weave-architecturelisted

# Weave Architecture Run an architecture/scaffolding task across multiple AI models (Claude, Antigravity, GPT), each working in its own **isolated git worktree**. After all models complete, **cherry-pick the best conventions, skills, agents, and scaffolding from each model** into a single, coherent architecture. Unlike the `weave-execute` skill (which targets feature implementation), this command focuses on **project-level documentation, conventions, and structural artifacts**. The architecture goal comes from `$ARGUMENTS`. If no arguments are provided, ask the user what they want scaffolded. --- ## Phase 1: Gather Context **Goal**: Understand the project's existing architecture and conventions. 1. **Read CLAUDE.md / AGENTS.md** if present — existing conventions constrain all outputs. 2. **Scan for existing components**: - Skills (`skills/*/SKILL.md`) - Agents (`agents/*.md`) - Hooks (`hooks/hooks.json`) - MCP servers (`.mcp.json`) - LSP servers (`.lsp.json`) 3. **Determine trunk branch**: ```bash git remote show origin | grep 'HEAD branch' ``` Fall back to `main`, then `master`, if detection fails. 4. **Record the current branch and commit**: ```bash git branch --show-current ``` ```bash git rev-parse HEAD ``` Store these — all worktrees branch from this point. 5. **Capture the architecture goal**: Use `$ARGUMENTS` as the goal. If `$ARGUMENTS` is empty, ask the user. 6. **Explore project structure**: Read files re