review

review is a command for Claude Code from hmake98/nestjs-starter. It costs 0 tokens per session (762 once invoked), scanned A, original, MIT.

A code-review checklist for a NestJS application, a TypeScript server framework. It checks module structure, services, controllers, errors, configuration access, authentication, and API documentation against project conventions.

In plain words
What is it for?
Use it to review a file or group of files for correctness, quality, dependency problems, error handling, environment configuration, controller responsibilities, access roles, and API annotations.
Why use it?
It catches inconsistent patterns and common design or security oversights before code is merged. It also keeps reviews aligned with the project's established rules.

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/hmake98/nestjs-starter/review
Clone the repo
git clone --depth 1 https://github.com/hmake98/nestjs-starter

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/hmake98/nestjs-starter/review.svg)](https://agentmods.dev/commands/hmake98/nestjs-starter/review)
Your own site
<a href="https://agentmods.dev/commands/hmake98/nestjs-starter/review"><img src="https://agentmods.dev/badge/commands/hmake98/nestjs-starter/review.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 762 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 5.1 $0.00000 $0.00762
Opus 5 $0.00000 $0.00381
Sonnet 5 $0.00000 $0.00152
Haiku 4.5 $0.00000 $0.00076

Measured 5d ago against content hash a8cbdd7e41a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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 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.

.claude/commands/review.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review the following code or file for quality, correctness, and adherence to this project's conventions: $ARGUMENTS

Read the file(s) being reviewed carefully. Then check against every rule below.


Checklist

Module structure

  • Feature module imports DatabaseModule directly — not UserModule or another feature module
  • No circular imports between feature modules
  • Module only exports what other modules actually need
  • CommonModule is only imported by AppModule

Services

  • All errors thrown as HttpException with an i18n key string and HttpStatus constant — never a raw string message
  • Existence checks use a private assertExists helper, not inline guards
  • No direct process.env access — use ConfigService.getOrThrow<T>(key)
  • @Injectable() decorator present
  • No business logic in controllers — controllers only delegate to services

Controllers

  • @ApiTags, @ApiBearerAuth('accessToken') present on class
  • Every method has @ApiEndpoint({ summary, messageKey }) — no bare HTTP decorators without doc
  • Admin controllers have @AllowedRoles([UserRole.ADMIN]) at class level
  • Public routes have @PublicRoute() — not missing auth bypass
  • Controllers return service result directly — no manual response shaping

DTOs

  • Response DTOs: @Expose() on every included field, @Exclude() on sensitive fields (passwordHash etc.)
  • Response DTOs have @ApiProperty with a faker example on each field
  • Input DTOs have class-validator decorators on every field
  • Update DTOs have all fields @IsOptional()
  • No any types

Repository

  • Only Prisma calls — no raw SQL unless necessary
  • findUnique with select: { id: true } for existence checks (not findFirst)
  • Soft delete sets deletedAt: new Date() — not a hard delete
  • Returns typed entity interfaces — not raw Prisma results with as any

Guards & decorators

  • @PublicRoute() used only where truly public — health check and auth endpoints
  • @AllowedRoles receives an array, not a spread

Read the full file on GitHub · 67 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 · 67 lines · 0 tokens per session scan A a8cbdd7e41a3

Subscribe to this mod's changes

review is a command published in the GitHub repository hmake98/nestjs-starter (61 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 762 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 2026-08-30.