ck:scout

Find relevant files and code paths across large repositories using parallel agents.

Updated May 10, 2026
One-click install
npx skills add https://github.com/dthuy62/kollet-app --skill ck-scout-dthuy62
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ck:scout
Source: https://github.com/dthuy62/kollet-app/tree/main/.opencode/skills/scout
Command: npx skills add https://github.com/dthuy62/kollet-app --skill ck-scout-dthuy62

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Scout helps you rapidly find relevant files, directories, and code relationships in large repositories without manually searching everywhere.

Core Features & Use Cases

  • Parallel discovery: Splits scouting work across multiple agents to cover different parts of a codebase at once.
  • Flexible search mode: Supports internal Explore agents by default and external Gemini/OpenCode agents when appropriate.
  • Use cases: Locate auth flows, trace feature ownership across folders, gather debugging context, or map where a change should be made before editing code.

Quick Start

Use Scout to search the repository for the files and code paths related to my task and return a concise discovery report.

Frequently Asked Questions about ck:scout

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

FAQPage Schema
How do I find relevant files and code paths across a large repository quickly?

To find relevant files and code paths quickly, you can use parallel codebase scouting to split search work across multiple agents, covering different directories at once for rapid discovery.

Can I trace feature ownership and cross-directory relationships without manually searching everywhere?

Tracing feature ownership and cross-directory relationships is supported by scouting large codebases using parallel agents that map relevant files and code paths concurrently.

Does parallel codebase scouting work with external agents like Gemini?

Parallel codebase scouting supports internal Explore agents by default and external Gemini or OpenCode agents when appropriate, allowing flexible search modes for repository discovery.

What is the best way to gather debugging context from scattered code directories?

Gathering debugging context is best handled by parallel scouting agents that locate relevant code paths and files across directories, returning a concise discovery report for your task.

How do I scope directory division and aggregate file discovery results with parallel agents?

Directory division and file discovery results are managed through task registration and timeout-aware result aggregation, ensuring parallel agents return coordinated scouting reports.

When should I use parallel agents for repository search instead of manual codebase exploration?

Parallel agents for repository search should be used when locating auth flows or mapping cross-directory changes in large codebases, replacing manual exploration with concurrent file discovery.