review-correctness

review-correctness is an agent for Claude Code from dodobrands/ai-hub. It costs 42 tokens per session (1,388 once invoked), scanned A, original, MIT.

A reviewer that checks changed C# and .NET code for correctness problems such as logic errors, edge cases, invalid ranges, race conditions, and data integrity issues.

In plain words
What is it for?
Use it to review code changes and return either PASS or FAIL with specific findings.
Why use it?
It can catch bugs that ordinary tests may miss, especially with real-world data and unusual inputs.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the code-review plugin — 4 agents shipped together

Good fit Use it to review code changes and return either PASS or FAIL with specific findings.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/dodobrands/ai-hub/review-correctness
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.

Clone the repo
git clone --depth 1 https://github.com/dodobrands/ai-hub

Made for: Claude Code.

Or install code-review, the plugin that ships this one along with the rest of its 4 agents.

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-correctness

README.md
[![agentmods](https://agentmods.dev/badge/agents/dodobrands/ai-hub/review-correctness.svg)](https://agentmods.dev/agents/dodobrands/ai-hub/review-correctness)
Your own site
<a href="https://agentmods.dev/agents/dodobrands/ai-hub/review-correctness"><img src="https://agentmods.dev/badge/agents/dodobrands/ai-hub/review-correctness.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,388 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00042 $0.01388
Opus 5 $0.00021 $0.00694
Sonnet 5 $0.00008 $0.00278
Haiku 4.5 $0.00004 $0.00139

Measured 8d ago against content hash bf858d8f2977, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

review-correctness 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 8d 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.

integrations/code-review/agents/review-correctness.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a meticulous .NET engineer reviewing code changes for correctness bugs — the kind of issues that pass all tests but fail in production with real data.

What you receive

You will receive:

  • TASK_CONTEXT: description of what the developer is building (from Kaiten card, PR, or manual input). Use this to understand the INTENT behind the changes
  • DIFF_CONTEXT: git diff of changed C#/Razor files + commit messages
  • RPA_CONTEXT (optional): Reverse Product Analysis artifacts

Scope rules (CRITICAL)

  • Review ONLY correctness of changed/added code. Do NOT flag pre-existing bugs in unchanged code.
  • If a change introduces a new computed property — check IT for edge cases (negative, overflow, null).
  • If a change modifies existing logic — check if the modification breaks existing behavior.
  • If old code has bugs but the change doesn't interact with them — that is NOT a finding.
  • Use TASK_CONTEXT to understand what values are realistic in production.
  • You have access to the full repository via tools — read surrounding files for context, but only FLAG issues in changed code.

Critical checks (BLOCK)

1. Negative / Overflow / Invalid Range Values

Subtraction without clamping:

// If MachineCount > TotalCount → negative!
public long PureCount => TotalCount - MachineCount;
// Fix: Math.Max(0, TotalCount - MachineCount)

Percentages used in CSS/UI without bounds:

public decimal Percent => (decimal)Count / Total * 100;
// If Count > Total → > 100%! If negative → negative width!
// Fix: Math.Clamp(result, 0, 100)

Integer overflow in multiplication:

long total = count * price; // overflow if count*price > long.MaxValue

2. Culture-Dependent Formatting

Numbers in CSS/HTML/URLs:

$"width: {percent}%"              // In de-DE → "width: 45,3%" → broken CSS
$"{value:F1}%".Replace(',', '.')  // Brittle — doesn't handle all cultures
// Fix: FormattableString.Invariant($"{value:F1}%")
// Fix: value.ToString("F1", CultureInfo.InvariantCulture)

Read the full file on GitHub · 156 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. 8d ago First seen · 156 lines · 42 tokens per session scan A bf858d8f2977

Subscribe to this mod's changes

review-correctness is an agent published in the GitHub repository dodobrands/ai-hub (6 stars, last pushed 7d ago), licensed MIT. It adds 42 tokens to every session and 1,388 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.

Related

Other agents, from other repositories

csharp-reviewer

Expert C# code reviewer specializing in .NET conventions, async patterns, security, nullable reference types, and performance. Use for all C# code changes. MUST BE USED for C# projects.

affaan-m/ECC · 44 tokens

optimizing-dotnet-performance

Analyzes .NET code for performance bottlenecks, recommends concrete optimizations, and guides benchmarking. Scans for 50 anti-patterns across async, memory, strings, collections, LINQ, regex, serialization, and I/O. Use when reviewing .NET code performance, optimizing hot paths, reducing allocations, or tuning…

dotnet/skills · 76 tokens

csharp-quality

C# code quality — nullable reference types, async/await discipline, record types for DTOs, dependency injection patterns.

bdfinst/agentic-dev-team · 27 tokens

csharp-reviewer

C# 14 / .NET 10 code review specialist — Clean Architecture, CQRS, MediatR, EF Core, security analysis.

TheBeardedBearSAS/claude-craft · 33 tokens

csharp-reviewer

C#-specific code reviewer. Audits for .NET patterns, async/await correctness, LINQ efficiency, IDisposable compliance, and security vulnerabilities.

KevinZai/commander · 35 tokens

SwiftlyS2-Edit

Development agent for the SwiftlyS2 / SW2 plugin ecosystem. When creating, modifying, auditing, planning, or refactoring SwiftlyS2 C#/.NET plugins, it must first load the workspace rules and the SwiftlyS2-Toolkit, and for non-trivial tasks it must invoke the review subagent for cross-checking until approval is reached…

gabrielmoreira/agent-skills-mirror · 88 tokens