dispatch
Use when a task file exists in .hyperflow/tasks/ and workers need dispatching. Fans out parallel workers under per-batch Reviewers, runs a final integration review, and commits per sub-task. Endpoint of the auto-chain — no auto-deploy. Trigger with /hyperflow:dispatch, "run the plan", "execute the task", "build it", "run the batches".
npx skills add jeremylongshore/claude-code-plugins-plus-skills --skill dispatch --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Use when a task file exists in .hyperflow/tasks/ and workers need dispatching. Fans out parallel workers under per-batch Reviewers, runs a final integration review, and commits per sub-task. Endpoint of the auto-chain — no auto-deploy. Trigger with /hyperflow:dispatch, "run the plan", "execute the task", "build it", "run the batches".
How it works
- Works as an orchestrator across multiple layers (Orchestrator, Quality Gates, Project Memory, Git Workflow, Security) and applies multi-level reviews per the triage flow.
- For each batch, loads tasks, resolves mode (default/lean/thorough), and dispatches Composer Workers in parallel per sub-task (one per sub-task).
- Each Composer loads a pre-authored brief if available, selects a worker persona (Implementer / Searcher / Writer), and stitches Project Context according to the resolved mode. It also injects prior batch learnings and outputs a complete worker prompt.
- Executes a per-batch cycle with sub-phases 2a–2d (pre-dispatch, fan-out, gate run, learnings+commit), followed by a final integration review for the batch. A final integration review occurs per batch and per full diff depending on configuration.
- Final step commits per sub-task and may append learnings to memory; end-of-chain gates handle audit/deploy prompts (via AskUserQuestion) if applicable.
When to use it
Triggered by /hyperflow:dispatch, or phrases like "run the plan", "execute the task", "build it", "run the batches". Use when there is a task file in .hyperflow/tasks/ and parallel dispatch and multi-level review are required.
What it can touch
- Reads and writes: Read, Write, Edit
- Executes Bash commands across git/tools: Bash(git:), Bash(gh:), Bash(grep:), Bash(rm:), Bash(bash:), Bash(python3:), Agent, Skill, AskUserQuestion
- Uses Worker prompts template: worker-prompt.md
- Interacts with .hyperflow/profile.md, architecture.md, conventions.md, and memory files for context depending on mode (default/lean/thorough)
Caveats
- Designed for Claude Code integration; license MIT.
- Requires specific task structure and phase/gate rules as described in the workflow; deviations may halt progress or skip reviews.
- No auto-deploy; end-of-chain gates may prompt for audit/deploy actions via AskUserQuestion.
# Dispatch Workhorse phase. Picks up a task file from `/hyperflow:plan` and runs it through the orchestrator pattern with parallel worker dispatch and multi-level 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
What does the dispatch skill do?
Use when a task file exists in .hyperflow/tasks/ and workers need dispatching. Fans out parallel workers under per-batch Reviewers, runs a final integration review, and commits per sub-task. Endpoint of the auto-chain — no auto-deploy. Trigger with /hyperflow:dispatch, "run the plan", "execute the task", "build it", "run the batches".
How do I install it?
Run `npx skills add jeremylongshore/claude-code-plugins-plus-skills --skill dispatch --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From jeremylongshore/claude-code-plugins-plus-skills, a repository with 2,596 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.