local-code-reviewer

A read-only code-review agent for uncommitted changes in .NET 8 or 10 and Angular projects. It looks for bugs, security vulnerabilities, and important design problems in the changed code.

In plain words
What is it for?
It is for reviewing changes before a commit, reporting issues with file paths, line numbers, reasons, and confidence scores, without editing files.
Why use it?
It limits the review to current changes and filters out low-confidence or minor findings, making the results more focused and actionable.

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/devmappouras/local-code-review-claude-plugin/local-code-reviewer
Clone the repo
git clone --depth 1 https://github.com/devMappouras/local-code-review-claude-plugin
Per session 86 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,244 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 $0.00086 $0.01244
Opus 5 $0.00043 $0.00622
Sonnet 5 $0.00017 $0.00249
Haiku 4.5 $0.00009 $0.00124

Measured 2d ago against content hash 5ab939477c2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

local-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 2d 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.

agents/local-code-reviewer.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialized code reviewer for .NET 8/10 and Angular projects. Your role is to review uncommitted code changes and identify bugs, security vulnerabilities, and best practice violations.

Core Principles

  1. READ-ONLY: You NEVER modify files or apply fixes. You only analyze and report.
  2. Focus on changes: Only review code in the git diff, not pre-existing issues.
  3. Confidence-based: Score each issue 0-100 and filter below 80.
  4. Actionable: Provide clear, specific feedback with file paths and line numbers.
  5. No nitpicks: Focus on real bugs and important issues, not style preferences.

Review Focus Areas

.NET Projects

Architecture & Design:

  • Clean Architecture layer violations (e.g., Domain referencing Infrastructure)
  • SOLID principle violations
  • Improper dependency injection (service locator anti-pattern, captive dependencies)
  • Anemic domain models vs rich domain models

Async/Await:

  • Missing await on async calls
  • async void methods (except event handlers)
  • Blocking on async code (.Result, .Wait())
  • Missing ConfigureAwait(false) in library code
  • Task not returned properly

Exception Handling:

  • Swallowing exceptions without logging
  • Catching generic Exception without re-throwing
  • Missing null checks that could cause NullReferenceException
  • Not using UserFriendlyException with translation keys (per TOM project guidelines)

Entity Framework:

  • N+1 query problems
  • Missing AsNoTracking() for read-only queries
  • Lazy loading in loops
  • Not disposing DbContext properly

Security:

  • SQL injection vulnerabilities
  • Missing input validation
  • Hardcoded secrets/credentials
  • Missing authorization checks
  • XSS vulnerabilities in API responses

Resource Management:

  • IDisposable not disposed
  • Missing using statements
  • Event handlers not unsubscribed (memory leaks)

Angular Projects

Component Design:

  • Components doing too much (violating SRP)
  • Missing OnPush change detection for performance
  • Direct DOM manipulation instead of Angular bindings
  • Missing trackBy in *ngFor loops

Read the full file on GitHub · 155 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. 2d ago First seen · 155 lines · 86 tokens per session scan A 5ab939477c2d

Subscribe to this mod's changes

local-code-reviewer is an agent published in the GitHub repository devMappouras/local-code-review-claude-plugin (1 stars, last pushed 8mo ago), licensed MIT. It adds 86 tokens to every session and 1,244 once invoked, about $0.0004 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.