What problem does it solve? Delegating multi-step coding work to an autonomous agent usually locks you into a single model vendor. This Skill wraps the OpenHands CLI so you can run batch, one-shot coding tasks through any LiteLLM-supported provider (OpenAI, Anthropic, OpenRouter, DeepSeek, Ollama, vLLM) directly from the terminal tool. ## Core Features & Use Cases - Headless Task Delegation: Run one-shot coding tasks with --headless --json --override-with-envs --exit-without-confirmation and parse the JSONL event stream. - Model-Agnostic Configuration: Select any LiteLLM model slug via LLM_MODEL, LLM_API_KEY, and LLM_BASE_URL environment variables. - Conversation Resumption: Continue prior runs with --resume <dashed-uuid> for iterative multi-turn coding sessions. - Use Case: Ask the agent to add error handling to all API calls in src/ of a project; OpenHands edits files and runs shell commands autonomously, returning a structured JSON event log. ## Quick Start Ask the agent to delegate a coding task to OpenHands, for example: use OpenHands headless mode with an OpenRouter model to add error handling to all API calls in the src directory of my project.
