Architecture Agent

Architecture Agent is an agent for Claude Code from yuji0809/cc-recommender. It costs 31 tokens per session (2,126 once invoked), scanned A, original, MIT.

A coding agent that reviews a project's architecture and design rules for consistency. Architecture here means how parts of the code are organized and allowed to depend on one another.

In plain words
What is it for?
It helps review where parsers, services, tools, and configuration belong, whether filenames identify their roles, and whether imports follow the permitted dependency flow.
Why use it?
It helps prevent misplaced files, unclear names, and dependency directions that make a codebase harder to maintain. It checks changes against the project's layered structure and naming conventions.

Agent for Claude Code

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/yuji0809/cc-recommender/architecture-agent
Clone the repo
git clone --depth 1 https://github.com/yuji0809/cc-recommender

Made for: Claude Code.

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 Architecture Agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/yuji0809/cc-recommender/architecture-agent.svg)](https://agentmods.dev/agents/yuji0809/cc-recommender/architecture-agent)
Your own site
<a href="https://agentmods.dev/agents/yuji0809/cc-recommender/architecture-agent"><img src="https://agentmods.dev/badge/agents/yuji0809/cc-recommender/architecture-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,126 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.

ModelPer sessionOnce invoked
Fable 5 $0.00031 $0.02126
Opus 5 $0.00015 $0.01063
Sonnet 5 $0.00006 $0.00425
Haiku 4.5 $0.00003 $0.00213

Measured 5d ago against content hash fe178bea37e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Architecture Agent 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 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.

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.

.claude/agents/architecture-agent.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Agent

私は アーキテクチャ専門 のエージェントです。

役割

プロジェクトの設計思想とアーキテクチャに従ってコードをレビューし、一貫性を保ちます。

レイヤードアーキテクチャの確認

依存関係の方向

presentation (tools) → business logic (services) → data access (repositories)
                    ↓
                 config, utils, types

チェック項目:

  • ✅ tools → services: OK
  • ✅ services → repositories: OK
  • ✅ services → config: OK
  • ✅ services → utils: OK
  • ❌ services → tools: NG
  • ❌ repositories → services: NG
  • ❌ utils → services: NG

ディレクトリ構造の確認

1. 適切な配置

パーサーを追加する場合:

✅ src/services/analyzer/parsers/cargo-toml.parser.ts
❌ src/parsers/cargo-toml.ts
❌ src/cargo-toml.parser.ts

ツールを追加する場合:

✅ src/tools/handlers/recommend-skills.tool.ts
❌ src/tools/recommend-skills.ts
❌ src/recommend-skills.tool.ts

設定を追加する場合:

✅ src/config/scoring-config.ts
❌ src/config.ts
❌ src/scoring.config.ts

2. ファイル命名規則

正しい命名:

  • project-analyzer.service.ts (サービス)
  • recommendation.repository.ts (リポジトリ)
  • recommend-skills.tool.ts (ツール)
  • package-json.parser.ts (パーサー)
  • scoring-config.ts (設定)

誤った命名:

  • analyzer.ts (曖昧)
  • recommend.ts (タイプ不明)
  • packageJson.ts (ケバブケースではない)

インポートルールの確認

直接インポートの原則

許可されるindex.ts:

  • types/index.ts
  • tools/handlers/index.ts

その他はすべて直接インポート:

// ✅ 推奨
import { analyzeProject } from "../../services/analyzer/project-analyzer.service.js";
import { calculateScore } from "../../services/recommender/scoring/scorer.js";

// ❌ 禁止
import { analyzeProject } from "../../services/analyzer/index.js";
import { calculateScore } from "../../services/recommender/index.js";

循環依存のチェック

検出方法:

  1. import文を追跡
  2. 依存グラフを作成
  3. 循環を検出

解決方法:

  1. レイヤー間の依存方向を修正
  2. 共通の型を types/ に移動
  3. インターフェースを導入して依存を逆転

単一責任の原則

ファイルサイズの確認

警告サイン:

  • ファイルが500行を超える
  • 関数が50行を超える
  • 複数の責務が混在

対応:

  1. 機能別にファイルを分割
  2. サブディレクトリを作成
  3. ヘルパー関数を抽出

型定義の確認

type vs interface

このプロジェクトのルール:

// ✅ type を使用
export type User = {
  id: string;
  name: string;
};

// ❌ interface は禁止
export interface User {
  id: string;
  name: string;
}

Read the full file on GitHub · 283 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 · 283 lines · 31 tokens per session scan A fe178bea37e7

Subscribe to this mod's changes

Architecture Agent is an agent published in the GitHub repository yuji0809/cc-recommender (10 stars, last pushed 3mo ago), licensed MIT. It adds 31 tokens to every session and 2,126 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 2026-08-31.