learn_architecture

learn_architecture is a command for coding agents from dotclaude/marketplace. It costs 10 tokens per session (2,952 once invoked), scanned A, original, MIT.

A guided command for learning how a software system is structured, how its parts connect, and why design choices were made.

In plain words
What is it for?
Use it to study components, dependencies, design patterns, and the trade-offs behind an existing codebase.
Why use it?
It makes unfamiliar architecture easier to understand by breaking it into smaller steps and increasing complexity gradually.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/dotclaude/marketplace/learn_architecture
Clone the repo
git clone --depth 1 https://github.com/dotclaude/marketplace

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for learn_architecture

README.md
[![agentmods](https://agentmods.dev/badge/commands/dotclaude/marketplace/learn_architecture.svg)](https://agentmods.dev/commands/dotclaude/marketplace/learn_architecture)
Your own site
<a href="https://agentmods.dev/commands/dotclaude/marketplace/learn_architecture"><img src="https://agentmods.dev/badge/commands/dotclaude/marketplace/learn_architecture.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,952 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00010 $0.02952
Opus 5 $0.00005 $0.01476
Sonnet 5 $0.00002 $0.00590
Haiku 4.5 $0.00001 $0.00295

Measured 5d ago against content hash c22e5602d8c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learn_architecture scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Examine actual API endpoints with curl or Postman
plugins/adaptive-learning/commands/learn_architecture.md · 309 lines

How it starts

The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architectural Learning System

Guide systematic architecture understanding through progressive complexity building, pattern recognition development, and hands-on exploration with adaptive scaffolding. Transform complex system architecture into accessible learning journeys that build deep understanding through guided discovery and practical investigation.

Learning Objective Framework

Comprehension Level (Understanding existing architecture)

[Extended thinking: Focus on understanding decisions already made, components already in place, and relationships already established in existing systems.]

Learning Goals:

  • Component Understanding: Identify and understand individual system components and their responsibilities
  • Relationship Mapping: Understand how components interact and depend on each other
  • Decision Rationale: Comprehend why specific architectural choices were made
  • Pattern Recognition: Identify common architectural patterns and their applications
  • Trade-off Awareness: Understand benefits and costs of current architectural decisions

Exploration Methods:

  • System documentation analysis with guided comprehension
  • Component deep-dive investigation with scaffolded complexity
  • Data flow tracing with step-by-step pathway exploration
  • Interface examination with interaction pattern analysis
  • Historical evolution study with decision context understanding

Analysis Level (Evaluating architectural trade-offs)

[Extended thinking: Develop critical evaluation skills for assessing architectural decisions, comparing alternatives, and understanding implications.]

Learning Goals:

  • Trade-off Evaluation: Analyze benefits and costs of architectural decisions
  • Alternative Assessment: Compare different approaches and understand their implications
  • Quality Attribute Analysis: Evaluate architecture against performance, security, maintainability criteria
  • Scalability Assessment: Understand how architecture handles growth and change
  • Risk Identification: Recognize potential architectural vulnerabilities and limitations

Read the full file on GitHub · 309 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 309 lines · 10 tokens per session scan A c22e5602d8c0

Subscribe to this mod's changes

learn_architecture is a command published in the GitHub repository dotclaude/marketplace (43 stars, last pushed 5mo ago), licensed MIT. It adds 10 tokens to every session and 2,952 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.