- Home
- Skills
- Agents & Orchestration
- Subagent Team Designer
Works with the AI Agents you already use
Subagent Team Designer
Subagent Team Designer does the design work, then writes the files.
$24
Subagent Team Designer
Example session with this skill installed
Design a subagent team for a TypeScript React project where PR reviews are slow and unit tests are often skipped. We use Claude Code.
- Read your context and instructions
- Compiled the subagent team designer
I propose a three-agent team using a Reviewer-Guardian pattern:
| Agent | Job | Trigger | Model |
|---|---|---|---|
ts-architect | Feature logic | Manual invocation for code | Sonnet |
test-generator | Jest/RTL tests | After code changes | Haiku |
pr-auditor | Lint/Style check | Before commits | Haiku |
[Generated subagent-test-generator.md and subagent-pr-auditor.md files follow...]
Connects securely to your tools. The creator never sees your data.
About this skill
Multi-agent setups fail in two predictable ways: one bloated do-everything agent whose context is a junk drawer, or a dozen fragmented micro-agents that lose the plot between handoffs. Subagent Team Designer does the design work, then writes the files. Describe your project, stack, and the workflow moments that hurt, and it proposes the right decomposition — which specialists to create, what each owns, where the boundaries go, and which orchestration pattern fits (orchestrator plus workers, pipeline, reviewer gate, or parallel fan-out). Then it writes each subagent definition properly: a delegation trigger the orchestrator can actually route on, a focused system prompt that reads like a job description, least-privilege tool access with the reasoning stated, and the model tier matched to the job. The download includes three reference files: the subagent definition template with field-by-field guidance, an orchestration-patterns guide with the anti-patterns to avoid, and a complete worked sample team (code-reviewer, test-writer, security-auditor). Works with Claude Code subagents and any harness using markdown agent definitions — and with Claude Code, Cursor, Codex CLI, Gemini CLI, and any SKILL.md agent.
How to use
Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
2 installs
Downloaded by developers to date
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 3 months ago
- Passed all security checks, Safe to install