Dspy Rlm Module

When you have a 500k token log file or an entire codebase that won't fit in a single prompt, this skill gives Claude a sandboxed Python REPL to explore it recursively. The LLM writes code to grep, slice, and summarize chunks, issuing sub-queries until it can answer. Requires Deno installed locally. The big gotcha is cost: one RLM call can spawn dozens of inner LLM calls, so keep max_llm_calls tight and use a cheap model like gpt-4o-mini for the inner loop. Overkill for anything under 100k tokens, but genuinely useful for log analysis, codebase audits, or any task where the model needs to write code to probe data it can't hold in working memory.