rlm
rlm (Recursive Language Model workflow)
Use this Skill when:
- The user provides (or references) a very large context file (docs, logs, transcripts, scraped webpages) that won't fit comfortably in chat context.
- You need to iteratively inspect, search, chunk, and extract information from that context.
- You can delegate chunk-level analysis to a subagent.
Mental model
- Main Claude Code conversation = the root LM.
- Persistent Python REPL (
rlm_repl.py) = the external environment. - Subagent
rlm-subcall= the sub-LM used likellm_query.
How to run
Inputs
More from jdubray/puffin
coding-standard-cpp
Enforce C++ coding standards including camelCase or snake_case variables, PascalCase classes, and consistent file naming.
26coding-standard-java
Enforce Java coding standards including camelCase variables, PascalCase classes, and PascalCase filenames matching class names.
23coding-standard-python
Enforce Python PEP 8 coding standards including snake_case variables, PascalCase classes, and snake_case filenames.
20coding-standard-javascript
Enforce JavaScript/ES6+ and TypeScript coding standards including camelCase variables, PascalCase classes, and kebab-case filenames.
18modularity-patterns
Recommends modularity, composition, and decoupling patterns for design challenges. Use when designing plugin architectures, reducing coupling, improving testability, or separating cross-cutting concerns.
17coding-standard-c
Enforce C coding standards including snake_case variables and functions, UPPER_SNAKE_CASE macros, and snake_case filenames.
16