rlm

Community

Recursively explore long-context prompts.

AuthorXiaoConstantine
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill enables handling arbitrarily long contexts by allowing the LLM to programmatically explore prompts via Query() and FINAL() patterns, reducing token consumption and latency.

Core Features & Use Cases

  • Long-context processing: Efficiently process contexts >50KB by chunking and recursive sub-LLM calls.
  • Token efficiency: Achieve significant token savings by avoiding full-context repetition.
  • Go REPL-based workflow: Leverage a Yaegi-based interpreter to run generated code and sub-queries.

Quick Start

Install the rlm binary and run a test with a large context file: rlm -context big-context.txt -query "Summarize findings" -verbose

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: rlm
Download link: https://github.com/XiaoConstantine/rlm-go/archive/main.zip#rlm

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.