← ClaudeAtlas

spec-dispatchlisted

Run an OpenSpec change's tasks in parallel — read the task queue, plan file-disjoint waves, dispatch one agent per task, verify, tick the boxes, commit. Use when the user says "dispatch the tasks", "run these tasks in parallel", "fan out the change", "/spec-dispatch", "implement this change with agents", or wants an OpenSpec change implemented by more than one agent at once. Fills the gap in OpenSpec's own `openspec-apply-change`, which is strictly serial and single-agent. Works with or without Herdr; chains to `herdr-dispatch` for the pane mechanics when inside it.
pivoshenko/pivoshenko.ai · ★ 6 · AI & Automation · score 81
Install: claude install-skill pivoshenko/pivoshenko.ai
# Spec Dispatch openspec queue -> wave plan -> agents -> verify -> tick -> commit. `openspec-apply-change` walks tasks one at a time in one context. This replaces that loop only. Planning artifacts (`proposal` / `specs` / `design` / `tasks`) stay sequential and stay with you - never fan those out; they need whole-repo context and each depends on the last. Everything here is substrate-independent. Inside Herdr (`HERDR_ENV=1`) subagents are panes per the `Herdr` instruction, and the mechanics - budget, split, start, brief, collect, blocked, cleanup - belong to `herdr-dispatch`. Outside it, dispatch the same waves with the `Agent` tool. Either way this skill owns only what is OpenSpec-specific. ## Preconditions ```bash test "${HERDR_ENV:-}" = 1 # decides the substrate only, never whether to proceed openspec status --change "<name>" --json ``` Read `applyRequires` and `isPlanningComplete`. Tasks artifact missing -> send the user to `/opsx:propose` or `/opsx:continue`. **Never author planning artifacts here.** Store-based work -> pass `--store <id>` on every openspec command and keep it sticky. ## Read the Queue ```bash openspec instructions apply --change "<name>" --json ``` Returns `progress {total, complete, remaining}` and `tasks[]` of `{id, description, done}`. **The list is flat.** No dependency edges, no file ownership - the `## 1. Backend` / `## 2. Frontend` grouping in `tasks.md` is flattened away. This JSON alone cannot tell you what is safe to run conc