Build an RLM

An RLM is a callable, pre-configured agent. It autonomously explores context, writes and executes code in a sandboxed REPL, calls tools, inspects results, and iterates until the task is done. Unlike a chat agent, an RLM is a function — you define its inputs, outputs, and tools, then call it from your code. It returns structured data, not chat messages.

This skill has two phases:

1. Plan — interactively define the RLM with the user, research feasibility, produce a plan
2. Build — implement the plan as code files

First action: Check skill freshness if due, then enter plan mode using the EnterPlanMode tool, unless the user is contributing to predict-rlm/RLM-GEPA itself. For contribution work, use Contributor mode first.