rlm-orchestrator

What problem does it solve?

This skill orchestrates large-context tasks by decomposing them into independent partitions, spawning parallel subagents, and aggregating results to produce a unified outcome. It addresses context window limitations and complex multi-file or multi-source workloads.

Core Features & Use Cases

• Partition-centric orchestration: automatically split tasks into independent parts for parallel processing.
• Parallel subagents: spawn multiple subagents (up to ~10 concurrent) with fresh context, and aggregate their results.
• Iterative refinement: identify gaps and spawn follow-up batches until completion.
• Claude Code-only workflow: suitable for environments where child agents cannot spawn in a single step.
• Use cases: large codebases analysis, multi-document synthesis, research-driven tasks.

Quick Start

Start by describing a large, multipart task and specify partition boundaries, then invoke the orchestrator (e.g., mention RLM or /rlm-orchestrator). Monitor batch results and review aggregated outcomes to guide next steps.