CLI options and flags
Not Ideal For
- Teams requiring actively maintained tools with regular updates and bug fixes
- Environments where system notifications are essential or broken features are unacceptable
- Projects not using Claude Code as the primary AI coding assistant
- Security-conscious setups where automatic prompt acceptance poses too much risk
Pros & Cons
Pros
Automatically accepts confirmation prompts to reduce interruptions, as highlighted in the 'Reduced interruptions' feature, allowing developers to focus on coding without manual confirmations.
Offers configurable toolsets to define which tools Claude can use, enabling customization of the AI-assisted coding experience based on project needs.
Provides a --yolo flag to accept all prompts automatically, ideal for developers who want maximum productivity in trusted environments, though it requires caution.
Defines trusted roots to auto-accept initial trust prompts in specified directories, streamlining setup for frequent project locations.
Cons
The README states the repo has 'graduated' and is no longer used by the author, with recommendations to use alternatives like hooks and permission modes, making it unreliable for long-term projects.
System notifications are marked as 'BROKEN' in the features list, with a note about a future update, indicating current functionality issues that detract from user experience.
Adds a Node.js CLI wrapper on top of Claude Code, requiring installation and configuration that might introduce complexity or compatibility issues compared to using Claude Code directly.
Automatic prompt acceptance in YOLO mode can lead to unintended actions if not carefully managed, as warned in the documentation, posing a trade-off between convenience and safety.
Frequently Asked Questions
Related Projects
SuperpowersAn agentic skills framework & software development methodology that works.
Everything Claude CodeThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Learn Claude CodeBash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
Claude Scientific SkillsTurn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 190,000+ scientists worldwide. 165 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.