hybrid-research

Find relevant files semantically and extract exact code references with file:line locations.

3|Updated Apr 14, 2026
One-click install
npx skills add https://github.com/joshka0/foxctl --skill hybrid-research
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hybrid-research
Source: https://github.com/joshka0/foxctl/tree/main/configs/skills/hybrid-research
Command: npx skills add https://github.com/joshka0/foxctl --skill hybrid-research

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you investigate an unfamiliar codebase quickly by combining fast exact file access with semantic discovery, so you can move from a question to concrete code evidence without getting stuck guessing file locations.

Core Features & Use Cases

  • Hybrid discovery + extraction: uses foxctl MCP semantic tools to find relevant files by concept, then uses native tools (Read/Grep/Glob) to extract exact code and callsites.
  • Evidence-aware research: incorporates memory_query and session_recall so results can reflect prior decisions and past investigation context.
  • Deeper code intelligence when needed: supports snippet extraction, symbol/type shaping, and relationship graph analysis for architecture-level understanding.
  • Read-only investigation safety: designed for exploration and reporting rather than code modification.

Quick Start

Ask the agent to investigate your question by running: /hybrid-research Explain how session continuity is implemented in foxctl and where decisions are stored.

Frequently Asked Questions about hybrid-research

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

FAQPage Schema
How do I find where a specific feature is implemented in an unfamiliar codebase?

Semantic code search finds relevant files by concept, then native tools like Grep and Read extract exact code references and callsites. This hybrid research approach yields precise file:line evidence without manually guessing file locations.

What is the best way to investigate software architecture across a large codebase?

Architecture analysis uses semantic discovery to locate relevant modules, then applies relationship graph analysis and symbol extraction to map structural dependencies. This produces an evidence-aware report grounding architectural understanding in exact code references.

Can I use memory and session tools to recall past codebase investigation context?

Yes, evidence-aware research incorporates memory_query and session_recall tools. This allows the investigation results to reflect prior decisions and past investigation context, providing continuity for ongoing codebase research tasks.

Does hybrid codebase research modify my source files during analysis?

No, this codebase research approach uses a read-only pipeline for exploration and reporting. It leverages semantic search and native Read, Grep, and Glob tools to extract findings safely without modifying your source code.

How do I extract exact code callsites when researching how a function works?

Semantic search first discovers relevant files by concept, then native tools like Grep and Read deterministically extract precise code callsites and snippets. This hybrid extraction ensures you get exact file:line references for understanding function implementations.