huashu-agent-swarmlisted

# Infinite Agent Loop — Multi-Agent Swarm Mode > Inspired by Nicholas Carlini's experiment of using 16 Claude instances to autonomously build a C compiler. > No master agent. Pure git self-organisation. Each agent independently claims tasks, writes code, and pushes. ## Trigger Conditions Use this skill when the user mentions "swarm mode", "multi-agent parallel", "infinite loop", "agent swarm", or "launch swarm". ## Prerequisites - tmux (`brew install tmux`) - Claude CLI (already installed) - A git repository (existing or new) ## Usage Workflow ### Step 1: Describe the Project The user tells me: - Project directory path (must be a git repository) - Project goal and overall description - Initial task list (or let the agents break it down themselves) - Number of agents (default: 8) - Code standards and test commands ### Step 2: Initialise the Project ```bash bash SKILL_DIR/scripts/setup_project.sh <project-directory> ``` This creates the following inside the project: - `AGENT_PROMPT.md` — Generated from a template; I customise it based on user requirements - `TASKS.md` — Initial task checklist - `current_tasks/` — Task claim directory - `agent_logs/` — Logs directory I then customise `AGENT_PROMPT.md` using `references/agent-prompt-template.md`, filling in project-specific details. ### Step 3: Launch the Swarm ```bash bash SKILL_DIR/scripts/start_swarm.sh <number-of-agents> <project-directory> ``` This will: 1. Create a git worktree for each agent (shared `.git