# Subagent Driven Development

> Use when: orchestrate specialized subagents to handle distinct parts of one larger task.

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

---


Goal: coordinate focused subagents so each does one job well.

Use for:
- tasks with separable concerns (research, implement, test, review)
- work too large for a single context to hold cleanly
- parallelizable streams that need a coordinator

Workflow:
1. Decompose the task into independent, well-scoped units.
2. For each unit, write a self-contained brief and success criteria.
3. State exactly what each subagent must return.
4. Dispatch read-only or independent units in parallel.
5. Integrate results; resolve conflicts and gaps yourself.
6. Verify the combined outcome against the original goal.

Briefs include:
- objective and constraints
- inputs and relevant files
- required output format
- what is out of scope

Rules:
- one clear responsibility per subagent
- never assume a subagent shares your context; spell it out
- keep write operations on one unit to avoid collisions
- the orchestrator owns final verification