Sub-Agent Collective

An experimental take on subagents — a 'collective' of agents built around context-engineering research, with hub-and-spoke coordination and test-driven handoffs between agents.

Rather than another flat list of agents, this project treats multi-agent coordination as a research problem: a hub-and-spoke architecture where a coordinator routes work to specialist agents with test-driven validation gates between handoffs.

Worth studying if you're pushing subagents beyond one-shot delegation — the README documents what worked, what didn't, and why.

Install: follow the repo's setup instructions; agents live in .claude/agents/ as usual.

Categories:

Subagents

Tags:

agents claude-code context-engineering experimental subagents

Your brand here

Reach our audience of professional directory owners and boost your sales.

Advertise on Claudeable

Featured tools:

Similar to Sub-Agent Collective

View all tools

Dev House

Build a Claude Code dev team of custom agents on the models you choose

Subagents

Create your own agent team — each member with its own role, skills, model and permission mode — and run them through a planning → coding → review workflow. Mixes Claude Code, OpenCode and Antigravity in one run, with shared memory and per-member cost tracking.

Claude Code Sub-Agents (lst97)

Full-stack development subagents with an orchestrated workflow

Subagents

A popular collection of specialized subagents for full-stack development — coordinated so agents hand work to each other across planning, implementation, review, and testing.

Claude Code Agents (wshobson)

A widely-used collection of focused, single-responsibility subagents

Subagents

One of the most popular subagent collections for Claude Code — dozens of production-oriented agents covering languages, frameworks, DevOps, security review, and architecture, designed for automatic delegation.