colinmollenhour

Shell out to claude CLI.

Run a multi-agent debate to compare options and converge on a decision.

Run the same task with multiple agents for reviews, critiques, or model comparison.

Autonomous large-task delivery agent. Use for long-running coding work that should go from objective or plan to implemented code, review fixes, PR/MR, and green CI with minimal human-in-the-loop gates.

Manage ClickUp tasks.

Generate a project template for Coolify

Run a multi-agent debate to compare options and converge on a decision.

Run the same task with multiple agents for reviews, critiques, or model comparison.

Manage OpenCode sessions from the CLI using occtl. Use when the user wants to list sessions, read messages, watch sessions, send prompts, answer permission requests, inspect todos/status/diffs, abort sessions, create worktrees, or orchestrate autonomous OpenCode work.

Run advanced agentic Claude Code invocations via `botctl prompt` (observable tmux TUI, YOLO-safe blockers, transcript-backed final answer). Use when you need a one-shot or multi-file Claude run that keeps a real interactive session (not `claude -p`), when launching parallel Claude participants for reviews or many-brain workflows, when a long source packet must be staged reliably, or when the user mentions botctl prompt, TUI-backed Claude, or isolated Claude sessions with --session-id.