agentmods.dev

dotnet-critique

dotnet-critique is a command for coding agents from mathisk2095/jko-claude-plugins. It costs 44 tokens per session (1,282 once invoked), scanned A, original, MIT.

A deep architecture review command for backend applications built with Microsoft’s .NET platform.

In plain words
What is it for?
Use it to review a whole .NET backend or a selected area, map its layers and entry points, and assess endpoints, real-time hubs, services, databases, and external clients.
Why use it?
It identifies overly complicated design, unclear boundaries, incorrect dependency lifetimes, data-access problems, concurrency risks, and poor distributed-system choices.

Command

Part of the dotnet-backend plugin — 1 skill, 4 commands shipped together

not rated 3 yesterday A scan 44 tokens original MIT
View the source file mathisk2095/jko-claude-plugins
Install

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.

agentmods
npx agentmods add commands/mathisk2095/jko-claude-plugins/dotnet-critique
Clone the repo
git clone --depth 1 https://github.com/mathisk2095/jko-claude-plugins

Or install dotnet-backend, the plugin that ships this one along with the rest of its 1 skill, 4 commands.

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 dotnet-critique

README.md
[![agentmods](https://agentmods.dev/badge/commands/mathisk2095/jko-claude-plugins/dotnet-critique.svg)](https://agentmods.dev/commands/mathisk2095/jko-claude-plugins/dotnet-critique)
Your own site
<a href="https://agentmods.dev/commands/mathisk2095/jko-claude-plugins/dotnet-critique"><img src="https://agentmods.dev/badge/commands/mathisk2095/jko-claude-plugins/dotnet-critique.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,282 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00044 $0.01282
Opus 5 $0.00022 $0.00641
Sonnet 5 $0.00009 $0.00256
Haiku 4.5 $0.00004 $0.00128

Measured 5d ago against content hash 16d58b5ee7b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dotnet-critique 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 5d 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.

plugins/dotnet-backend/commands/dotnet-critique.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conduct a comprehensive critique of the .NET backend. If $ARGUMENTS is provided, focus on that project, directory, file, or feature area. Otherwise critique the backend as a whole.

First: Use the dotnet-backend-expert skill for all architecture principles, review order, and anti-pattern detection.

Gather Context First

  1. Detect the solution and SDK context:
    • *.sln, global.json, Directory.Build.props, Directory.Packages.props
    • target frameworks from *.csproj
    • whether the app is a Kestrel API, worker, SignalR host, AppHost, or a mix
  2. Identify the composition root:
    • Program.cs
    • service-registration extensions
    • AppHost project if present
  3. Map the architecture:
    • endpoints/controllers/route groups
    • application/services/use cases
    • domain/entities/value objects
    • infrastructure/data/external clients
    • contracts/schemas/DTOs

Critique Process

  1. AI slop detection (start here): Run the checklist from references/ai-slop.md before anything else.
  2. Architecture map: Determine whether the project is a modular monolith, layered system, vertical slice app, or accidental blob.
  3. Boundary review:
    • endpoints and hubs stay thin (DN-01, DN-02)
    • services orchestrate and enforce workflow
    • flag vague Coordinator / Manager / Engine / Orchestrator types (DN-21)
    • domain owns invariants
    • infrastructure stays behind boundaries
  4. Kestrel and hosting review:
    • listener and reverse-proxy posture explicit
    • forwarded headers and trust boundaries deliberate
    • request limits and protocol choices match exposure
  5. DI and lifetimes:
    • check singleton/scoped/transient choices
    • flag scoped-in-singleton bugs (DN-05)
    • flag service locator and hidden runtime resolution (DN-04, DN-17)
  6. Endpoint and contract review:
    • request/response models separated from entities (DN-08)
    • validation at the boundary
    • consistent error shapes and status codes
  7. SignalR review:
    • hubs thin, no business logic (DN-02)
    • no fragile in-memory connection state if the app needs scale-out (DN-15)
    • review whether the peer is actually a SignalR client or a generic socket need
  8. Security and operational review:
    • auth/authz boundaries deliberate
    • browser-facing backends have explicit CORS posture
    • public surfaces have a rate-limiting/abuse story
    • health checks and graceful shutdown present
  9. Data access review:
    • DbContext lifetime and transaction boundaries (DN-07, DN-11)
    • EF Core query shape, tracking, and repository tradeoffs (DN-10)
  10. Concurrency review: - sync-over-async, blocking calls, missing cancellation, shared mutable state (DN-06, DN-12, DN-13, DN-14)
  11. Distributed systems review: - challenge microservice or messaging complexity unless justified (DN-19)
  12. File and project size review: - flag files >300 lines as split candidates - flag files >500 lines as urgent - flag projects that mix unrelated layers
  13. Anti-pattern scan: Check for DN-01 through DN-21 from references/anti-patterns.md.

Read the full file on GitHub · 122 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. 5d ago First seen · 122 lines · 44 tokens per session scan A 16d58b5ee7b0

Subscribe to this mod's changes

dotnet-critique is a command published in the GitHub repository mathisk2095/jko-claude-plugins (3 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 1,282 once invoked, about $0.0002 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.

Backend and APIsCode reviewai-codingclaude-codeclaude-code-marketplaceclaude-code-pluginclaude-code-skills
Related

Other commands, from other repositories

route

Generate a Kibana server route with proper validation, error handling, and TypeScript types. Supports all HTTP methods and common patterns like CRUD operations and Elasticsearch queries.

ch-bas/kibana-plugin-helper · 32 tokens

embeddable

Generate a custom Embeddable panel that can be placed on Kibana Dashboards, with factory registration, input/output types, and React rendering.

ch-bas/kibana-plugin-helper · 28 tokens

expression

Generate custom Expression Functions and Renderers for use in Kibana Canvas, Lens, and Dashboard visualizations.

ch-bas/kibana-plugin-helper · 20 tokens

fast-dev

Set up a fast development environment for Kibana plugin development — mock server, optimized config, test infrastructure, and Storybook setup to minimize Kibana restarts.

ch-bas/kibana-plugin-helper · 31 tokens

saved-object

Generate a custom Saved Object type with registration, mappings, migrations, CRUD service, and management integration for a Kibana plugin.

ch-bas/kibana-plugin-helper · 24 tokens

ui-action

Generate custom UI Actions and Triggers for inter-plugin communication in Kibana — register actions, attach to triggers, execute across plugins.

ch-bas/kibana-plugin-helper · 25 tokens