WatchAndyTW

WatchAndyTW/multi-model-team

Plugin Claude Code

Marketplace for the multi-model-team plugin — delegate token-heavy work to local CLI backends with dynamic routing, multi-agent /team fan-out, and a statusline HUD.

WatchAndyTW/multi-model-team

Plugin Claude Code

Delegates token-heavy, self-contained tasks to local CLI backends chosen by task size and type, with credit-exhaustion fallback through the backend chain to native Claude and a glanceable statusline HUD. Routing and shipped backend behavior are configured in config/roster.json; adding a new backend kind requires…

WatchAndyTW/multi-model-team

Instructions file

Claude Code instructions for WatchAndyTW/multi-model-team, covering multi-model-team — project guide for claude, ⚠️ backend invocation quirks, agy (gemini) — needs a tty → runs under node-pty, opencode — no tty, prompt on stdin, and it ignores cwd and codex — no tty needed.

WatchAndyTW/multi-model-team

Agent

Dispatcher for the agy (Gemini) CLI backend — a configurable, equal tool, not a fixed task bucket. WHERE work routes is decided by config/roster.json (routes + tags.txt) and per-subtask /team assignments, not hardcoded here. By the shipped routing config, agy is the default lane for fast, commodity, easily-verifiable…

WatchAndyTW/multi-model-team

Agent

Dispatcher for the codex (OpenAI Codex CLI) backend — a configurable, equal tool, not a fixed task bucket. WHERE work routes is decided by config/roster.json (routes + tags.txt) and per-subtask /team assignments, not hardcoded here. By the shipped routing config, codex is the default lane for code review…

WatchAndyTW/multi-model-team

Agent

Dispatcher for the grok (Grok Build, xAI's harness) CLI backend — a configurable, equal tool, not a fixed task bucket. WHERE work routes is decided by config/roster.json (routes + tags.txt) and per-subtask /team assignments, not hardcoded here. grok runs on WHICHEVER MODEL IS CONFIGURED IN GROK ITSELF (the plugin…

WatchAndyTW/multi-model-team

Agent

Dispatcher for the opencode (OpenCode CLI) backend — a configurable, equal tool, not a fixed task bucket. WHERE work routes is decided by config/roster.json (routes + tags.txt) and per-subtask /team assignments, not hardcoded here. opencode runs on WHICHEVER MODEL THE USER CONFIGURED IN OPENCODE ITSELF (the plugin…

WatchAndyTW/multi-model-team

Command

Set up multi-model-team — create your personal roster at /.claude/mmt-roster.json (seeded from the shipped default) so your tuning survives plugin updates, and print the next steps (roster precedence + statusline HUD).

WatchAndyTW/multi-model-team

Command

Run a question through the multi-model Fusion pipeline — fan it out to a configurable panel of models in parallel (default panel is the user-configurable set from reasoning.panel in roster.json, defaulting to Opus+Sonnet+Gemini; override per-invocation with a spec like "2:gemini,opus,codex,opencode"), have a judge…

WatchAndyTW/multi-model-team

Command

Run a task through the multi-model team pipeline — decompose into role-assigned subtasks, dispatch dependency-aware, verify each result, fix failures in a bounded loop, then synthesize. YOU staff it: a spec like "orch:claude:2;impl:opencode:1,claude:2;review:codex:2" says which backend does which job (oh-my-claudecode…