Official marketplace for YOLO Mode plugins
npx claudepluginhub nbiish/yolo-modeAn autonomous agent loop plugin for Claude Code that implements the Ralph Loop pattern. It takes a prompt, plans tasks, and iteratively executes them using fresh contexts until completion.
nbiish
Transform Claude Code into a self-driving developer
YOLO Mode implements the Ralph Loop pattern for autonomous agentic coding. It plans, executes, and verifies complex tasks with minimal human intervention while maintaining context hygiene through fresh context windows.
YOLO_PLAN.md to track progresstts-cli--dangerously-skip-permissions for maximum autonomy# Add the marketplace
claude plugin marketplace add https://github.com/nbiish/yolo-mode
# Install the plugin
claude plugin install yolo-mode@yolo-marketplace
Use in Claude Code:
/yolo "Refactor the authentication system"
/yolo "Audit security" --agent opencode
/yolo-tts "Build a React component library" # With voice feedback
# Install from source
git clone https://github.com/nbiish/yolo-mode.git
cd yolo-mode
pip install -e .
# Run anywhere
yolo-mode "Your goal here" --tts
yolo-mode "Your goal here" --agent opencode
/yolo "Create a REST API with FastAPI"
/yolo-tts "Write unit tests for the utils module"
# Basic usage (defaults to Claude Code)
yolo-mode "Implement user authentication"
# With OpenCode
yolo-mode "Refactor database schema" --agent opencode
# With Google Gemini
yolo-mode "Generate documentation" --agent gemini
# With Mini-SWE-Agent (NEW in v0.2.0)
yolo-mode "Write a sudoku game" --agent mini
/yolo-mini "Create unit tests for utils.py" # Slash command
# With voice feedback
yolo-mode "Build a dashboard" --tts
# Complex multi-step goal
yolo-mode "Set up a CI/CD pipeline with GitHub Actions, Docker, and AWS deployment"
npm install -g @anthropic-ai/claude-codebrew install opencodepip install mini-swe-agent (NEW in v0.2.0)To achieve true autonomous operation without permission prompts for every tool use, you MUST start Claude Code with the following flag:
claude --dangerously-skip-permissions
If you do not use this flag, the "YOLO Mode" loop will pause and wait for your approval whenever the agent tries to use a tool (Bash, File Edit, etc.), defeating the purpose of autonomous operation.
Recommendations:
YOLO_PLAN.md before executionUser Goal
↓
[Planner] Creates YOLO_PLAN.md with task checklist
↓
[Executor Loop] While tasks remain:
- Reads next pending task
- Spawns fresh Claude instance
- Executes task autonomously
- Updates plan file
↓
[Feedback] Ask user for additional tasks
yolo-mode/
├── .claude-plugin/ # Plugin metadata
├── commands/ # Slash command definitions
│ ├── yolo.md
│ └── yolo-tts.md
├── yolo_mode/ # Python package
│ └── scripts/
│ └── yolo_loop.py
├── llms.txt/ # AI documentation
└── setup.py # CLI packaging
/yolo-mini command, updated agent registrycommands/*.md structureSee CONTRIBUTING.md for guidelines.
MIT License - See LICENSE file.