← ClaudeAtlas

peeking-worklisted

Use when checking a dispatched task's live progress without joining or interrupting it, or judging whether a stuck/failed task looks like a permission denial. Not for status alone (`dispatching-work`'s list branch).
wayne930242/straw-boss · ★ 4 · AI & Automation · score 77
Install: claude install-skill wayne930242/straw-boss
## Overview Read-only. Never interrupts a `working` pane, never sends input, never substitutes for the actual checkpoint-answering flow — it only tells you what a dispatched task is currently doing. Every straw-boss skill that needs this reads it through here; the pane-read, progress-trail, and transcript-tail mechanics are not reimplemented inline anywhere else. ## Task 1: Resolve the target dispatch Identify which dispatch to peek at — from a task_id/plan slug, a session_id, or a description the caller gave you. Read its instruction file (`~/.straw-boss/dispatch/<app>--<slug>.json`, or the plan status file under `~/.straw-boss/plans/<slug>/status/` for a plan task) to get its `mode`, `session_id`, `cwd`, and — for `herdr-pane` — its agent name. Ask the caller if more than one dispatch could match. **Verification:** the target dispatch is confirmed from its actual instruction/status file, not guessed from a name alone. ## Task 2: Read the progress trail first Before touching the live pane or transcript, read the dispatch's own progress log — a sibling `<app>--<slug>.progress.jsonl` next to its instruction file (per `dispatch-mechanics.md`'s "Reporting scripts"), written by the dispatched agent's own `report-progress.py` calls throughout its work. Tail it (most recent few entries) rather than dumping the whole file. For a plan task, also check its status file — a terminal or checkpoint status there answers the question outright. If the trail (plus, for a plan task, the