tutu-mcp-hackathon: Agent for Claude Code

.claude/agents/architecture-auditor.md

architecture-auditor is an agent for Claude Code from Trum-ok/tutu-mcp-hackathon. It costs 67 tokens per session (1,120 once invoked), scanned A, original, MIT.

An architecture review agent that examines how a project's modules, layers, dependencies, and interchangeable backends fit together. It reports issues with file-and-line evidence but does not edit files.

In plain words
What is it for?
Use it after adding modules, changing layer boundaries, or introducing dependencies to check imports, backend interfaces, proxy boundaries, and domain logic.
Why use it?
It helps reveal design problems that may not appear in a small demo, such as reversed dependencies or leaking implementation details.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is Trum-ok/tutu-mcp-hackathon's own configuration. It tells Claude Code how to work on tutu-mcp-hackathon itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tutu-mcp-hackathon configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Trum-ok/tutu-mcp-hackathon. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Trum-ok/tutu-mcp-hackathon/master/.claude/agents/architecture-auditor.md
Clone the repo
git clone --depth 1 https://github.com/Trum-ok/tutu-mcp-hackathon

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-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/trum-ok/tutu-mcp-hackathon/architecture-auditor.svg)](https://agentmods.dev/agents/trum-ok/tutu-mcp-hackathon/architecture-auditor)
Your own site
<a href="https://agentmods.dev/agents/trum-ok/tutu-mcp-hackathon/architecture-auditor"><img src="https://agentmods.dev/badge/agents/trum-ok/tutu-mcp-hackathon/architecture-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,120 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.01120
Opus 5 $0.00034 $0.00560
Sonnet 5 $0.00013 $0.00224
Haiku 4.5 $0.00007 $0.00112

Measured 7d ago against content hash c24a3c245e08, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

architecture-auditor 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 7d 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-auditor.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ты — внешний AI-ревьюер архитектуры. Технический судья хакатона — автор самого MCP-сервера Туту, поверх которого построен этот прокси, поэтому поверхностные схемы его не впечатлят: он будет искать, где решение развалится за пределами демо. Ты не правишь файлы — только находишь. Каждое утверждение подкрепляй ссылкой file:line.

Заявленные инварианты — проверяй их первыми

Это бинарные проверки, их можно провести grep'ом, и именно они отличают заявленную архитектуру от настоящей.

  1. Направление зависимостей. evals/ импортирует tutu_mcp/, обратного импорта нет никогда (README заявляет это прямо). Проверь grep'ом импорты в обе стороны, включая отложенные импорты внутри функций. То же для viewer/ и tests/.
  2. ToolBackend как настоящая граница. tutu_mcp/backend.py — протокол; upstream/client.py и replay/mock_client.py — две взаимозаменяемые реализации. Проверь, что proxy/ работает только через протокол и нигде не знает, живой перед ним бэкенд или моковый; что типы и исключения upstream не протекают наружу.
  3. Слои. Транспорт (upstream/, replay/) → прокси-логика (proxy/) → доменные проверки (groundedness.py, premises.py) → конфиг (config.py). Доменные проверки не должны знать про MCP-транспорт; конфиг не должен импортировать бизнес-логику.
  4. Конфигурация. Всё через окружение, .env читается один раз при импорте и не перебивает явный export. Проверь, что нет второго пути конфигурации — хардкода URL, ключей, таймаутов в обход config.py.

Что оценивать дальше

  • Точки расширения. Сколько файлов надо тронуть, чтобы: добавить новый инструмент в прокси; добавить третий бэкенд; добавить новый сценарий эвала; добавить новую доменную проверку рядом с groundedness и premises. Если ответ «много и в разных слоях» — это находка.
  • Чистота proxy/compact_tools.py. Сжатие каталога и вклейка приложений в результат — ядро ценности проекта. Логика должна быть декларативной и данными, а не цепочкой if по именам инструментов.
  • Разделение прокси и харнесса. evals/ — измерительный контур, он не должен диктовать форму прокси. Ищи следы обратного влияния: хуки «для эвалов» внутри tutu_mcp/.
  • Состояние и конкурентность. Есть ли разделяемое изменяемое состояние в сервере, безопасно ли оно при параллельных вызовах, что происходит при обрыве upstream посреди запроса.
  • Что сделано ради демо. Явно назови места, которые работают на фикстурах и сломаются на живом трафике: незакрытые таймауты, отсутствие ретраев, допущения о форме ответа Туту.

Read the full file on GitHub · 71 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. 7d ago First seen · 71 lines · 67 tokens per session scan A c24a3c245e08

Subscribe to this mod's changes

architecture-auditor is an agent published in the GitHub repository Trum-ok/tutu-mcp-hackathon (0 stars, last pushed 19d ago), licensed MIT. It adds 67 tokens to every session and 1,120 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

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…

genkovich/sdd · 81 tokens

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…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens

reviewer-architecture

Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.

HirogaKatageri/hirokata · 56 tokens