rig-tasklisted

# rig-task — implement one unit of work end-to-end Take a single unit of work — a tracker issue **or** an ad-hoc "implement this" with no issue filed — code it test-first, open a PR, drive it to a clean review, and hand back. **Never auto-merges unless `--auto-merge` is passed** (then CI gates the merge — see Step 5). This is the orchestrator over the kit's building blocks: it delegates isolation to `/rig-worktree`, review to `/rig-review`, and the fix loop to `/rig-review fix`, so each concern lives in one place. It's the single-unit sibling of `/rig-epic` (one unit vs many interleaved), and mirrors its lifecycle: **`start`** gets you to an open PR, **`finish`** drives the review to clean. By default a bare invocation runs both in one continuous session — the phases exist for when you want to open the PR, let CI / the review bot run, and `finish` later. `/rig-sprint` calls this once per item. ## Configuration Reads `.rig/config.json` (defaults in parentheses): - `tracker.provider` — `linear` | `github` | `none` (`none`). Selects how the spec is loaded and the PR is linked. `none` → the item is an ad-hoc task description; no ticket calls. - `tracker.ticketPrefix` — e.g. `ABC-`; used to infer a ticket from the branch. - `tracker.githubIntegration` — when `true`, GitHub drives PR/merge transitions (In Review, Done); rig still sets the start-of-work "In Progress" (Step 1), which GitHub can't observe before a PR exists. When `false`/absent, you may move states free