parallel-subagent-dispatch

Community

Dispatch independent subagents without context loss.

AuthorRosetears520
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It prevents MainAgent context from being polluted by read-heavy exploration and enables faster, safer progress by splitting independent work across specialist subagents that return evidence anchors for reconciliation.

Core Features & Use Cases

  • Context-saving read-only dispatch: Offload noisy repository scouting (broad searches, reference mapping, log/test evidence) to one or more read-only subagents.
  • Parallel independence routing: Split two or more unrelated work packages (review vs security vs test analysis, separate subsystem investigations) when they do not share mutable state or editing dependencies.
  • Evidence-first reconciliation: Require compact, verifiable outputs (file/line or symbol anchors, classifications, confidence) and stress-test conflicts before claiming completion.

Quick Start

Use the skill when you need ROSE to split independent investigation work across subagents and then reconcile their evidence into a single coherent result, without overlapping edits.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: parallel-subagent-dispatch
Download link: https://github.com/Rosetears520/aili-workflows/archive/main.zip#parallel-subagent-dispatch

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.