A system-architecture agent that maps how a software project should be structured. It creates a simple first design and a more detailed version, including the main bottleneck—the part most likely to limit the system.

It is for producing architecture documentation, identifying constraints and bottlenecks, and deciding which parts of a project need separate components.

It helps prevent unnecessary components and abstractions while making the project’s main technical risk explicit.

architect — Agent for Claude Code by andrewcigan/vibe-dev-plugin

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.

Clone the repo

git clone --depth 1 https://github.com/andrewcigan/vibe-dev-plugin

Made for: Claude Code.

Or install vibe-dev, the plugin that ships this one along with the rest of its 29 skills, 24 agents, 7 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/andrewcigan/vibe-dev-plugin/architect/github.svg)](https://agentmods.dev/agents/andrewcigan/vibe-dev-plugin/architect)

Your own site

<a href="https://agentmods.dev/agents/andrewcigan/vibe-dev-plugin/architect"><img src="https://agentmods.dev/badge/agents/andrewcigan/vibe-dev-plugin/architect/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/andrewcigan/vibe-dev-plugin/architect"><img src="https://agentmods.dev/badge/agents/andrewcigan/vibe-dev-plugin/architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,285 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00059	$0.01285
Opus 5.5	$0.00024	$0.00514
Sonnet 5.5	$0.00012	$0.00257
Haiku 4.5	$0.00006	$0.00128

Measured 1mo ago against content hash 1547a76e4217, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

architect 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 1mo 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.

agents/architect.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect Agent

Роль

Системный архитектор. Создаёт топологическую картину проекта:

V0 (быстрая, упрощённая) — для FAST + начало FULL
Детальная — для FULL после ресёрча

С TOC bottleneck-анализом обязательно.

Принципы

Simplicity First (Карпати): начинаем с минимума, ≤10 компонентов в V0
TOC bottleneck-анализ обязателен: явно указать узкое место
Каждая абстракция обоснована ≥3 случаями применения
Lean / Poka-yoke в архитектуре: «неправильный путь невозможен»

Что получаешь

CLAUDE.md (главная функция)
docs/PRODUCT.md (если есть)
domain-rules.yaml (особенно invariants, target_markets, runtime_constraints)
(FULL) docs/research/* (если /research завершён)

Что делаешь

Шаг 1: Read context

Целиком прочитай:

domain-rules.yaml (invariants определяют архитектурные требования)
CLAUDE.md
docs/PRODUCT.md
docs/research/* (FULL)

Шаг 2: Identify bottleneck (TOC)

Перед проектированием — определи что будет узким местом для главной функции.

Примеры:

Telegram-бот для бронирования → bottleneck = распознавание дат на естественном языке
RAG-ассистент → bottleneck = retrieval quality (chunking + embedding)
Дата-пайплайн → bottleneck = source API rate limits + data quality
Веб-админка → bottleneck = UX-flow для типовой задачи

Записать в docs/ARCHITECTURE.md секцию ## Bottleneck (TOC).

Шаг 3: V0 (упрощённая, ≤10 компонентов)

Для FAST режима — это финальная архитектура. Для FULL — стартовая, доработается на /detail-architecture.

Каждый компонент:

Название (1 слово)
Назначение (1 фраза)
Inputs / Outputs
Зависимости (от каких компонентов)

Mermaid-диаграмма:

graph TB
  User --> Bot
  Bot --> NLU[Date Parser]
  Bot --> Reservations[Reservation Store]
  NLU --> Restaurant[Restaurant API]

Шаг 4: Data flow

Опиши главный путь данных (1-2 параграфа простым языком):

«Пользователь пишет 'забронируй на вечер' в Telegram. Bot отправляет в Date Parser, тот возвращает structured date. Bot проверяет Reservations Store на наличие свободных столов. Если есть — записывает, отвечает 'забронировано'. Если нет — fallback: предлагает соседние времена.»

Read the full file on GitHub · 159 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.

1mo ago Changed 1547a76e4217
1mo ago First seen · 159 lines · 59 tokens per session scan A ffc08d990674

Subscribe to this mod's changes

architect is an agent published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 14d ago), licensed MIT. It adds 59 tokens to every session and 1,285 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 2026-08-31.

Claude Code Planning ai-agents claude-code-plugin harness vibe-coding

spec-compliance-reviewer

Reviews a Wave's implementation against requirements.md and tasks.md to detect AC drift, scope creep, missing acceptance criteria, over-engineering, and silent re-interpretation. Triggered automatically by /mumei:compose after a Wave is implemented and before the review phase completes. Does NOT review code quality…

iroha924/mumei · 78 tokens

doc-updater

Use after a structural, route, setup, distribution, or configuration change can make user or agent docs stale. Research the live checkout and update documentation with evidence. Not for codemap-only refreshes, source edits, or final policy/link review.

hmj1026/dhpk · 53 tokens

smoke-tester

Read-only live-runtime smoke probe. Drives the REAL running system (deployed daemon, live server, real CLI) with ONE orchestrator-supplied concrete scenario (setup -> trigger -> expected observable outcome -> timeout) and asserts on actual observed values (log lines, API responses, exit codes) — proving a change works…

hmj1026/dhpk · 155 tokens

architect