# Vc Scout

Fast codebase scouting using shell search and optional parallel research agents.

- Repository: https://github.com/withkynam/vibecode-pro-max-kit (1164 stars)
- Category: AI and agents
- License: MIT
- Last updated: 2026-06-21
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add withkynam/vibecode-pro-max-kit --skill vc-scout -g -a claude-code -y`
Codex: `npx skills add withkynam/vibecode-pro-max-kit --skill vc-scout -g -a codex -y`
Cursor: `npx skills add withkynam/vibecode-pro-max-kit --skill vc-scout -g -a cursor -y`
Gemini CLI: `npx skills add withkynam/vibecode-pro-max-kit --skill vc-scout -g -a gemini-cli -y`

## Description

Fast codebase scouting using shell search and optional parallel research agents. Use for file discovery, task context gathering, and quick scoped searches across directories.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Scout

> **Output style:** Follow `process/development-protocols/communication-standards.md`, answer-first, plain language, no unexplained jargon, TL;DR on long responses.

Fast, token-efficient codebase scouting using parallel agents to find files needed for tasks.

## Arguments
- Default: Scout using local shell search plus optional parallel `research-agent` delegation (`./references/internal-scouting.md`)
- `ext`: Scout using external Gemini/OpenCode CLI tools in parallel (`./references/external-scouting.md`)

## When to Use

- Beginning work on feature spanning multiple directories
- User mentions needing to "find", "locate", or "search for" files
- Starting debugging session requiring file relationships understanding
- User asks about project structure or where functionality lives
- Before changes that might affect multiple codebase parts

## Quick Start

1. Analyze user prompt to identify search targets
2. Use a wide range of Grep and Glob patterns to find relevant files and estimate scale of the codebase
3. Use local shell search first, then optionally spawn parallel `research-agent` workers with divided directories when the search space is large
4. Collect results into concise report

## Configuration

Read from `.claude/.vc.json` (falls back to legacy `.claude/.ck.json` if present):
- `gemini.model` - Gemini model (default: `gemini-3-flash-preview`)

## Workflow

### 1. Analyze Task
- Parse user prompt for search targets
- Identify key directories, patterns, file types, lines of code
- Determine optimal SCALE value of subagents to spawn

### 2. Divide and Conquer
- Split codebase into logical segments per agent
- Assign each agent specific directories or patterns
- Ensure no overlap, maximize coverage

The rest: https://github.com/withkynam/vibecode-pro-max-kit/blob/HEAD/.claude/skills/vc-scout/SKILL.md