vc-scout
vc-scout finds files across your codebase using shell search patterns and optional parallel research agents to divide large search spaces. Use it when you need to locate specific files, understand project structure, or gather context before starting work on features spanning multiple directories.
vc-scout quickly locates files across your codebase using shell search and optional parallel agents to map project structure.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-06-21
vc-scout quickly locates files across your codebase using shell search and optional parallel agents to map project structure. vc-scout finds files across your codebase using shell search patterns and optional parallel research agents to divide large search spaces. Use it when you need to locate specific files, understand project structure, or gather context before starting work on features spanning multiple directories.
Use it when
- Yes.
- vc-scout can search multiple directories in parallel using optional parallel research agents to divide large search spaces.
Verify before relying
Read SKILL.md below before installing (4 files). Open directory: indexed for reading, not audited.
Install
withkynam/vibecode-pro-max-kit/vc-scout · repository language: JavaScript
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I find files across directories with vc-scout?
vc-scout locates files across your codebase using shell search patterns and optional parallel research agents. Specify your search criteria—by filename, extension, or pattern—and vc-scout divides the search space across multiple directories to accelerate discovery. This approach helps you quickly understand project structure and gather context before making changes that might affect multiple codebase parts.
Can vc-scout search for files by extension?
Yes. vc-scout supports searching for files matching specific patterns or extensions to scope a task or feature. You can target TypeScript files, configuration files, or any other file type by specifying the extension or pattern you need. This focused search helps you efficiently locate all relevant files without scanning the entire codebase.
Does vc-scout search multiple directories in parallel?
vc-scout can search multiple directories in parallel using optional parallel research agents to divide large search spaces. This parallel approach accelerates file discovery across your project, making it practical to search large codebases without consuming excessive tokens or waiting for sequential scans to complete.
Where does this feature live in the code with vc-scout?
vc-scout helps you locate where features and functions are defined across your codebase. By searching for specific code patterns, filenames, or references, you can quickly identify which files contain the code you're looking for, making it easier to understand dependencies and plan changes that span multiple parts of your project.
What is vc-scout's license?
vc-scout is released under the MIT license, allowing you to use, modify, and distribute it freely in both open-source and commercial projects.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
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-agentdelegation (./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
(truncated - see the full file via the links below)
File tree — 4 files
.claude/skills/vc-scout/SKILL.md
.claude/skills/vc-scout/references/external-scouting.md
.claude/skills/vc-scout/references/internal-scouting.md
.claude/skills/vc-scout/references/task-management-scouting.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Quickly locate and identify files across a large codebase to understand project structure”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
vc-debug guides you through structured investigation before any fix, combining root cause tracing, defense-in-depth validation, and verification protocols. Handle code bugs, system failures, CI/CD issues, and performance degradation with frameworks for each scenario—from call stack analysis to log inspection to frontend verification.
vc-audit-context validates your project's context layer, routing tables, and shared-skill discovery across agents. Run built-in validators to catch missing context files, broken skill references, and protocol misalignment, then regenerate your machine-readable skill catalog.
Pi-context-pipeline combines file discovery with optional GitHub research to assemble a lean context pack and ready-to-use coding prompt. It routes scoped queries through local scouting and optional external research, producing cited artifacts that narrow focus and streamline the handoff to code changes.
vc-autopilot is a contract skill that owns the provisional goal block artifact for Autopilot Mode. It emits the structured 9-field block after clarification, detects resume scenarios from pasted blocks, and validates artifacts against the D1 spec. The skill also handles V7 UPDATE variants when validation completes.
vc-setup guides you through configuring an agent development harness tailored to your project. It detects your tech stack, asks clarifying questions to understand your codebase, then scaffolds the necessary directory structure and context files—always requesting approval before making changes. Works equally well on new projects and those with existing configurations.
vc-context-discovery is the canonical context-loading entry point for every agent session. It discovers and surfaces all nested files under process folders, extracts frontmatter metadata, and routes context by domain using keyword matching. Use the auto-discovery script or keyword-first routing to load exactly the docs your task needs.
More skills vc-problem-solving (MIT)