scan-project

Scan codebases and map signals to Claude Code automation recommendations.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/jeff-hamm/ai-tools --skill scan-project-jeff-hamm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: scan-project
Source: https://github.com/jeff-hamm/ai-tools/tree/main/src/skills/scan-project
Command: npx skills add https://github.com/jeff-hamm/ai-tools --skill scan-project-jeff-hamm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Scan a codebase and identify Claude Code automation opportunities across MCP servers, skills, hooks, subagents, and plugins; then deliver a prioritized recommendations report tailored to the project's stack.

Core Features & Use Cases

  • Phase 1 — Scan: Collect signals from project manifests, repo layout, tooling signals, and sensitive files in a read-only pass.
  • Phase 2 — Map signals to recommendations: Translate signals into a concise list of Claude Code automations (MCP servers, skills, hooks, subagents, and plugins) with justification and scope.
  • Output: Read-only suggestions that do not modify the project; provides an actionable automation plan and rationale.

Quick Start

Run the scan-project skill on a repository to generate a prioritized automation plan.

Frequently Asked Questions about scan-project

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

FAQPage Schema
How do I identify automation opportunities in my codebase for Claude Code?

To identify Claude Code automation opportunities, scan a project's manifests, repo layout, and tooling signals to map them to actionable MCP servers, skills, hooks, subagents, and plugins.

Can I generate a Claude Code automation plan without modifying my project files?

Yes, you can generate an automation plan without modifying files because the scan operates in a read-only pass, delivering suggestions and rationale while keeping the repository untouched.

What is the best way to discover which MCP servers and subagents fit my project stack?

The best way to discover fitting MCP servers and subagents is to apply project signals across common stacks and artifacts, producing a prioritized mapping that justifies each automation recommendation.

How do I map project signals to Claude Code hooks and plugins?

Map project signals to Claude Code hooks and plugins by translating sensitive file indicators and tooling configurations into a concise, explainable list of automations with defined scope.

Does scan-project require any dependencies or external components to run?

No, scan-project requires no dependencies or external components to run, operating independently to analyze the repository and return a read-only workflow of automation suggestions.

When should I not use an automated codebase scan for Claude Code automations?

You should avoid relying solely on an automated scan when you need to execute changes directly, as the tool delegates decisional ownership to experts and only provides read-only suggestions.