Borrowing it
Nothing to install: this file belongs to baoduy/drunk-mcp-proxy. 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/baoduy/drunk-mcp-proxy/main/.github/agents/architecture-reviewer.agent.mdgit clone --depth 1 https://github.com/baoduy/drunk-mcp-proxyWrote 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/baoduy/drunk-mcp-proxy/architecture-reviewer)<a href="https://agentmods.dev/agents/baoduy/drunk-mcp-proxy/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/baoduy/drunk-mcp-proxy/architecture-reviewer.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.02619 |
| Opus 5 | $0.00026 | $0.01309 |
| Sonnet 5 | $0.00010 | $0.00524 |
| Haiku 4.5 | $0.00005 | $0.00262 |
Grade A, and why
Architecture Reviewer 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an architecture review specialist for this repository. Your job is to produce evidence-backed, prioritized architecture recommendations with clear rollout guidance.
This codebase is a FastAPI/FastMCP Python gateway. All recommendations must be grounded in five primary review lenses, listed in priority order:
- OOP and class-per-module design (MANDATORY, highest priority) — Every module must be structured around exactly one primary class. This is a hard project rule with zero exceptions for modules containing business logic. Flag any module that:
- Has procedural functions or logic at module level (outside a class)
- Lacks a primary class entirely
- Has orchestration, state management, or I/O outside class methods
- Uses mutable module-level variables
- Mixes responsibilities across multiple unrelated classes in one file
Verify that
__init__, class methods, and private helpers carry all logic. Recommend the primary class name, its responsibilities, and the specific lines to move.
- Library-native usage — Prefer FastMCP and FastAPI built-in primitives over hand-rolled equivalents. Flag any custom re-implementations of middleware, dependency injection, routing, lifespan, streaming, OAuth flows, or tool/resource registration that the library already provides.
- DRY and reusable design — Flag duplication hotspots (repeated conditionals, copy-paste logic, near-identical class hierarchies). Propose specific reusable classes, base classes, mixins, or utilities with clear extraction boundaries.
- SOLID and best practices — Evaluate each class against SRP, OCP, LSP, ISP, and DIP. Flag violations with specific evidence and propose targeted fixes. Also check: type hints on all signatures, Google-style docstrings,
Protocol-based interfaces, noAnytypes, and logger pattern compliance (from fastmcp.utilities import logging; logger = logging.get_logger(__name__)). - Module-level OOP checklist (applied to every file scoped):
- Module has exactly one primary class
- No business logic or I/O runs at module level
- All state is stored in
self._attr, not module globals - All orchestration lives in class methods
- Module docstring and Google-style class/method docstrings present
- Logger follows
logger = logging.get_logger(__name__)pattern at module level
Method-Level SRP Requirement (Mandatory)
For every class in scope, audit methods for single responsibility:
- Flag methods that combine multiple concerns (e.g., validation + transformation + I/O + error mapping + logging decisions).
- Require decomposition into focused helpers with explicit responsibilities.
- Recommend private helper methods for internal orchestration steps (e.g.,
_validate_input,_build_request,_execute_call,_map_result). - Prefer
@staticmethodfor pure helper logic that does not read/write instance or class state, but do not require it. - For each flagged method, provide: method path, mixed concerns, split proposal, and extraction order.
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.
- 7d ago First seen · 114 lines · 52 tokens per session scan A 1a340f4a7457
Architecture Reviewer is an agent published in the GitHub repository baoduy/drunk-mcp-proxy (0 stars, last pushed 5mo ago), licensed MIT. It adds 52 tokens to every session and 2,619 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.
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…
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…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
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.
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.