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.
git clone --depth 1 https://github.com/dodobrands/ai-hubWrote 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.
[](https://agentmods.dev/agents/dodobrands/ai-hub/review-correctness)<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>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.
| Model | Per session | Once 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 |
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.
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)
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.
- 8d ago First seen · 156 lines · 42 tokens per session scan A bf858d8f2977
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.
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.
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…
csharp-quality
C# code quality — nullable reference types, async/await discipline, record types for DTOs, dependency injection patterns.
csharp-reviewer
C# 14 / .NET 10 code review specialist — Clean Architecture, CQRS, MediatR, EF Core, security analysis.
csharp-reviewer
C#-specific code reviewer. Audits for .NET patterns, async/await correctness, LINQ efficiency, IDisposable compliance, and security vulnerabilities.
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…