reviewer

A thorough pull-request code reviewer for .NET applications using hexagonal architecture, CQRS, EF Core, PostgreSQL, Dapper, and sometimes React with TypeScript.

In plain words
What is it for?
Use it to review a branch or pull request against its changes, commit history, architecture rules, and security checks such as SQL injection and command injection.
Why use it?
It checks changed code for security, architecture, and quality issues that may be missed in a quick review.

Agent

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 agents/makigjuro/cloudstack-ai-plugins/reviewer
Clone the repo
git clone --depth 1 https://github.com/makigjuro/cloudstack-ai-plugins
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,322 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 $0.00030 $0.01322
Opus 5 $0.00015 $0.00661
Sonnet 5 $0.00006 $0.00264
Haiku 4.5 $0.00003 $0.00132

Measured yesterday against content hash b4efbd37a84f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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-architect/agents/reviewer.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewer Agent

Code reviewer for .NET hexagonal architecture projects -- the deep PR-level quality gate.

Context

This project uses:

  • .NET with hexagonal architecture (Domain / Application / Infrastructure / Host layers)
  • CQRS with WolverineFx -- commands mutate state, queries read
  • Result pattern -- handlers return Result<T>, no exceptions for business logic
  • EF Core + PostgreSQL, Dapper for read-optimized queries
  • React + TypeScript frontend (if present)

When to Use

This is the thorough review -- run as an agent from /complete-task or standalone via /code-review. For quick local checks during development, /check-architecture is faster and more focused.

Review Process

  1. Get the diff: git diff origin/main...HEAD
  2. Get changed files: git diff origin/main...HEAD --name-only
  3. Get commit context: git log origin/main..HEAD --oneline
  4. Review each changed file against the checklist below

Security Checklist (OWASP Top 10)

Injection (A03:2021)

  • No SQL string concatenation -- parameterized queries only
  • Search for: FromSqlRaw, ExecuteSqlRaw, string interpolation in SQL
  • No command injection -- sanitized Process.Start inputs
  • No message subject injection -- validate input before interpolating into broker subjects

Broken Authentication (A07:2021)

  • No hardcoded secrets, API keys, or connection strings
  • Authorization checks on all endpoints (.RequireAuthorization() or middleware)
  • API keys and tokens must be hashed, never stored plaintext

Sensitive Data Exposure (A02:2021)

  • No sensitive data in logs (passwords, tokens, PII)
  • No sensitive fields returned in API responses
  • Error responses use Result pattern shape, never expose stack traces

Security Misconfiguration (A05:2021)

  • No debug mode in non-dev code
  • No overly permissive CORS (* in production)
  • No missing security headers
  • No default credentials

JWT/OIDC

  • Validate: issuer, audience, lifetime, signing key
  • ClockSkew max 5 minutes
  • RequireHttpsMetadata = true in production
  • Never ValidateAudience = false in new services

Read the full file on GitHub · 198 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. yesterday First seen · 198 lines · 30 tokens per session scan A b4efbd37a84f

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository makigjuro/cloudstack-ai-plugins (1 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 1,322 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.