Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Added new helper scripts: rlm_path.py (path validation) and rlm_redact.py (secret redaction). - Introduced a cleanup script: scripts/cleanup.sh and new testing files in the tests/ directory. - Expanded core controller scripts to include rlm_plan.py, rlm_batch_runner.py, and rlm_runner.py. - Removed duplicate LICENSE.md file, retaining LICENCE.md. - Updated documentation to reflect new scripts and capabilities.
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.
User asks: Find all authentication errors in this 80,000-line application log
- 1Stores the log file as external context via rlm_ctx.py store
- 2Generates a keyword-based slice plan with rlm_auto.py targeting auth-related terms
- 3Creates async batches of slices with rlm_async_plan.py
- 4Spawns subcalls via sessions_spawn to process each batch
- 5Aggregates subcall results into a structured error report
Structured list of authentication error occurrences with line numbers and surrounding context