Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →ccplugins/dispatch
Use when a task file exists in `.hyperflow/tasks/` and workers need dispatching — `/hyperflow:dispatch`, "run the plan", "execute the task", "build it". Dispatches parallel workers, runs thinking-tier batch reviews, finishes with a final integration review. Endpoint of the auto-chain (no auto-deploy — user opts in to push).
Passed 12 of 17 test cases with the skill, and 2 of 17 without it.
and 13 more in the full report
13 fixed3 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
The orchestration starter initiated dispatch with arguments `user-auth.md chain-mode=auto`. Do we need to pause at Step 0 and present an AskUserQuestion prompt to ask the user whether to run in auto or manual mode?
| Checked | Without skill | With skill |
|---|---|---|
| Bypasses Step 0 mode selection prompt when chain-mode is explicitly provided as an argument | Passed | Passed |
| Proceeds directly to loading the task file | Missed | Passed |
The instructions your model reads when the skill loads.
Workhorse phase. Picks up a task file from /hyperflow:scope and runs it through the orchestrator pattern with parallel worker dispatch and thinking-tier reviews.
This skill exercises Layer 3 (Orchestrator), Layer 5 (Quality Gates), Layer 6 (Project Memory), Layer 8 (Git Workflow), and Layer 9 (Security) from the doctrine. Multi-level review (L1–L5) is applied per the triage's flow profile.
Every substantive step dispatches at least one Agent.
| Step | Worker tier | Thinking tier | Notes |
|---|---|---|---|
| 0 — Mode confirm | — | — | AskUserQuestion only (exempt) |
| 1 — Load task | — | — | File read only (exempt) |
| 2 — Per batch | Implementer / Searcher / Writer × N parallel (Sonnet) | Reviewer (Opus) per sub-task at L1–L | Both tiers · per sub-task |
| 2b — Quality gates | Worker (Sonnet) runs lint/typecheck/tests | Reviewer (Opus) judges gate output | Both tiers |
| 3 — Final integration | — | Reviewer (Opus) L1–L over full diff | Mandatory |
| 4 — Wrap up | Writer (Sonnet) deletes task, appends memory, auto-commits | Reviewer (Opus) sanity-checks the commit + memory entries | Both tiers |
| 5 — End of chain | — | — | Two AskUserQuestion gates: audit? deploy? (exempt — gates only) |
Iron rule — thinking agents ≥ batches + 1 (per-batch reviewer + final integration). With per-step thinking-tier reviewers in Step 4, the floor rises to batches + 2.
Every batch reviewer and the final integration reviewer uses the level set below. Profile comes from /hyperflow:spec triage and is propagated via the chain-mode args.
| Profile | Levels | Workers | Reviewers |
|---|---|---|---|
fast | L1 | 1 | inline self-review only |
standard | L1–L2 | 1–2 | 1 per-batch reviewer |
deep | L1–L5 | 3+ | per-batch + final integration |
research | L1–L2 + synthesis | 3+ searchers | inline synthesis |
creative | L1–L3 + UX | 1–2 | 1 reviewer |
scientific | L1–L5 + TDD | 2–3 | per-batch + final |
L1 syntax/format · L2 spec/naming/edges · L3 integration/security · L4 perf/scale · L5 a11y/UX. See review-levels.md for the full checklist.
| Gate | When | Format |
test cases passed, vs 2 / 17 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.