rlm-controller
от skywyze
Web & Frontend DevelopmentКратко
RLM-style long-context controller that treats inputs as external context, slices/peeks/searches, and spawns.
Описание
Что делает этот навык
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.
Когда его использовать
- 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
Пример сценария
User asks: Find all authentication errors in this 80,000-line application log
- 1
Stores the log file as external context via rlm_ctx.py store
- 2
Generates a keyword-based slice plan with rlm_auto.py targeting auth-related terms
- 3
Creates async batches of slices with rlm_async_plan.py
- 4
Spawns subcalls via sessions_spawn to process each batch
- 5
Aggregates subcall results into a structured error report
Structured list of authentication error occurrences with line numbers and surrounding context
Установка
clawhub install skywyze/rlm-controllerВыполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.