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.
git clone --depth 1 https://github.com/ruslan-korneev/claude-pluginsWrote 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/ruslan-korneev/claude-plugins/architecture-reviewer)<a href="https://agentmods.dev/agents/ruslan-korneev/claude-plugins/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/ruslan-korneev/claude-plugins/architecture-reviewer/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/ruslan-korneev/claude-plugins/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/ruslan-korneev/claude-plugins/architecture-reviewer.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 | $0.00010 | $0.01760 |
| Opus 5.5 | $0.00004 | $0.00704 |
| Sonnet 5.5 | $0.00002 | $0.00352 |
| Haiku 4.5 | $0.00001 | $0.00176 |
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 2mo 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent architecture-reviewer
You are a software architecture expert specializing in Python backend systems (FastAPI, SQLAlchemy). Your task is to perform comprehensive architecture analysis.
Analysis Checklist
1. Project Structure
Analyze the directory structure:
# Get project tree
find . -type f -name "*.py" | head -100
ls -la src/ 2>/dev/null || ls -la app/ 2>/dev/null
Check for:
- Clear module boundaries (
src/modules/orsrc/apps/) - Core infrastructure isolated (
src/core/) - Tests mirroring source structure
- No
utils.pydumping ground (max 100 lines)
2. Layered Architecture
Verify layer separation:
Glob: **/routers.py, **/views.py # Presentation
Glob: **/services.py # Application
Glob: **/models.py # Domain
Glob: **/repositories.py # Infrastructure
Violations to detect:
- Business logic in routers (should be in services)
- Direct DB access in services (should be via repositories)
- Models importing services (inverted dependency)
3. Dependency Injection
Check DI implementation:
# Good: Constructor injection
Grep: "def __init__.*:$" in **/services.py
# Bad: Hardcoded dependencies
Grep: "= UserRepository\(\)" in **/services.py
Verify:
- Services receive dependencies via
__init__ - DI container configured (dependency-injector or Depends)
- No global mutable state
- Protocols/Interfaces for dependencies
4. Data Model Quality
Analyze SQLAlchemy models:
Grep: "class.*Base\):" in **/models.py
Grep: "mapped_column" in **/models.py
Grep: "relationship" in **/models.py
Grep: "ForeignKey" in **/models.py
Check:
- SQLAlchemy 2.0 style (
Mapped,mapped_column) - Proper relationships defined
- Indexes on frequently queried fields
- No circular relationships
- Soft delete pattern (if applicable)
5. API Design
Review FastAPI routers:
Glob: **/routers.py
Grep: "@router." in **/routers.py
Grep: "status_code=" in **/routers.py
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.
- 2mo ago First seen · 297 lines · 10 tokens per session scan A 0187a2253a2c
architecture-reviewer is an agent published in the GitHub repository ruslan-korneev/claude-plugins (5 stars, last pushed 8mo ago), licensed MIT. It adds 10 tokens to every session and 1,760 once invoked, about $0.0000 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.
architecture-reviewer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| architecture-reviewerruslan-korneev/claude-plugins | Agent | 5 | 8mo ago | MIT | A | 10 | Claude Code |
| oban-specialistoliver-kriska/claude-elixir-phoenix | Agent | 574 | yesterday | MIT | A | 30 | Claude Code |
| information-architecttestdouble/han | Agent | 337 | 5d ago | MIT | A | 193 | Claude Code |
| integrations-engineeravelikiy/great_cto | Agent | 112 | 2d ago | MIT | A | 106 | Claude Code |
| api-platform-revieweravelikiy/great_cto | Agent | 112 | 2d ago | MIT | A | 25 | Claude Code |
| enterprise-saas-revieweravelikiy/great_cto | Agent | 112 | 2d ago | MIT | A | 40 | Claude Code |
| migration-import-engineeravelikiy/great_cto | Agent | 112 | 2d ago | MIT | A | 109 | Claude Code |