how

Explains codebase architecture and subsystem flows through parallel exploration agents.

Updated Jul 29, 2026
One-click install
npx skills add https://github.com/mmdmcy/fluttAIrbar --skill how-mmdmcy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: how
Source: https://github.com/mmdmcy/fluttAIrbar/tree/main/plugins/pstack/skills/how
Command: npx skills add https://github.com/mmdmcy/fluttAIrbar --skill how-mmdmcy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Understanding how an unfamiliar subsystem works requires hours of manual code reading, and answering placement or layering questions demands architectural context most engineers lack when onboarding onto a new area. ## Core Features & Use Cases - Explain Mode: Answers "how does X work" questions by spawning parallel read-only explorer agents that trace code paths, then synthesizing their findings into a structured architectural explanation with overview, key concepts, flow, file map, and gotchas. - Critique Mode: After explaining, spawns multiple independent critic agents that evaluate the architecture against a rubric covering abstraction fit, data model, boundary discipline, evolution readiness, complexity, and consistency. - Lead Judgment: Categorizes critique findings into act-on, consider, noted, and dismissed buckets so architectural feedback is actionable rather than noisy. - Use Case: Ask "how does the rate limiter work?" and receive a senior-engineer-level walkthrough of the data model, request path, and enforcement points, with exact file references. ## Quick Start Ask the agent to explain how a specific subsystem or feature in your codebase works, optionally requesting an architectural critique.

Frequently Asked Questions about how

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

FAQPage Schema
How do I understand how a subsystem in a large codebase works?▼

Ask a how-style question naming the subsystem, such as how the rate limiter or billing flow works. The skill spawns parallel explorer agents that trace the code paths, then synthesizes their findings into a structured explanation with file references.

How to get an architectural critique of existing code?▼

Request a critique alongside the explanation. The skill first explains the architecture, then spawns multiple independent critic agents that evaluate it against a rubric covering abstraction fit, data model, boundaries, and evolution readiness.

Can this answer where new code should live in a project?▼

Yes, placement, ownership, and layering questions are a core use case. The explanation maps where things live and how components connect, giving you the context to decide which package or layer should own new functionality.

Does the exploration modify any files in the repository?▼

No, all explorer, explainer, and critic agents run in read-only mode. They use Glob, Grep, and Read to inspect the code and return findings without making any changes to the codebase.

When should I use a single-pass explanation instead of parallel explorers?▼

Simple questions about a single module or narrow function use one agent that explores and explains in a single pass. Complex subsystems spanning multiple files or services trigger 2-4 parallel explorers whose findings are then synthesized.