maw-execute-tasklisted

Adversarial multi-agent development pipeline. Use when the user says "take the next task", "work through tasks", "run the pipeline", or wants to implement a task from the task board with full planning, review, implementation, and QA cycle. Supports flags: --worktree (force worktree mode), --no-worktree (force branch-only mode). These override the saved setting for the current run only. Supports positional arg: a task number or ID (e.g. `/maw-execute-task 3`, `/maw-execute-task TASK-003`) to run a specific task out of priority order instead of picking the highest-priority pending task. Model-invocation is guarded: if invoked by the model rather than an explicit user command, the auto-invoke guard applies (see Invocation guard) — confirmation is required before any state change unless the user disabled the guard in maw/settings.json.
pockerhead/maw · ★ 4 · Code & Development · score 67

Install: claude install-skill pockerhead/maw

# Adversarial Multi-Agent Development ## Settings Pipeline settings are stored in `maw/settings.json`. The orchestrator checks this file at the start of every run. **Schema v2** (providers are first-class): ```json { "worktree_mode": "always", "default_provider": "host", "spawn_timeout_min": 30, "allow_unverified_profile": false, "providers": { "claude": { "default_model": "sonnet", "default_effort": "medium" }, "codex": { "default_model": "gpt-5.6-sol", "default_effort": "medium" } }, "agents": { "code-reviewer": { "provider": "codex", "model": "gpt-5.6-sol", "effort": "xhigh" }, "planner": { "model": "opus" } } } ``` Agent names everywhere are the agent file stems: `clarifier`, `premise-challenge`, `planner`, `plan-reviewer-1`, `plan-reviewer-2`, `implementer`, `code-reviewer`, `fixer`, `qa`. - `worktree_mode`: `always` — always create a git worktree for the task (default if user picks this); `never` — work on a feature branch directly, no worktree; `ask` — ask the user each time before starting a task - `default_provider`: `"host"` (literal, default) = the harness this orchestrator is running in; or pin to `"claude"` / `"codex"`. - `providers.<p>.default_model` / `default_effort`: per-provider defaults, used whenever an agent resolves to provider `<p>` without an explicit model/effort of its own. - `agents.<name>`: an **atomic partial profile** for one agent — any of `provider`, `model`, `effort`. Values set here are *explic