rlm-controller

Web & Frontend Development
v1.2.0
Benign

RLM-style long-context controller that treats inputs as external context, slices/peeks/searches, and spawns.

2866 downloads866 installsby @skywyze

Setup & Installation

Install command

clawhub install skywyze/rlm-controller

If the CLI is not installed:

Install command

npx clawhub@latest install skywyze/rlm-controller

Or install with OpenClaw CLI:

Install command

openclaw skills install skywyze/rlm-controller

or paste the repo link into your assistant's chat

Install command

https://github.com/openclaw/skills/tree/main/skills/skywyze/rlm-controller

What This Skill Does

A policy-driven scaffold for processing inputs too large for a single context window. Stores input as an external context file, slices or searches it in chunks, and spawns batched subcalls to aggregate structured results. Hard limits on recursion depth, slice count, and subcall count are enforced throughout.

Handles inputs that exceed the model context window by splitting work into bounded subcalls rather than truncating or requiring manual chunking.

When to Use It

  • Scanning 50,000-line server logs for error patterns
  • Extracting structured data from large JSONL datasets
  • Analyzing an entire repository across multiple files at once
  • Summarizing dense technical documentation in controlled sections
  • Running keyword searches across multi-file audit trails

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: Scanning 50,000-line server logs for error patterns

AGENT
  1. 1Scanning 50,000-line server logs for error patterns
  2. 2Extracting structured data from large JSONL datasets
  3. 3Analyzing an entire repository across multiple files at once
  4. 4Summarizing dense technical documentation in controlled sections
  5. 5Running keyword searches across multi-file audit trails
OUTPUT
RLM-style long-context controller that treats inputs as external context, slices/peeks/searches, and spawns.

Share this skill

Security Audits

VirusTotalBenign
OpenClawBenign
View full report

These signals reflect official OpenClaw status values. A Suspicious status means the skill should be used with extra caution.

Details

LanguageMarkdown
Last updatedFeb 25, 2026