BuildForPeople

LiveOpen source

Agent Oracle

An AI agent orchestration design skill for Claude Code: decide agent count, topology, loop bounds and harness controls before autonomous work starts.


Agent Oracle is an AI agent orchestration design skill for Claude Code. Before any autonomous work starts, it decides four things and says them out loud: the scope, how many agents the task needs, what stops each loop, and which harness controls and budgets apply.

Each answer is grounded in one of five guides: evaluation, multi-agent patterns, harness engineering, long-horizon prompting and self-improvement loops, backed by cited research and NVIDIA's harness guidance. It defaults to one agent, treats token, tool-call, time and cost limits as a contract, and only trusts a loop bound that is deterministic.

Two standard-library CLIs come with it: an evaluator that scores a JSON test set against a weighted rubric and can gate CI, and a coordination demo. Python 3.10+, no network calls. Part of a three-skill suite with Skill Vision and Research Hound.

Read more: Claude AI skills for research and agent design.

Questions about Agent Oracle?

Ask about features, licensing, pricing or setup. Your email goes to [email protected] and the reply comes back to your inbox.

Email a question