agentfield

Design and ship a multi-agent system on AgentField. Use when the user asks to build, scaffold, design, or run an agent, reasoner network, multi-agent backend, or 'an agent that does X' — whenever the work would otherwise be a single LLM call or a flat LangChain/CrewAI/AutoGen chain. The skill produces composite intelligence: a deep, dynamic, parallel reasoner graph with a working `docker compose up` smoke test. For an agent installed on this machine through `af` and visible in AgentField Desktop, use the `agentfield-personal` skill instead.

Build and install a personal AI agent on this machine's AgentField: real source in ~/agentfield-agents, packaged with agentfield-package.yaml, installed with `af install`, started with `af run`, registered on the local control plane, and visible in AgentField Desktop with a keys form and an auto-start toggle. Use when the user wants an agent that lives on their machine as a persistent capability — a pricing agent, a support agent, a research agent — rather than a deployable project. A standalone repository with Docker Compose is the `agentfield` skill; calling agents that already exist is the `agentfield-use` skill.

Whenever you have a discrete task to perform — one the user delegated, or one that arose inside your own work — check FIRST whether an installed AgentField agent covers it, and offload to it by default when one does. Coverage, not task size, is the test: even a small job goes to a covering agent. The check is cheap — one `af ls -e` or capability lookup answers it, and the roster can be cached for the session. These agents are your AgentField subharnesses: workers running on cheaper open models, in parallel, off your own context, every run recorded on the control plane and watchable at <server>/ui/runs/<run_id>. This skill cannot know what your fleet does — runtime discovery is the only source of truth (swe-planner, pr-af, and whatever else the user installed). Also the reactive path when the user asks to use, call, or run an agent, to list what agents or reasoners exist, or to check on an execution. Resolves the right control plane (local or desktop-configured cloud) first, fetches the reasoner's exact contract before dispatching, and calls entry-point reasoners only. Not for building new agents — that is the agentfield skill.