# Dispatching Parallel Agents

Use when facing 2+ independent tasks without a written plan, with no conflicting shared...

- Repository: https://github.com/GanyuanRan/Aegis (1408 stars)
- Category: AI and agents
- License: MIT
- Last updated: 2026-10-25
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add GanyuanRan/Aegis --skill dispatching-parallel-agents -g -a claude-code -y`
Codex: `npx skills add GanyuanRan/Aegis --skill dispatching-parallel-agents -g -a codex -y`
Cursor: `npx skills add GanyuanRan/Aegis --skill dispatching-parallel-agents -g -a cursor -y`
Gemini CLI: `npx skills add GanyuanRan/Aegis --skill dispatching-parallel-agents -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add GanyuanRan/Aegis`

## Description

Use when facing 2+ independent tasks without a written plan, with no conflicting shared mutable state or sequential dependencies, where parallel delegation beats inline cost; otherwise inline. Planned tasks use subagent-driven-development.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Dispatching Parallel Agents

## Purpose

Use parallel children for two or more ad-hoc, bounded tasks only when their
independence is already credible and concurrency is worth the coordination.
Parallelism changes elapsed time; it does not relax evidence, ownership, or
completion requirements.

## Dispatch Gate

Dispatch only when all are true:

- there are `2+` distinct tasks or evidence questions;
- one task's result is not needed to define or start another;
- the tasks do not require overlapping writes or the same mutable resource;
- a shared root cause is unlikely based on current evidence;
- each result can be returned with bounded evidence and unresolved unknowns;
- available concurrency and expected work justify coordination cost.

Keep work inline when decomposition is still exploratory, failures may share a
root cause, full-system context is required, or tasks are too small to repay the
handoff. A written implementation plan routes to
`aegis:subagent-driven-development`, not this ad-hoc workflow.

## Context And Ownership

Choose the live host's context inheritance mode deliberately. Give each child
the minimum sufficient instructions and evidence; do not rely on accidental
inheritance or assume that context must never be inherited.

Each task packet states:

- goal and question to resolve;
- allowed files, systems, and side effects;
- known facts and evidence locations;
- constraints, non-goals, and stop condition;
- expected result shape, including unknowns and verification refs.

Isolated model context does not imply an isolated filesystem, process, Git
repository, credential, rate limit, or external service. Prefer read-only
investigation. If children may edit, assign disjoint write ownership explicitly.
The coordinator owns staging, commits, branches, worktrees, integration, and other Git lifecycle mutations.

## Execution

The rest: https://github.com/GanyuanRan/Aegis/blob/HEAD/skills/dispatching-parallel-agents/SKILL.md