agentfield-use

agentfield-use is an Agent task delegation & fan-out skill for AI agents, published by Agent-Field in the agentfield repository on GitHub. Skillspace rates agentfield-use F (45/100) and the safety scan rated it risky; the rating is based on static analysis only.

Risky. This skill has patterns associated with unsafe behaviour. Read the source carefully before running it.

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…

Grade

F

Quality

45 / 100

Safety

Risky

GitHub stars

2,560

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since.

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.