Scan (Grade A) logo

Scan (Grade A)Security-tested development skill for Claude AI. Grade A. Analyze an existing codebase. Maps structure, architecture, conventions, and concerns.

— (0)
Daniel NikulshynReviewed by Daniel Nikulshyn·Updated July 2026

Overview

Scan (Grade A) is a security-tested development skill for Claude AI that analyzes an existing codebase to map its structure, architecture, conventions, and concerns. It's designed for brownfield projects with existing codebases before introducing Plan-Build-Run. The skill delegates analysis to 4 parallel codebase-mapper subagents, prioritizing accuracy over speed. It provides a comprehensive map of the codebase, which serves as context for planners and executors to make informed decisions.

Key features

  • Codebase structure mapping
  • Architecture analysis
  • Convention identification
  • Concern detection
  • Parallel analysis via subagents
  • Integration with Plan-Build-Run ecosystem

Pricing

Model
Free
Category
Skills
Rating
No reviews yet

Use cases

Brownfield Project Analysis

Analyze an existing codebase to understand its structure, architecture, and conventions before introducing Plan-Build-Run.

Codebase Refactoring

Use the comprehensive map produced by Scan (Grade A) to inform refactoring decisions and ensure minimal disruption to existing codebase.

Pros & Cons

Pros

  • Accurate codebase analysis
  • Delegates analysis to parallel subagents for efficiency
  • Provides comprehensive map of codebase structure, architecture, conventions, and concerns
  • Prioritizes accuracy over speed

Cons

  • Requires existing codebase
  • May require significant computational resources for large codebases
  • Depends on proper configuration and execution of subagents

Reviews

Sign in to leave a review.

No reviews yet. Be the first!

Q&A

What are the prerequisites for using Scan?

You must have an existing codebase in a supported directory. The tool relies on the pbr tools.js CLI and requires proper configuration of subagents; without these, Scan will abort with an error.

Asked by Urszula Kowalczyk · Mar 18, 2026

Can Scan be integrated with other tools in the Plan-Build-Run ecosystem?

Yes, Scan is designed to integrate with the Plan-Build-Run workflow. It generates a detailed map that serves as context for subsequent planning and execution phases within that ecosystem.

Asked by Jasper Vermeer · Mar 10, 2026

What kind of output can I expect after a Scan runs on my project?

The skill produces a comprehensive map of the codebase, detailing its structure, architecture, conventions, and identified concerns. Each output file contains frontmatter or the first 20 lines of analysis, which can be used as context for planners and executors.

Asked by Jibril Abubakar · Feb 1, 2026

How does Scan (Grade A) handle large codebases that may strain computational resources?

Scan delegates analysis to four parallel codebase-mapper subagents, prioritizing accuracy over speed. While this parallelism improves throughput, very large repositories may still require significant compute, so users should ensure sufficient resources before running.

Asked by Zofia Kaczmarek · Dec 26, 2025

Ask a question

Skills alternatives

Manage Headers (Grade A) logo
Manage Headers (Grade A)Skills

Security-tested development skill for Claude AI. Grade A. Inspects and configures the security headers a Power Pages site sends to browsers — Content Security Policy, frame and clickjacking protection

— (0)
Free
Using Git Worktrees (Grade A) logo
Using Git Worktrees (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktre

— (0)
Free
Ga4 Bigquery Schema (Grade A) logo
Ga4 Bigquery Schema (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. GA4 BigQuery Export Schema Reference — complete field reference, nested structures, query patterns, and performance tips

— (0)
Free
Meta Capi (Grade A) logo
Meta Capi (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Meta Conversions API (CAPI) Setup Reference — architecture, event types, customer information hashing, deduplication, implementation examples, AEM

— (0)
Free
Callees (Grade A) logo
Callees (Grade A)Skills

Security-tested development skill for Claude AI. Grade A. Lista o que uma funcao/metodo chama (call graph direto)

— (0)
Free
Test Module Name (Grade A) logo
Test Module Name (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Name Haskell test modules after the module under test with a Spec suffix in the same namespace. Use when writing or reviewing Haskell test module

— (0)
Free
Board Of Directors (Grade A) logo
Board Of Directors (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Simulate a 5-member expert board deliberation for major decisions. Use when evaluating plans, architecture choices, feature designs, or any decisi

— (0)
Free
Advpl Mvc Avancado (Grade A) logo
Advpl Mvc Avancado (Grade A)Skills

Security-tested development skill for Claude AI. Grade A. MVC avançado via PE (Pontos de Entrada) — adicionar grids customizadas em telas MVC padrão (CNTA300/MATA070/MATA440/MATA460/FINA040 via *STRU)

— (0)
Free