rlm-navigator

Navigate codebases using hierarchical AST skeletons and minimal token usage.

Updated Feb 2, 2026
One-click install
npx skills add https://github.com/seanrobertwright/Orion --skill rlm-navigator
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: rlm-navigator
Source: https://github.com/seanrobertwright/Orion/tree/main/.claude/skills/rlm-navigator
Command: npx skills add https://github.com/seanrobertwright/Orion --skill rlm-navigator

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill aids in the efficient navigation and understanding of complex codebases by treating source files as hierarchical trees of AST skeletons, minimizing the need to read full files.

Core Features & Use Cases

  • Recursive Codebase Navigation: Treats source files as hierarchical trees for efficient navigation.
  • Minimal Token Usage: Signatures and docstrings replace full file content to save tokens.
  • Workflows: Provides a structured workflow for health checks, exploration, reading signatures, surgical drilling, and searching across files.
  • Sub-Agent Delegation: Supports large directories by delegating tasks to specialized sub-agents.
  • REPL-Assisted Analysis: Offers a Python REPL for stateful analysis and progress reporting.
  • Chunk-Delegate-Synthesize Workflow: Handles large files and cross-file analysis with progress reporting.
  • Document Navigation: Supports navigation of non-code files using specific document tools.

Quick Start

Use the rlm-navigator skill to get a status check of the codebase with 'get_status'.

Frequently Asked Questions about rlm-navigator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I navigate complex codebases without exceeding token limits?

Complex codebases are navigated with minimal token usage by treating source files as hierarchical AST skeletons and reading signatures instead of full file content. This approach reduces context window consumption during exploration.

What is the best way to perform surgical drilling into specific functions across large files?

Surgical drilling into large files is handled using a chunk-delegate-synthesize workflow that delegates tasks to specialized sub-agents. This method isolates specific code sections and reports progress during cross-file analysis.

Can I analyze non-code documents alongside source files for codebase understanding?

Yes, document navigation is supported using specific document tools alongside source file analysis. The system handles non-code files to provide comprehensive codebase understanding and contextual exploration.

Does AST analysis support stateful exploration and progress reporting?

AST analysis supports stateful exploration through an integrated Python REPL. This allows for stateful analysis and progress reporting while traversing hierarchical source file trees and performing cross-file searches.

How do I get a quick health check of an unfamiliar codebase?

You can get a quick health check of an unfamiliar codebase by requesting a status check. This workflow evaluates the codebase structure using AST skeletons to provide an immediate overview without reading full files.