@staff0rd/assist 0.528.3 → 0.530.0

package/README.md

@@ -379,7 +379,7 @@ Requires `assist` installed on the Windows host.
 Concurrent sessions in one repo can be isolated with native git worktrees instead of keeping multiple physical clones: see [docs/parallel-work.md](docs/parallel-work.md). All of these flags **default off**:
 
 - `worktree.enabled` (parallel work) — spill concurrent sessions into adjacent `<clone>-N` worktrees. Off means every session on the repo shares its single working copy.
-- `worktree.watcher` — starting a backlog run also ensures one starred **watcher** session in the clone itself: a claude session whose prompt is `/watch`, so the clone keeps fast-forwarding and rebuilding while the run works in its worktree. One watcher per clone — a run that finds a live one spawns no second, and the reason lands in `daemon.log`. Needs `worktree.enabled` and a `/watch` command in the repo.
+- `worktree.watcher` — starting a backlog run also ensures one starred **watcher** session in the clone itself: a claude session whose prompt is `/watch`, run with `--permission-mode auto`, so the clone keeps fast-forwarding and rebuilding while the run works in its worktree. The watcher's cwd is always the clone, never a worktree. One watcher per clone — a run (fresh or chained) that finds a live one spawns no second, and the reason lands in `daemon.log`; a watcher that has stopped or errored is replaced by the next run. Needs `worktree.enabled`, a `/watch` command in the repo, and an `auto-build` run entry in its `assist.yml` (what `assist watch wait --build` invokes).
 - `worktree.trunk` (trunk-based) — on, a spilled worktree's branch tracks `origin/<trunk>` so commits land on the mainline. Off, it starts off the remote default branch with no mainline tracking, leaving the session to raise its own branch and PR.
 
   While it is on, a job that commits never runs in the clone: `backlog run <id>` (spawned fresh or chained into from a session already sitting in the clone) and PR checkouts (`review <n>`, `review-pr-comments <n>`) always allocate a `<clone>-N`, even when the clone is idle and clean. Committing there would land the work on the local mainline and leave every later worktree starting from that HEAD. Plain prompts, `spawnInTree` sessions, `draft`/`bug`/`refine` and every other command keep the normal clone-preferring placement, and a session pinned in place stays where it was launched. There is no fallback — if the worktree can't be created the spawn fails with the reason in `daemon.log` rather than dropping the job in the clone. Non-trunk repos are unaffected.

package/claude/commands/design.md

@@ -7,7 +7,7 @@ You are being asked to act as an expert designer for the remainder of this task.
 
 ## Step 1: Load the design system prompt
 
-Read `~/.claude/system-prompt.md` in full. This is a 647-line design system prompt that defines your identity, workflow, and standards as a designer. Adopt it as your operating context for this task — its instructions take precedence over your default behaviour for the design work that follows.
+Read `~/.claude/design-system-prompt.md` in full. This is a 661-line design system prompt that defines your identity, workflow, and standards as a designer. Adopt it as your operating context for this task — its instructions take precedence over your default behaviour for the design work that follows.
 
 If the file is missing, tell the user to run `assist sync` first and stop.
 
@@ -22,3 +22,9 @@ Apply the adopted design guidance to the following request:
 $ARGUMENTS
 
 Follow the workflow the system prompt lays out — ask clarifying questions first when the request is new or ambiguous, acquire design context before mocking from scratch, build a skeleton early, and run `polish-pass` before delivery.
+
+## Step 4: Deliver as an artifact
+
+The design system prompt is written for a filesystem-based project, so it talks about saving HTML files. In Claude Code the file is the intermediate, not the deliverable: **publish the finished design as an artifact** so the user gets a URL they can open and share. Do not deliver a scratchpad path.
+
+Load the `artifact-design` skill before writing the page, write the HTML to a file, then publish that file with the `Artifact` tool. When iterating, edit the same file and publish again so the URL stays stable. Keep a design on disk only as a working intermediate, or when the user asks for a file specifically.