Agent skill · Code Review & Quality

dispatching-parallel-agents

The parallel fan-out primitive. Routed to by any skill or command that splits work across independent units and dispatches an agent per unit — subagent-driven-development, /sprint, parallel /review. It owns the dispatch/collect/funnel discipline: bound concurrency, isolate units, collect every result, dedupe overlap, and funnel through finding-triage then checkpoint-aggregator. Raw agent output is never consumed before the funnel runs; an agent that errors drops its unit without corrupting the batch.

arbiterForgegithub.com/arbiterForgeGitHub ↗
claude-codecodexAGPL-3.0
Install
npx skills add arbiterForge/codeArbiter --skill dispatching-parallel-agents --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 6 KB
Bundled scripts: none
Path: core/surface/skills/dispatching-parallel-agents/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 138 · +1 this week
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# dispatching-parallel-agents Fan out, collect everything, funnel before consuming. Plumbing other skills dispatch through — it owns the parallel discipline, not domain logic. ## Pre-flight The caller supplies the work. Confirm it, or STOP and surface the gap — never invent units or pick an agent on a hunch: - **The unit list** — N discrete, independently-completable units of work, each with its scope and target paths. - **The agent kind** — which agent kind to dispatch per unit (e.g. `backend-author`, `frontend-author`, `scout`, `security-reviewer` at `{{PLUGIN_ROOT}}/agents/<name>.md`). One kind per batch. - **The completion contract** — what each agent must return: a structured result, its unit ID, and a pass/fail/error status. Self-reports are claims, not evidence (see Phase 4). ## Phase 1 — Partition · gate: BLOCK Split the work into units that do not collide. A unit owns a distinct file or path set; two units in one batch MUST NOT mutate the same path. - **Independent paths** — units touch disjoint files. Dispatch directly. This is the common, fast case. - **Shared paths unavoidable** — units must mutate the same file or tree. Do NOT dispatch into the conflict. Route to `usin

What's inside
Steps it walks through
  1. Pre-flight
  2. Phase 1 — Partition · gate: BLOCK
  3. Phase 2 — Dispatch · gate: BLOCK
  4. Phase 3 — Collect · gate: BLOCK
  5. Phase 4 — Dedupe · gate: BLOCK
  6. Phase 5 — Funnel · gate: STOP
  7. Hard rules
More from codeArbiter
All skills →
About this skill
What does the dispatching-parallel-agents skill do?

The parallel fan-out primitive. Routed to by any skill or command that splits work across independent units and dispatches an agent per unit — subagent-driven-development, /sprint, parallel /review. It owns the dispatch/collect/funnel discipline: bound concurrency, isolate units, collect every result, dedupe overlap, and funnel through finding-triage then checkpoint-aggregator. Raw agent output is never consumed before the funnel runs; an agent that errors drops its unit without corrupting the batch.

How do I install it?

Run `npx skills add arbiterForge/codeArbiter --skill dispatching-parallel-agents --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 arbiterForge/codeArbiter, a repository with 138 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.

Keep going