Borrowing it
Nothing to install: this file belongs to yuji0809/cc-recommender. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/yuji0809/cc-recommender/main/.claude/agents/architecture-agent.mdgit clone --depth 1 https://github.com/yuji0809/cc-recommenderWrote 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/yuji0809/cc-recommender/architecture-agent)<a href="https://agentmods.dev/agents/yuji0809/cc-recommender/architecture-agent"><img src="https://agentmods.dev/badge/agents/yuji0809/cc-recommender/architecture-agent/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/yuji0809/cc-recommender/architecture-agent"><img src="https://agentmods.dev/badge/agents/yuji0809/cc-recommender/architecture-agent.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 | $0.00031 | $0.02126 |
| Opus 5.5 | $0.00012 | $0.00850 |
| Sonnet 5.5 | $0.00006 | $0.00425 |
| Haiku 4.5 | $0.00003 | $0.00213 |
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 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.
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.tstools/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:
- import文を追跡
- 依存グラフを作成
- 循環を検出
解決方法:
- レイヤー間の依存方向を修正
- 共通の型を types/ に移動
- 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:
- 機能別にファイルを分割
- サブディレクトリを作成
- 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;
}
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 First seen · 283 lines · 31 tokens per session scan A fe178bea37e7
Architecture Agent is an agent published in the GitHub repository yuji0809/cc-recommender (10 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 2,126 once invoked, about $0.0001 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.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…