review-module

review-module is a command for Claude Code from antosubash/SimpleModule. It costs 0 tokens per session (1,994 once invoked), scanned A, original, MIT.

A command that checks a SimpleModule module against its architecture rules and project conventions. It reports violations without changing files.

In plain words
What is it for?
Use it to review a named C# module, record each problem with its location and fix, and verify that module references use the intended contracts.
Why use it?
It helps find forbidden implementation dependencies and other convention problems before they spread through the codebase.

Command for Claude Code

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/antosubash/simplemodule/review-module
Clone the repo
git clone --depth 1 https://github.com/antosubash/SimpleModule

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 review-module

README.md
[![agentmods](https://agentmods.dev/badge/commands/antosubash/simplemodule/review-module.svg)](https://agentmods.dev/commands/antosubash/simplemodule/review-module)
Your own site
<a href="https://agentmods.dev/commands/antosubash/simplemodule/review-module"><img src="https://agentmods.dev/badge/commands/antosubash/simplemodule/review-module.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,994 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 $0.00000 $0.01994
Opus 5 $0.00000 $0.00997
Sonnet 5 $0.00000 $0.00399
Haiku 4.5 $0.00000 $0.00199

Measured today against content hash 2d922cc61a44, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-module 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 today.

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/commands/review-module.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Convention review for a SimpleModule module. Checks the module against the Constitution and project conventions.

If no module name was supplied as an argument, ask: "Which module would you like to review? (e.g. Products, Orders)"

Work through all 7 areas below in order. Do not auto-fix violations — record them and report at the end. For each violation found, record: file path, approximate line or pattern, what's wrong, how to fix it.

Replace {Name} with the module name throughout.


Area 1 — Architecture: No impl→impl dependencies

Read modules/{Name}/src/SimpleModule.{Name}/SimpleModule.{Name}.csproj.

For every <ProjectReference> path in that file, check whether the path points into another module's implementation assembly. A violation is a path that:

  • Contains modules/ (or modules\)
  • Does NOT end with .Contracts/SimpleModule.*.Contracts.csproj (or the backslash equivalent)

References to .Contracts projects are fine. References to the host or shared infrastructure are fine.

Violation fix: Replace the implementation reference with a reference to the other module's .Contracts project. Inject I{OtherModule}Contracts via constructor rather than using the concrete class directly.


Area 2 — Endpoints: CrudEndpoints helpers and TypedResults

Grep for MapGet|MapPost|MapPut|MapDelete in modules/{Name}/src/SimpleModule.{Name}/Endpoints/.

Check each match:

  1. CrudEndpoints helpers — Standard CRUD operations should use CrudEndpoints.GetAll, CrudEndpoints.GetById, CrudEndpoints.Create, CrudEndpoints.Update, or CrudEndpoints.Delete rather than raw inline Results.* returns for the same operation. Flag any endpoint that manually reimplements what a CrudEndpoints helper already provides.

  2. TypedResults — API endpoints must use TypedResults.* (e.g., TypedResults.Ok(...), TypedResults.NotFound()) not the non-generic Results.* static methods. Flag any use of Results.Ok, Results.NotFound, etc.

Read the full file on GitHub · 140 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. today First seen · 140 lines · 0 tokens per session scan A 2d922cc61a44

Subscribe to this mod's changes

review-module is a command published in the GitHub repository antosubash/SimpleModule (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,994 tokens. 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 2026-09-04.