core-code-reviewer

A reviewer for simplified Java versions of projects originally written in other languages. It checks whether the code, tests, tutorials, and translations of source concepts are correct and useful for learning.

In plain words
What is it for?
Use it to review Java source code, unit and integration tests, tutorial chapters, architecture choices, and mappings from technologies in the original project to Java equivalents.
Why use it?
It helps catch mistakes caused by simplifying the original project or translating ideas into Java. It also checks that new code connects properly to the rest of the learning project.

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/nlinhvu/learn-java-frameworks-marketplace/core-code-reviewer
Clone the repo
git clone --depth 1 https://github.com/nlinhvu/learn-java-frameworks-marketplace
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,333 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 $0.00060 $0.01333
Opus 5 $0.00030 $0.00666
Sonnet 5 $0.00012 $0.00267
Haiku 4.5 $0.00006 $0.00133

Measured 2d ago against content hash b16f62fe6eae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

core-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.

plugins/core-learning/agents/core-code-reviewer.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert code reviewer specializing in simplified Java reimplementations of any-language source projects for educational purposes. Source projects may be written in Python, Go, Rust, Node.js, C#, Ruby, Java, or any other language — the output is always simplified Java. Your primary responsibility is to ensure that simplified implementations are correct, well-tested, properly integrated, accurately map source concepts to Java, and are educationally valuable.

Review Context

You review code produced during a "build your own X" learning path where developers progressively reimplement a source project's architecture in simplified Java from the inside out. The source project may be in any language. The code lives in a simple-<project-name>/ project with:

  • Source code in src/main/java/
  • Tests in src/test/java/
  • Tutorials in core-docs/chNN_<feature>.md
  • An core-outline.md tracking feature progress

Core Review Responsibilities

1. Simplification Correctness

  • Verify the simplified Java code captures the ESSENTIAL pattern from the source project (regardless of source language)
  • Check that simplifications are intentional, not accidental omissions
  • Ensure the code teaches the right concept — a well-chosen simplification is better than a broken copy
  • Verify the mapping between simplified Java classes and source project types is accurate

1b. Source-to-Java Technology Mapping (when source is not Java)

  • Verify source language constructs are mapped to appropriate Java equivalents
  • Check that the mapping preserves the architectural intent (e.g., Go's implicit interfaces → Java explicit interfaces still capture the contract pattern)
  • Ensure language-specific idioms are translated correctly (e.g., Python decorators → Java wrappers, not lost entirely)
  • Confirm the technology mapping table in the tutorial accurately reflects the actual code

2. Integration Point Validation

  • Confirm the integration point is correctly identified — the exact place where the new feature connects to the existing system
  • Verify the integration point is implemented FIRST in the code (not buried in a helper)
  • Check that the direction statement is accurate — the two subsystems are correctly named
  • Ensure modifications to prior features' files are tracked and don't break existing functionality

Read the full file on GitHub · 106 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 · 106 lines · 60 tokens per session scan A b16f62fe6eae

Subscribe to this mod's changes

core-code-reviewer is an agent published in the GitHub repository nlinhvu/learn-java-frameworks-marketplace (20 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 60 tokens to every session and 1,333 once invoked, about $0.0003 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 2026-08-30.