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/commands/ruslan-korneev/claude-plugins/arch-review)<a href="https://agentmods.dev/commands/ruslan-korneev/claude-plugins/arch-review"><img src="https://agentmods.dev/badge/commands/ruslan-korneev/claude-plugins/arch-review.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 | $0.00021 | $0.01710 |
| Opus 5 | $0.00010 | $0.00855 |
| Sonnet 5 | $0.00004 | $0.00342 |
| Haiku 4.5 | $0.00002 | $0.00171 |
Grade A, and why
arch:review 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 6d 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command /architect:review
Comprehensive architecture review for Python backend projects.
Instructions
Step 1: Discover Project Structure
Use Glob to map the project:
# Find main structure
Glob: **/main.py, **/app.py, **/wsgi.py
Glob: **/__init__.py
Glob: **/models.py, **/services.py, **/routers.py, **/repositories.py
# Find configuration
Glob: **/config.py, **/settings.py, **/.env.example
# Find tests
Glob: **/test_*.py, **/*_test.py, **/conftest.py
Step 2: Analyze Layer Architecture
Check if proper separation exists:
| Layer | Files | Responsibility |
|---|---|---|
| Presentation | routers.py, views.py |
HTTP handling, DTOs |
| Application | services.py |
Business logic |
| Domain | models.py |
Entities, business rules |
| Infrastructure | repositories.py |
Data access |
Check violations:
- Business logic in routers (should be in services)
- Direct DB access in services (should be via repositories)
- Models returning DTOs (should return domain objects)
Step 3: Check Module Boundaries
For each module, verify:
- Cohesion: Related functionality grouped together
- Coupling: Minimal dependencies on other modules
- Encapsulation: Clear public API (
__init__.pyexports)
# Check for cross-module imports
Grep: "from src.modules.users" in orders/
Grep: "from src.modules.orders" in users/
Circular dependencies:
Module A imports Module B
Module B imports Module A ← Problem!
Step 4: Analyze Dependency Injection
Check how dependencies are managed:
Good patterns:
# Constructor injection
class UserService:
def __init__(self, repository: UserRepository):
self._repository = repository
# DI container (dependency-injector)
user_service = providers.Factory(UserService, repository=user_repository)
Bad patterns:
# Hard-coded dependencies
class UserService:
def __init__(self):
self._repository = UserRepository() # Tight coupling!
# Global instances
user_service = UserService() # Global state!
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.
- 6d ago First seen · 285 lines · 21 tokens per session scan A ba58b3f17664
arch:review is a command published in the GitHub repository ruslan-korneev/claude-plugins (4 stars, last pushed 6mo ago), licensed MIT. It adds 21 tokens to every session and 1,710 once invoked, about $0.0001 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 commands, from other repositories
api-contract-review
API platform contract review. Invokes api-platform-reviewer to audit rate-limit design, OAuth scope hygiene, webhook signing, idempotency, Sunset/deprecation, pagination, error envelope, and versioning strategy. Critical before v1 GA.
docs
The documentation report: references, diagrams, drift, API docs, badges, README structure, links, Pages.
doctor
Report which formatters this repository needs, which are installed, and how to install the rest.
fec-doc-sync
Sync README, docs, environment variables, scripts, API/routing/component descriptions and deployment instructions from code and project sources of truth.
dotnet-harden
Scan and harden .NET backend code against high-impact anti-patterns such as sync-over-async, lifetime bugs, fat endpoints, and fragile SignalR state.
document
On-demand documentation generation — API docs, architecture updates, user guides.