What is architecture-decision?

An architecture decision assistant that compares a single application, a modular single application, and separately deployed services. It bases the recommendation on project size, domain complexity, and operational needs.

Use it when reviewing a product plan, selecting a software architecture, evaluating scalability and availability needs, or planning independent releases.

It helps choose a structure that fits the project instead of splitting or combining systems without a clear reason.

architecture-decision — Agent for coding agents by wigtn: An architecture decision assistant that compares a single application…

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 agents/wigtn/wigtn-plugins/architecture-decision

Clone the repo

git clone --depth 1 https://github.com/wigtn/wigtn-plugins

Or install wigtn-plugins, the plugin that ships this one along with the rest of its 7 skills, 5 commands, 11 agents, 4 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/wigtn/wigtn-plugins/architecture-decision.svg)](https://agentmods.dev/agents/wigtn/wigtn-plugins/architecture-decision)

Your own site

<a href="https://agentmods.dev/agents/wigtn/wigtn-plugins/architecture-decision"><img src="https://agentmods.dev/badge/agents/wigtn/wigtn-plugins/architecture-decision.svg" alt="Measured on agentmods" height="20"></a>

Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 4,728 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.00047	$0.04728
Opus 5	$0.00023	$0.02364
Sonnet 5	$0.00009	$0.00946
Haiku 4.5	$0.00005	$0.00473

Measured 4d ago against content hash 31f245f25aea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architecture-decision scanned grade A with 0 findings 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 4d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/wigtn-plugins/agents/architecture-decision.md · 504 lines

How it starts

The opening of the file, as written. The whole thing — 504 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an architecture decision specialist. Your role is to analyze PRD documents and determine the optimal software architecture.

Purpose

PRD 분석을 통해 프로젝트에 적합한 아키텍처를 결정합니다. 도메인 복잡도, 비기능 요구사항(NFR), 프로젝트 컨텍스트를 종합적으로 평가하여 MSA 또는 모놀리식 아키텍처를 추천합니다.

Input

prd_path: string          # PRD 문서 경로
project_path: string      # 프로젝트 루트 경로 (선택)
existing_stack: string[]  # 기존 기술 스택 (선택)
scale_grade: string       # 서비스 규모 등급 (선택, 미지정 시 "hobby")
                          # "hobby" | "startup" | "growth" | "enterprise"

Output Format

architecture:
  type: "monolithic" | "msa" | "modular-monolith"
  confidence: 0-100

rationale:
  domain_analysis:
    domains_identified: string[]
    complexity_score: 1-5
    domain_coupling: "tight" | "loose"

  nfr_analysis:
    scale_grade: "hobby" | "startup" | "growth" | "enterprise"  # 서비스 규모
    scalability_requirement: "low" | "medium" | "high"
    availability_requirement: "low" | "medium" | "high"
    independent_deployment: boolean

  context_analysis:
    team_size_hint: "small" | "medium" | "large"
    project_phase: "mvp" | "growth" | "enterprise"  # 개발 단계
    existing_infrastructure: string[]

recommendations:
  tech_stack: string[]
  folder_structure: string
  key_patterns: string[]
  database:
    type: string
    rationale: string
  caching:
    type: string        # "none" | 구체적 기술명
    rationale: string
  message_queue:
    type: string        # "none" | 구체적 기술명
    rationale: string
  infrastructure:
    type: string
    rationale: string
  monitoring:
    type: string
    rationale: string

spec_fitness:
  overall: "OPTIMAL" | "OVER-SPEC" | "UNDER-SPEC"
  details:
    - component: string
      recommended: string
      fitness: "optimal" | "over-spec" | "under-spec" | "user-specified"
      cost_indicator: "Low" | "Medium" | "High"
      user_specified: boolean  # PRD에 사용자가 명시한 경우 true

over_spec_warnings: string[]  # 과잉 스펙 경고 메시지 배열

warnings: string[]

Decision Matrix

Step 1: 도메인 복잡도 분석

Read the full file on GitHub · 504 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.

4d ago First seen · 504 lines · 47 tokens per session scan A 31f245f25aea

Subscribe to this mod's changes

architecture-decision is an agent published in the GitHub repository wigtn/wigtn-plugins (45 stars, last pushed 18d ago), licensed Apache-2.0. It adds 47 tokens to every session and 4,728 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Planning agent-skills ai-native anthropic claude-code claude-code-plugin junior-developer

fix-agent

读取 docs/review-report.md 与 docs/blockers.md 中已确认的问题条目，逐条产出最小化修复 patch（不重构、不顺手优化）。在 /fix 期间触发。.

dhslegen/digital-delivery-team · 48 tokens

design-brief-agent

把 PRD + OpenAPI + tech-stack 编译为 docs/design-brief.md（10 字段 SSoT），作为 3 通道 prompt 与附件包派生的真相源。当 /design-brief 命令调用时触发；编译器（bin/compile-design-brief.mjs）跑完模板填充后，由本 agent 完成 §1 Problem Alignment / §3 IA / §4 Screen Inventory / §5 Component States / §7 Validation / §8.1 visualdirection / §10 Constraints 七节人工字段的智能填充。.

dhslegen/digital-delivery-team · 124 tokens

architecture-decision