# Subagent Fanout

> Parallelize independent sub-jobs across fresh-context subagents instead of one bloated context. Use when a goal branches into many independent pieces.

- Skill: `archive228/subagent-fanout` (Agent Skill)
- Install (CLI): `npx skillmds@latest add archive228/subagent-fanout`
- Raw SKILL.md: https://api.skillmd.com/api/skills/archive228/subagent-fanout/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: archive228 (https://skillmd.com/u/archive228)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/archive228/subagent-fanout

---

# Subagent Fan-out
One context loaded with ten jobs' worth of material is the exact shape that triggers context rot. Ten small contexts don't.
- Spawn one subagent per independent unit (one file, one source, one check). Each gets a fresh context window.
- An **orchestrator** synthesizes their results — it never does the per-unit work itself.
- Give each worker a tight role and only the input it needs.
- Use ONLY when the pieces are genuinely independent. Sequential dependencies stay in one chain.
Fan-out for breadth (research, multi-file edits, multi-source verification). Keep it serial when step N needs step N-1's output.