Skills

Dispatching Parallel Agents

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

Install

npx skills add GanyuanRan/Aegis --skill dispatching-parallel-agents -g -a claude-code -y
Repository
GanyuanRan/Aegis1.4k
Category
AI and agents
Updated
10d ago
License
MIT
Context cost
Lightabout 897 tokens
Runs scripts
No, instructions only

What it does

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.

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

Read the whole SKILL.md on GitHub

More in AI and agents