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.
git clone --depth 1 https://github.com/wigtn/wigtn-pluginsWrote 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.
[](https://agentmods.dev/agents/wigtn/wigtn-plugins/architecture-decision)<a href="https://agentmods.dev/agents/wigtn/wigtn-plugins/architecture-decision"><img src="https://agentmods.dev/badge/agents/wigtn/wigtn-plugins/architecture-decision/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00047 | $0.01337 |
| Opus 5.5 | $0.00019 | $0.00535 |
| Sonnet 5.5 | $0.00009 | $0.00267 |
| Haiku 4.5 | $0.00005 | $0.00134 |
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 22d 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.
How it starts
The opening of the file, as written. The whole thing — 93 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.
/implement DESIGN Phase의 Step 2에서 호출된다. PRD와 프로젝트 상태를 보고 아키텍처 유형과 규모에 맞는 기술을 정하고, 규모에 비해 과하거나 부족한 선택을 짚는다.
Input
prd_path: string # PRD 문서 경로
project_path: string # 프로젝트 루트 경로 (선택)
existing_stack: string[] # 기존 기술 스택 (선택)
scale_grade: string # "hobby" | "startup" | "growth" | "enterprise" (선택)
Output Format
architecture:
type: "monolithic" | "modular-monolith" | "msa"
confidence: "high" | "medium" | "low"
rationale:
domains: string[] # 식별한 비즈니스 도메인
domain_coupling: "tight" | "loose"
scale_grade: string # 서비스 규모 (아래 추정 규칙)
project_phase: "mvp" | "growth" | "enterprise" # 개발 단계 — scale_grade와 별개 축
key_nfrs: string[] # 결정에 영향을 준 NFR (PRD 인용)
recommendations:
tech_stack: string[]
folder_structure: string
key_patterns: string[]
components: # database / caching / message_queue / infrastructure / monitoring
- component: string
choice: string # "none" 가능
fitness: "optimal" | "over-spec" | "under-spec" | "user-specified"
rationale: string
warnings: string[] # Over/Under-Spec 제안 + 설계상 주의점
결정 방법
기존 프로젝트가 있으면 그 구조를 존중한다. 전환을 제안할 만한 근거가 PRD에 있을 때만 제안한다.
유형은 세 축을 함께 보고 정한다. 판단이 갈리면 더 단순한 쪽을 고른다.
| 유형 | 맞는 경우 | 구조 |
|---|---|---|
| Monolithic | 도메인 1-2개, 팀 1-5명, MVP/POC | 레이어 기반 단일 트리 (api/services/repositories/models) |
| Modular Monolith | 도메인 경계가 뚜렷한 3개 이상, 팀 3-10명, 향후 분리 가능성 | 도메인별 모듈 + shared |
| MSA | 독립 배포·독립 스케일링이 PRD에 요구됨, 팀 10명+, 폴리글랏 필요 | 서비스별 배포 단위 + gateway/infra |
MSA 신호: 99.99% 이상 가용성, 하루 수회 배포, 도메인 간 데이터 격리 필수, K8s·서비스메시 기존 인프라.
Scale Grade
PRD §4.0에 명시된 값을 쓴다. 없으면 키워드로 추정하고, 그래도 없으면 Hobby로 가정해 과잉 스펙을 막는다.
| 등급 | 추정 키워드 |
|---|---|
| Hobby | 사이드 프로젝트, 포트폴리오, 학습, 해커톤 |
| Startup | MVP, 스타트업, 프로토타입, 초기 서비스 |
| Growth | PMF, 확장, 스케일링, 시리즈 |
| Enterprise | 엔터프라이즈, 글로벌, 멀티 리전, 금융, 의료 |
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.
- 22d ago Changed · -411 lines 3cbf3098f007
- 1mo ago First seen · 504 lines · 47 tokens per session scan A 31f245f25aea
architecture-decision is an agent published in the GitHub repository wigtn/wigtn-plugins (45 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 1,337 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other agents, from other repositories
fix-agent
A repair agent that applies small, targeted code fixes for problems already recorded in review documents.
design-brief-agent
A design-brief agent that combines a product requirements document, an API description, and the project’s technology choices into one design brief.
metrics-agent
An analysis agent that reads raw delivery measurements and produces an efficiency comparison report. It explains which project stages improved or worsened and whether the available data can support those conclusions.
architect-agent
An architecture agent that creates the system plan, data model, and OpenAPI contract— a formal description of how software services communicate.
docs-agent
An AI documentation agent that prepares delivery documents after implementation and verification pass. Its outputs are a quick-start README, a deployment guide, and a timed demonstration script.
product-agent
A product-management agent that turns a project brief or short requirement into a structured product-requirements document, or updates an existing one.