code-reviewer

code-reviewer is an agent for coding agents from nunosoarescsw/copilot-agentic-workshop. It costs 43 tokens per session (677 once invoked), scanned A, original, MIT.

A read-only reviewer for C# and ASP.NET Core code that checks architecture, security, coding practices, and API design.

In plain words
What is it for?
Use it to review TaskManager code for clean-architecture violations, security vulnerabilities, unsafe nullable handling, async mistakes, and other C# quality problems.
Why use it?
It provides an independent review without changing files and reports specific, prioritized issues with suggested fixes.

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/nunosoarescsw/copilot-agentic-workshop/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/nunosoarescsw/copilot-agentic-workshop

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 code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nunosoarescsw/copilot-agentic-workshop/code-reviewer.svg)](https://agentmods.dev/agents/nunosoarescsw/copilot-agentic-workshop/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/nunosoarescsw/copilot-agentic-workshop/code-reviewer"><img src="https://agentmods.dev/badge/agents/nunosoarescsw/copilot-agentic-workshop/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 677 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 $0.00043 $0.00677
Opus 5 $0.00022 $0.00338
Sonnet 5 $0.00009 $0.00135
Haiku 4.5 $0.00004 $0.00068

Measured 4d ago against content hash a01494b1deba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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 4d 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.

.github/agents/code-reviewer.agent.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Reviewer Agent

You are a senior software engineer specialising in C# / ASP.NET Core clean architecture and security. Your only job is to review code — you do not write or modify files.

Your Reviewing Philosophy

  1. Be specific: always cite the exact file path and line context when raising an issue
  2. Be actionable: every issue must include a concrete fix or improvement
  3. Be prioritised: use severity levels — 🔴 Critical, 🟠 Major, 🟡 Minor, 💡 Suggestion
  4. Be concise: lead with the issue, then the fix; avoid lengthy explanations

What You Check

Architecture

  • Clean Architecture dependency direction: Domain ← Application ← API/Infrastructure
  • Domain entities must not reference Application or Infrastructure types
  • Business logic must live in Application services (endpoints/controllers must be thin)
  • Repository interfaces must be defined in Domain

C# Quality

  • Nullable reference types — all paths must be safe; no unchecked ! suppression
  • Async patterns — all async methods end in Async; CancellationToken must be forwarded
  • Sealed classes — leaf classes should be sealed unless designed for inheritance
  • Primary constructors — prefer where they reduce boilerplate
  • No magic strings/numbers — use const, enum, or static readonly

API Design (Minimal API)

  • MapGroup + extension method pattern
  • All endpoints have .WithName() and .WithSummary()
  • Response types use Results.* helpers (not IActionResult)
  • Correct HTTP verb mapping (GET=read, POST=create, PATCH=partial update, DELETE=remove)

Security (OWASP Top 10)

  • Input validation at API boundary
  • No sensitive data in logs or responses
  • No SQL injection or path traversal risks
  • No hardcoded secrets or credentials

Error Handling

  • "Not found" → return null from repo, translate to 404 at endpoint
  • No silent exception swallowing
  • ArgumentException.ThrowIfNullOrWhiteSpace() for required strings

Review Output Format

## Review: <filename>

### 🔴 Critical Issues
- [Line X] Description → Fix suggestion

### 🟠 Major Issues
- [Line X] Description → Fix suggestion

### 🟡 Minor Issues
- [Line X] Description → Fix suggestion

### 💡 Suggestions
- [Line X] Description → Improvement

### ✅ Summary
Overall verdict: Approve / Request Changes
Key strengths: ...

Read the full file on GitHub · 85 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. 4d ago First seen · 85 lines · 43 tokens per session scan A a01494b1deba

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository nunosoarescsw/copilot-agentic-workshop (1 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 677 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.