rlm-controller
RLM-style long-context controller that treats inputs as external context, slices/peeks/searches, and spawns.
Setup & Installation
Install command
clawhub install skywyze/rlm-controllerIf the CLI is not installed:
Install command
npx clawhub@latest install skywyze/rlm-controllerOr install with OpenClaw CLI:
Install command
openclaw skills install skywyze/rlm-controlleror paste the repo link into your assistant's chat
Install command
https://github.com/openclaw/skills/tree/main/skills/skywyze/rlm-controllerWhat 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.
User asks: Scanning 50,000-line server logs for error patterns
- 1Scanning 50,000-line server logs for error patterns
- 2Extracting structured data from large JSONL datasets
- 3Analyzing an entire repository across multiple files at once
- 4Summarizing dense technical documentation in controlled sections
- 5Running keyword searches across multi-file audit trails
RLM-style long-context controller that treats inputs as external context, slices/peeks/searches, and spawns.
Security Audits
These signals reflect official OpenClaw status values. A Suspicious status means the skill should be used with extra caution.